[R] probit analysis with natural response
Dear all,
I have try to use mle() from package stats4 to estimate parameters of
the following model:
p = Pr(Y = 0) = C + (1 - C)F(x'\beta)
a probit model with natural response.
The log-likelihood function is:
fr - function(c, alpha, beta) {
P - c + (1-c) * pnorm(alpha + beta * x)
P - pmax(pmin(P,1),0)
-(sum(log(choose(n,r))) + sum(r * log(P)) + sum((n -r)* log(1-P)))
}
When give the following dataset:
r - c(3,4,4,3,5,4,5,9,8,11,12,13)
n - rep(15,12)
x - c(0, 1.1, 1.3, 2.0, 2.2, 2.8, 3.7, 3.9, 4.4, 4.8, 5.9, 6.8)
x - log10(x)
And then,
fit - mle((fr), start = list(c =0.2, alpha = 0, beta =0), method = BFGS)
It will give the following error message:
Error in optim(start, f, method = method, hessian = TRUE, ...) :
initial value in 'vmmin' is not finite
However, when I set beta to 0.1, mle() could terminate normally. Set
beta to 0.001 or 5, for example, the above command will give the
following error message:
Error in optim(start, f, method = method, hessian = TRUE, ...) :
non-finite finite-difference value [3]
~~~or [1] when beta set to 5.
What's wrong? And how to improve the above code?
Thanks in advance!
Jinsong Zhao
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Howto reduce number of ticks in X, Y axis while still containing all the data
Gundala Viswanath gundalav at gmail.com writes: I am trying to plot 100 x 100 matrix data in a level plot. The problem I have is that the x/y -axis label in ticks are jumbled together. Thus I want X/Y axis to contain 10 ticks only, yet still plotting all the 100 data. Is there a way to do it? The code I have below doesn't work. Well, the code did not work because you did not provide example data and forgot that levelplot is lattice, but when I add these two lines, it works for me. Scaling is 20,40,..., and all point are shown (hope so, I did not count). Dieter library(lattice) mat.data = matrix(rnorm(100*100),nrow=100) # Corr contains 100x100 matrix corr - cor(t(mat.data), method =pearson) # Plot them levelplot(corr, main=PCC of Top-100 Genes, xlab=Gene, ylab=Gene, scale=list(y=list(tick.number=10)) # Doesn't work ) __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Pointwise Confidence Bounds on Logistic Regression
On Thu, 19 Jun 2008, Bryan Hanson wrote:
Thanks so much to all who offered assistance. I have to say it would have
taken me a long time to figure this out, so I am most grateful. Plus,
studying your examples greatly improves my understanding.
As a follow up, the fit process gives the following error:
Warning messages:
1: In eval(expr, envir, enclos) :
non-integer #successes in a binomial glm!
Is this something I should worry about? It doesn't arise from glm or
glm.fit
It does arise from glm(), which runs the initialization code for the
family. Specifically
binomial()$initialize
expression({
if (NCOL(y) == 1) {
if (is.factor(y))
y - y != levels(y)[1]
n - rep.int(1, nobs)
if (any(y 0 | y 1))
stop(y values must be 0 = y = 1)
mustart - (weights * y + 0.5)/(weights + 1)
m - weights * y
if (any(abs(m - round(m)) 0.001))
warning(non-integer #successes in a binomial glm!)
}
else if (NCOL(y) == 2) {
if (any(abs(y - round(y)) 0.001))
warning(non-integer counts in a binomial glm!)
n - y[, 1] + y[, 2]
y - ifelse(n == 0, 0, y[, 1]/n)
weights - weights * n
mustart - (n * y + 0.5)/(n + 1)
}
else stop(for the binomial family, y must be a vector of 0 and 1's\n,
or a 2 column matrix where col 1 is no. successes and col 2 is
no. failures)
})
You specified a binomial family with responses 0.1 and 0.9. That makes no
sense -- the binomial distribution is for integers. Perhaps you mean 1/10
and 9/10, in which case you needed a weight of 10, but I'm forced to
guess.
Thanks, Bryan
For the record, a final complete working code is appended below.
x - c(1:40)
y1 - c(rep(0.1,10), rep(NA, 10), rep(0.9,20))
y2 - c(rep(0.1,15), rep(NA, 10), rep(0.9,15))
data - as.data.frame(cbind(x,y1,y2))
plot(x, y1, pch = 1, ylim = c(0,1), col = red, main = Logistic Regression
w/Confidence Bounds, ylab = y values, xlab = x values)
points(x, y2, pch = 3, col = blue)
abline(h = 0.5, col = gray)
fit1 - glm(y1~x, family = binomial(link = logit), data, na.action =
na.omit)
fit2 - glm(y2~x, family = binomial(link = logit), data, na.action =
na.omit)
lines(fit1$model$x, fit1$fitted.values, col = red)
lines(fit2$model$x, fit2$fitted.values, col = blue)
## predictions on scale of link function
pred1 - predict(fit1, se.fit = TRUE)
pred2 - predict(fit2, se.fit = TRUE)
## constant for 95% confidence bands
## getting two t values is redundant here as fit1 and fit2
## have same residual df, but the real world may be different
res.df - c(fit1$df.residual, fit2$df.residual)
## 0.975 because we want 2.5% in upper and lower tail
const - qt(0.975, df = res.df)
## confidence bands on scale of link function
upper1 - pred1$fit + (const[1] * pred1$se.fit)
lower1 - pred1$fit - (const[1] * pred1$se.fit)
upper2 - pred2$fit + (const[2] * pred2$se.fit)
lower2 - pred2$fit - (const[2] * pred2$se.fit)
## bind together into a data frame
bands - data.frame(upper1, lower1, upper2, lower2)
## transform on to scale of response
bands - data.frame(lapply(bands, binomial(link = logit)$linkinv))
## plot confidence bands
lines(fit1$model$x, bands$upper1, col = pink)
lines(fit1$model$x, bands$lower1, col = pink)
lines(fit2$model$x, bands$upper2, col = lightblue)
lines(fit2$model$x, bands$lower2, col = lightblue)
On 6/19/08 12:28 PM, Gavin Simpson [EMAIL PROTECTED] wrote:
On Thu, 2008-06-19 at 10:42 -0400, Bryan Hanson wrote:
[I've ommitted some of the conversation so far...]
E.g. in a logistic model, with (say) eta = beta_0 + beta_1*x one may
find, on the
linear predictor scale, A and B (say) such that P(A = eta = B) = 0.95.
Then P(expit(A) = expit(eta) = expit(B)) = 0.95, which is exactly
what is wanted.
I think I follow the above conceptually, but I don't know how to implement
it, though I fooled around (unsuccessfully) with some of the variations on
predict().
I'm trying to learn this in response to a biology colleague who did
something similar in SigmaPlot. I can already tell that SigmaPlot did a lot
of stuff for him in the background. The responses are 0/1 of a particular
observation by date. The following code simulates what's going on (note
that I didn't use 0/1 since this leads to a recognized condition/warning of
fitting 1's and 0's. I've requested Brian's Pattern Recognition book so I
know what the problem is and how to solve it). My colleague is looking at
two populations in which the LD50 would differ. I'd like to be able to
put the pointwise confidence bounds on each curve so he can tell if the
populations are really different.
By the way, this code does give a (minor?) error from glm (which you will
see).
Can you make a suggestion about how to get those confidence bounds on
there?
Also, is a probit link more appropriate here?
Thanks, Bryan
x - c(1:40)
y1 - c(rep(0.1,10), rep(NA, 10), rep(0.9,20))
y2 - c(rep(0.1,15), rep(NA, 10), rep(0.9,15))
data -
Re: [R] create .exe file with R?
See 'Writing R Extensions' On Thu, 19 Jun 2008, Hua Li wrote: Dear all, I'm writing to check with you whether there is a way to create .exe file(or something like that) with R. Now working on creating a program to take inputs from users (with tcl/tk), I would appreciate any idea to make the program run on its own rather than every time having to run my source code in R. Thanks! Hua __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] how to write symbol (nabla) in R graph
Nuno Prista nmprista at fc.ul.pt writes: Can anyone of you tell me how to write a nabla symbol in an R graph? I have not tested it, but according to http://www.gnu.org/software/plotutils/manual/html_chapter/plotutils_10.html nabla is Unicode [0321] Check documentation on plothmath how to use it. Note: the documents cited in plotmath are huge, and it would be nice to have something like the gnu-reference I google for a short list. Dieter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Programming Concepts and Philosophy
Simon Blomberg wrote: I try to use a functional programming style. I define functions within functions when it is helpful in terms of information hiding. I avoid writing functions with side-effects as much as possible, so the only communication of the called function with the caller function is through the arguments and the returned value. I try to keep the code as simple and clear as possible (this is one of the things I fail at most). An appropriate amount of comments is also useful, especially when returning to old code after a long break. OOP is useful for really big projects, but I find OOP unnecessarily complicated for small jobs. I found Code Complete, by McConnell (http://www.cc2e.com/) to be very helpful. I'm sure there are other books around with similar tips. Before I switched to R, I used XLisp-Stat. I found learning Lisp to be a really good way to learn good programming practices. Good Lisp code is the closest thing you can get to poetry in computer programming. Lisp Style Design, by Miller and Benson was helpful. I'd like to see an S Style Design. i support this view. i found sicp (structure and interpretation of computer programs, by abelson sussman, a real classic in the field) particularly enlightening, although it certainly is a bit outdated in many respects -- but just a bit. functional programming style is great, but beware -- r will create (afaik, experts please correct me if this is wrong) a deep copy of about any object you send as an argument to a function (if only when it is actually used inside the function), and the result may be that the more beautiful the code, the more the performance sucks. in pure functional programming, a function cannot change any part of the object passed to it as an argument, so there's no need for making a local copy. in r everything can happen as you can deparse the call to a function inside the function body, and you can never tell whether the object you pass to a function will be changed or not, given only the function's signature. vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] R web site-Useability finding varous bits of documentation
hadley wickham h.wickham at gmail.com writes: Note that the R-project page (www.r-project.org) and CRAN are two things, albeit closely related. CRAN is for DOWNLOADing, including free contributed docs. So that is the main reason, contrib.docs are not there in the www.r-project.org sidebar. Why does there need to be two sites? I agree. I never understood this division, and it adds a lot of confusion because parts are repeated. Dieter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] YAPMQ - Yet Another PlotMath Question
Peter Dalgaard p.dalgaard at biostat.ku.dk writes: Notice that paste()ing two expressions does not yield an expression result. Instead, it deparses both arguments and gives a character string. May I suggest to add this sentence to the expression documentation? That section is VERY terse. Dieter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Howto reduce number of ticks in X, Y axis while still containing all the data
Hi Dieter, I'm aware of the need to include lattice library. I just didn't show it. However my code still cant' produce the same results as yours. My data.mat contain this form of output print(data.matrix) 11145 3545 8951 11097 16599 11100 8566 .. (upto 100 more) 11145 1.000 0.9979445 0.9966705 0.9855180 0.9775806 0.9949439 0.9579916 3545 0.9979445 1.000 0.9973328 0.9910627 0.9847413 0.9947414 0.9521648 8951 0.9966705 0.9973328 1.000 0.9882817 0.9829629 0.9938390 0.9558376 11097 0.9855180 0.9910627 0.9882817 1.000 0.9969120 0.9846531 0.9490246 16599 0.9775806 0.9847413 0.9829629 0.9969120 1.000 0.9785536 0.9383424 (up to 100 more) Which is different from yours, that gives: [,1] [,2] [,3] [,4] [,5] [1,] 1.00 0.1348954834 0.0751601237 0.0348865551 -0.2111789755 [2,] 0.1348954834 1.00 0.0543903623 -0.0183413605 -0.1684300250 [3,] 0.0751601237 0.0543903623 1.00 0.1070384198 -0.0598198329 [4,] 0.0348865551 -0.0183413605 0.1070384198 1.00 0.0632082205 [5,] -0.2111789755 -0.1684300250 -0.0598198329 0.0632082205 1.00 Can you suggest how can I over come this problem? - Gundala Viswanath Jakarta - Indonesia On Fri, Jun 20, 2008 at 3:38 PM, Dieter Menne [EMAIL PROTECTED] wrote: Gundala Viswanath gundalav at gmail.com writes: I am trying to plot 100 x 100 matrix data in a level plot. The problem I have is that the x/y -axis label in ticks are jumbled together. Thus I want X/Y axis to contain 10 ticks only, yet still plotting all the 100 data. Is there a way to do it? The code I have below doesn't work. Well, the code did not work because you did not provide example data and forgot that levelplot is lattice, but when I add these two lines, it works for me. Scaling is 20,40,..., and all point are shown (hope so, I did not count). Dieter library(lattice) mat.data = matrix(rnorm(100*100),nrow=100) # Corr contains 100x100 matrix corr - cor(t(mat.data), method =pearson) # Plot them levelplot(corr, main=PCC of Top-100 Genes, xlab=Gene, ylab=Gene, scale=list(y=list(tick.number=10)) # Doesn't work ) __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] colnames of a column
have you read the docs? Yes, I'm reading the manual An Introduction to R.. start with ?`[` Ok...I haven't read it. Thanks. Alfredo __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] plot function
dear userRs, I am deeply ashamed asking you this very basic question, but I did neither get it online nor by the S/R-literature I have. I simply want to plot the values of a COUPLE of vectors within one graph - in concrete a couple of time series, a couple of distributions and some stacked area graphs. I am higly convinced, that there are dozens of solutions. Could you please recommend me one? All the best, Norbert __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] how to write symbol (nabla) in R graph
On Fri, 20 Jun 2008, Dieter Menne wrote: Nuno Prista nmprista at fc.ul.pt writes: Can anyone of you tell me how to write a nabla symbol in an R graph? We need to know what is meant by 'nabla': http://en.wikipedia.org/wiki/Nabla_symbol tries to disambiguate. I have not tested it, so others are left to find your errors for you. but according to http://www.gnu.org/software/plotutils/manual/html_chapter/plotutils_10.html nabla is Unicode [0321] U+0321 is COMBINING PALATALIZED HOOK BELOW ! You have misread that document, which is about Hershey encodings not Unicode. Check documentation on plothmath how to use it. Perhaps you meant ?Hershey ? Note: the documents cited in plotmath are huge, and it would be nice to have something like the gnu-reference I google for a short list. Like the reference http://www.stat.auckland.ac.nz/~paul/R/CM/AdobeSym.html ? The Gnuplot reference you cite does qualify as 'huge' and you have demonstrated how unclear it is. ?plotmath has both the definitive documentation and a reference to a short table (added by Paul Murrell at my suggestion). Steve Ellison's answer is Unicode U+2207 via the symbol font. That is 'Nabla' (capitalized) according to http://www.alanwood.net/unicode/mathematical_operators.html although the Adobe glyph name is 'gradient'. To summarize, do one of Use \xd1 in font = 5 Use plotmath with symbol(\xd1) (or equivalent) Use \u2207 on systems that support UTF-8 (and with a font and graphics device that supports this). E.g. plot(1:5, type=n) text(1,1, \xd1, font=5) text(2,2, expression(symbol(\xd1))) text(3,3, \u2207) Depending on the locale and graphics device (and version of R) each of these may or may not work -- the first is probably the most reliable. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Some help with dates.
Hey, I'm new to R but familiar with other programming languages. Basically, I want to store an array of dates. For each of these dates I want to store only the day of the week and the hour. So for example: Monday 12 would be Monday at 12 o'clock and Tuesday 20 would be Tuesday at 8 p.m. Alternatively it could be stored as 0-6 for Sunday to Saturday. So Tuesday at 11 a.m. would be something like 2 11. These dates don't need to be stored exactly like I have written. I just would like to know how R would store a day of the week combined with an hour in a variable. Thanks, Paul [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] plot function
Norbert NEUWIRTH norbert.s.neuwirth at univie.ac.at writes: I am deeply ashamed asking you this very basic question, but I did neither get it online nor by the S/R-literature I have. I simply want to plot the values of a COUPLE of vectors within one graph - in concrete a couple of time series, a couple of distributions and some stacked area graphs. I am higly convinced, that there are dozens of solutions. Could you please recommend me one? It would be good if you provide a data set and an example that comes close to what you want. With standard graphic, check the use of lines instead of plot. And for lattice, have a look at http://dsarkar.fhcrc.org/lattice/book/figures.html for example Fig 15.12 is a bit similar to your request. Dieter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] How/When to use :: and :::?
Hi Dear R users, I check help(Syntax) but I still don't know how to use :: and ::: and when I should use it. Can anyone give me a answer? Thanks in advance Chunhao Tu __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How/When to use :: and :::?
[EMAIL PROTECTED] wrote: Hi Dear R users, I check help(Syntax) but I still don't know how to use :: and ::: and when I should use it. Can anyone give me a answer? Thanks in advance ?`::` vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Plotting barplot and scatterplot on same device - x-axis problem
Hi R-users I'm a relative newbie and uses R mostly for graphical purpose. I have a layout problem when plotting a scatterplot and a barplot using par(new=TRUE). The baseline of the x-axis is not positioned equal for the two plotting functions (see picture) and I have been unable to find out how this is changed. http://www.nabble.com/file/p18025066/pic.jpeg I have added the script if this is of interrest: par(mar = c(7, 4, 4, 2) + 0.1) barplot(rbind(data$Asn,data$Glu,data$NH3), beside=T, axes=TRUE, xlim=c(0,57), ylim=c(0,10)) par(new=TRUE) plot(1:14,data$Acidification.time, axes=FALSE, type=b, xlab=, ylab=, xlim=c(0.3,14.7), ylim=c(6,8)) axis(1,pos=6, labels=FALSE, at=c(0.3,1:14,14.7)) text(1:14, par(usr)[3], srt = 90, adj = 1, labels = data$Month, xpd = TRUE) axis(4,pos=14.7) All help will be greatly appreciated -- View this message in context: http://www.nabble.com/Plotting-barplot-and-scatterplot-on-same-device---x-axis-problem-tp18025066p18025066.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Some help with dates.
Check out 'POSIXlt'. This should provide a hint as to how you can do it:
?as.POSIXlt
x - as.POSIXlt('2008-03-04 11:00')
x
[1] 2008-03-04 11:00:00 GMT
unlist(x)
sec min hour mday mon year wday yday isdst
0 011 4 2 108 263 0
?POSIXlt
myDate - paste(x$wday, x$hour)
myDate
[1] 2 11
On Fri, Jun 20, 2008 at 4:35 AM, Paul Fisch [EMAIL PROTECTED] wrote:
Hey,
I'm new to R but familiar with other programming languages.
Basically, I want to store an array of dates. For each of these dates I
want to store only the day of the week and the hour. So for example:
Monday 12 would be Monday at 12 o'clock and Tuesday 20 would be Tuesday
at 8 p.m.
Alternatively it could be stored as 0-6 for Sunday to Saturday. So Tuesday
at 11 a.m. would be something like 2 11.
These dates don't need to be stored exactly like I have written. I just
would like to know how R would store a day of the week combined with an hour
in a variable.
Thanks,
Paul
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
--
Jim Holtman
Cincinnati, OH
+1 513 646 9390
What is the problem you are trying to solve?
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Problems with basic loop
I'm having trouble creating a looping variable and i can't see wher ethe
problem arises from any hep gratfully appreciated
First create a table
x-table(SURVEY$n_0,exposed)
x
exposed
False True
Under 16241
16-19 689
20-24 190 37
25-34 555 204
35-44 330 87
45-54 198 65
55-64 67 35
65+ 108
Now ectors to store counts and column proportions
xT-x[,True]
xF-x[,False]
yT-x[,True]/colSums(x)
yF-x[,False]/colSums(x)
check length for dynamic looping
length(yT)
[1] 8
now create loop
for(i in 1:length(yT)){
+ pwr.2p2n.test(2*(asin(sqrt(yT[i]))-asin(sqrt(yF[i]))),n1=xT[i],n2=xF[i])
+ }
Error in pwr.2p2n.test(2 * (asin(sqrt(yT[i])) - asin(sqrt(yF[i]))), n1 =
xT[i], :
number of observations in the first group must be at least 2
this confuses me as if i enter the data as values the procedure works?
Thanks in advance
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Using metric units in plots
People, It appears that one has to use Imperial measurements in plot parameters? I can't find any info on using metric units . . Thanks, Phil. -- Philip Rhoades Pricom Pty Limited (ACN 003 252 275 ABN 91 003 252 275) GPO Box 3411 Sydney NSW 2001 Australia E-mail: [EMAIL PROTECTED] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Problem with date-x-axis in lattice
Hello list, i am trying to plot a continous variable y against a date variable, both in one dataframe named df, using a code like this library(lattice) plot1-xyplot(y~date, data=df, type=b) date is of class Date, of course, format=%d.%m.%Y, and spans two calendar years. The problem is that the x-axis is labeled with only one tick mark corresponding to the year with century (%Y) of the second calendar year. Is there a way to define the increment of the x-axis tick marks? Cheers Henning -- [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Programming Concepts and Philosophy
On Fri, Jun 20, 2008 at 09:06:24AM +0200, Wacek Kusnierczyk wrote: Simon Blomberg wrote: I try to use a functional programming style. I define functions within functions when it is helpful in terms of information hiding. I avoid writing functions with side-effects as much as possible, so the only communication of the called function with the caller function is through the arguments and the returned value. I try to keep the code as simple and clear as possible (this is one of the things I fail at most). An appropriate amount of comments is also useful, especially when returning to old code after a long break. OOP is useful for really big projects, but I find OOP unnecessarily complicated for small jobs. I found Code Complete, by McConnell (http://www.cc2e.com/) to be very helpful. I'm sure there are other books around with similar tips. Before I switched to R, I used XLisp-Stat. I found learning Lisp to be a really good way to learn good programming practices. Good Lisp code is the closest thing you can get to poetry in computer programming. Lisp Style Design, by Miller and Benson was helpful. I'd like to see an S Style Design. i support this view. i found sicp (structure and interpretation of computer programs, by abelson sussman, a real classic in the field) particularly enlightening, although it certainly is a bit outdated in many respects -- but just a bit. functional programming style is great, but beware -- r will create (afaik, experts please correct me if this is wrong) a deep copy of about any object you send as an argument to a function (if only when it is actually used inside the function), and the result may be that the more beautiful the code, the more the performance sucks. Not necessarily -- R's promise mechanism quite reasonably ensures that copies of parameter objects are only made upon modifying these objects. However, on a more fundamental programming philosophy note, the fact that R does not allow multiple references to one object is a limitation. One of the fundamental principles of good programming is that there should be a one-to-one correspondence between instances in the program and objects in the real world (problem domain etc.), and having no references makes achieving this difficult (and quite impossible for more complex systems). Best regards, Jan -- +- Jan T. Kim ---+ | email: [EMAIL PROTECTED] | | WWW: http://www.cmp.uea.ac.uk/people/jtk | *-= hierarchical systems are for files, not for humans =-* __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Problems with basic loop
Michael Pearmain wrote:
I'm having trouble creating a looping variable and i can't see wher ethe
problem arises from any hep gratfully appreciated
First create a table
x-table(SURVEY$n_0,exposed)
x
exposed
False True
Under 16241
16-19 689
20-24 190 37
25-34 555 204
35-44 330 87
45-54 198 65
55-64 67 35
65+ 108
Now ectors to store counts and column proportions
xT-x[,True]
xF-x[,False]
yT-x[,True]/colSums(x)
yF-x[,False]/colSums(x)
check length for dynamic looping
length(yT)
[1] 8
now create loop
for(i in 1:length(yT)){
+ pwr.2p2n.test(2*(asin(sqrt(yT[i]))-asin(sqrt(yF[i]))),n1=xT[i],n2=xF[i])
+ }
Error in pwr.2p2n.test(2 * (asin(sqrt(yT[i])) - asin(sqrt(yF[i]))), n1 =
xT[i], :
number of observations in the first group must be at least 2
this confuses me as if i enter the data as values the procedure works?
Thanks in advance
Er, the first row under 16 has a count of 1 in the True column and
it confuses you that you get an error saying that you need at least 2??
But what looks _really_ confused is what you are trying to do in the
first place: The p's you are passing to pwr.2p2n are the empirical
relative frequencies of the individual age groups. This sort of reverses
cause and effect (presumably the exposure does not cause middle age) and
it is pretty odd to compare a particular row in a table with everything
else jumbled together but worse, it is post-hoc power calculation, which
is just a plain Bad Idea (as several people have pointed out before).
--
O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B
c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K
(*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918
~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] [R-pkgs] playwith 0.8-55
playwith package version 0.8-55 is now on CRAN. It provides a GTK+ interface for interacting with R plots. Screenshots of some examples are online at: http://code.google.com/p/playwith/wiki/Screenshots Changes in Version 0.8-55 o argument `parameters`: automatically constructs widgets to control parameter values appearing in the call. o default action when dragging on the plot is zoom. default action on right-click is zoomout. o whether to start in time.mode is determined by looking at the data: TRUE if the x data has a 'ts' or 'zoo' class. o restrict zooming to x axis in time.mode only if a time.vector was not specified. o concept of the main function which accepts typical plot arguments (xlim, ylim, main, etc) -- not necessarily the top-level call. By default, a depth-first search is used to find a function that accepts `xlim` or `...`. o callArg() now uses standard evaluation by default, rather than quoting its argument. Old code will need to be changed! o use RGtk2 rather than gWidgets for edit.call and edit.annotations because gWidgets is very slow. o reasonable guess for data points and labels with ggplot::qplot() o enabled pretty ggplot2 plots (print.ggplot with pretty=TRUE) if using grid package version = 2.7 (older versions had a problem with viewports being popped). o code reorganisation: split tools into separate files; ESS style. The predecessor to this package, plotAndPlayGTK, has been moved to the CRAN archive. -- Felix Andrews / 安福立 PhD candidate Integrated Catchment Assessment and Management Centre The Fenner School of Environment and Society The Australian National University (Building 48A), ACT 0200 Beijing Bag, Locked Bag 40, Kingston ACT 2604 http://www.neurofractal.org/felix/ 3358 543D AAC6 22C2 D336 80D9 360B 72DD 3E4C F5D8 ___ R-packages mailing list [EMAIL PROTECTED] https://stat.ethz.ch/mailman/listinfo/r-packages __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using metric units in plots
On Fri, 20 Jun 2008, Philip Rhoades wrote: People, It appears that one has to use Imperial measurements in plot parameters? I can't find any info on using metric units . . In package grid you can use several different units. In base graphics there are a very few par()s that use inches (and I am pretty sure that comes from the US unit as used in S, not the 'Imperial' one -- see e.g. Wikipedia). But those are rarely used. Also most graphics devices are dimensioned in inches with resolutions in dpi. Function cm() might help you. Thanks, Phil. -- Philip Rhoades Pricom Pty Limited (ACN 003 252 275 ABN 91 003 252 275) GPO Box 3411 Sydney NSW 2001 Australia E-mail: [EMAIL PROTECTED] -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using metric units in plots
Prof Brian Ripley, Prof Brian Ripley wrote: On Fri, 20 Jun 2008, Philip Rhoades wrote: People, It appears that one has to use Imperial measurements in plot parameters? I can't find any info on using metric units . . In package grid you can use several different units. When I search the R site for grid I get: Package ‘grid’ was removed from the CRAN repository In base graphics there are a very few par()s that use inches (and I am pretty sure that comes from the US unit as used in S, not the 'Imperial' one -- see e.g. Wikipedia). But those are rarely used. This is a bit confusing - as far as I can see, ALL the pars use inches? I understand the US effect but shouldn't Metric units be supported directly? Also most graphics devices are dimensioned in inches with resolutions in dpi. Function cm() might help you. Thanks, Phil. -- Philip Rhoades Pricom Pty Limited (ACN 003 252 275 ABN 91 003 252 275) GPO Box 3411 Sydney NSW 2001 Australia E-mail: [EMAIL PROTECTED] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Problems with basic loop
Thanks for the reply Peter,
I did just see that i had put the first error message,(agreed rather an
obvious error) in and not the second i received
Warning message:
In asin(sqrt(yF[i])) : NaNs produced
The reason i'm looking at this is advert exposure True and False.
I'm inspecting age to asses weather or not to weight data in order to
normalise groups for later questions,
The questions that i am looking at later on are not scale based questions
so i cannot perform t-tests on these, so i thought the only viable way was
to look at z-tests for proportions to check for post-hoc differences
Any advise on other methods would be gratefully taken
On Fri, Jun 20, 2008 at 11:14 AM, Peter Dalgaard [EMAIL PROTECTED]
wrote:
Michael Pearmain wrote:
I'm having trouble creating a looping variable and i can't see wher ethe
problem arises from any hep gratfully appreciated
First create a table
x-table(SURVEY$n_0,exposed)
x
exposed
False True
Under 16241
16-19 689
20-24 190 37
25-34 555 204
35-44 330 87
45-54 198 65
55-64 67 35
65+ 108
Now ectors to store counts and column proportions
xT-x[,True]
xF-x[,False]
yT-x[,True]/colSums(x)
yF-x[,False]/colSums(x)
check length for dynamic looping
length(yT)
[1] 8
now create loop
for(i in 1:length(yT)){
+
pwr.2p2n.test(2*(asin(sqrt(yT[i]))-asin(sqrt(yF[i]))),n1=xT[i],n2=xF[i])
+ }
Error in pwr.2p2n.test(2 * (asin(sqrt(yT[i])) - asin(sqrt(yF[i]))), n1 =
xT[i], :
number of observations in the first group must be at least 2
this confuses me as if i enter the data as values the procedure works?
Thanks in advance
Er, the first row under 16 has a count of 1 in the True column and
it confuses you that you get an error saying that you need at least 2??
But what looks _really_ confused is what you are trying to do in the
first place: The p's you are passing to pwr.2p2n are the empirical
relative frequencies of the individual age groups. This sort of reverses
cause and effect (presumably the exposure does not cause middle age) and
it is pretty odd to compare a particular row in a table with everything
else jumbled together but worse, it is post-hoc power calculation, which
is just a plain Bad Idea (as several people have pointed out before).
--
O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B
c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K
(*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918
~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907
--
Michael Pearmain
Senior Statistical Analyst
1st Floor, 180 Great Portland St. London W1W 5QZ
t +44 (0) 2032191684
[EMAIL PROTECTED]
[EMAIL PROTECTED]
Doubleclick is a part of the Google group of companies
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using metric units in plots
On 20/06/2008 6:41 AM, Philip Rhoades wrote: Prof Brian Ripley, Prof Brian Ripley wrote: On Fri, 20 Jun 2008, Philip Rhoades wrote: People, It appears that one has to use Imperial measurements in plot parameters? I can't find any info on using metric units . . In package grid you can use several different units. When I search the R site for grid I get: Package ‘grid’ was removed from the CRAN repository That's because it became a base package. It's distributed with R, not as a separate package on CRAN. In base graphics there are a very few par()s that use inches (and I am pretty sure that comes from the US unit as used in S, not the 'Imperial' one -- see e.g. Wikipedia). But those are rarely used. This is a bit confusing - as far as I can see, ALL the pars use inches? I understand the US effect but shouldn't Metric units be supported directly? I believe only inches are used as physical units, but many of the par() values don't use physical units. There are lines, user coordinates, etc. And plot() makes almost no use of physical units. Duncan Murdoch Also most graphics devices are dimensioned in inches with resolutions in dpi. Function cm() might help you. Thanks, Phil. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] plot function
On 20/06/2008 4:09 AM, Norbert NEUWIRTH wrote: dear userRs, I am deeply ashamed asking you this very basic question, but I did neither get it online nor by the S/R-literature I have. I simply want to plot the values of a COUPLE of vectors within one graph - in concrete a couple of time series, a couple of distributions and some stacked area graphs. I am higly convinced, that there are dozens of solutions. Could you please recommend me one? x - 1:1000 y1 - rnorm(1000) y2 - rexp(1000) ylim - range(c(y1,y2)) plot(x, y1, col=blue, ylim = ylim) points(x, y2, col=red) Duncan Murdoch __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using metric units in plots
Philip Rhoades wrote: This is a bit confusing - as far as I can see, ALL the pars use inches? I understand the US effect but shouldn't Metric units be supported directly? That's one of my complains, but it seems that this will take time. I don't believe it would be too hard to implement metric parameters in every function. Maybe Humanity must lose a few more people in airplane crashes or nuclear plant meltdowns before we ban those unscientific units from use. Alberto Monteiro __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Problems with basic loop
Michael Pearmain wrote:
Thanks for the reply Peter,
I did just see that i had put the first error message,(agreed rather an
obvious error) in and not the second i received
Warning message:
In asin(sqrt(yF[i])) : NaNs produced
Ah. Notwithstanding other remarks, that one would be due to
yT-x[,True]/colSums(x)
The divisor here is a vector of length two!! So every 2nd time you are dividing
with the wrong thing and in one case that gets you a relative frequency bigger
than 1...
The reason i'm looking at this is advert exposure True and False.
I'm inspecting age to asses weather or not to weight data in order to
normalise groups for later questions,
The questions that i am looking at later on are not scale based questions
so i cannot perform t-tests on these, so i thought the only viable way was
to look at z-tests for proportions to check for post-hoc differences
Any advise on other methods would be gratefully taken
I still don't see where the notion of power needs to come in. Shouldn't
the effect size for The questions that I am looking at later enter
somehow? If you just want to know whether there is age-dependent
exposure, how about
chisq.test(SURVEY$n_0,exposed)
(or wilcox.test if you want something that takes the group ordering into
account, or prop.trend.test). If, for better or worse, you want to test
single rows, you could use
chisq.test(SURVEY$n_0 == 35-44,exposed)
etc.
On Fri, Jun 20, 2008 at 11:14 AM, Peter Dalgaard [EMAIL PROTECTED]
wrote:
Michael Pearmain wrote:
I'm having trouble creating a looping variable and i can't see wher ethe
problem arises from any hep gratfully appreciated
First create a table
x-table(SURVEY$n_0,exposed)
x
exposed
False True
Under 16241
16-19 689
20-24 190 37
25-34 555 204
35-44 330 87
45-54 198 65
55-64 67 35
65+ 108
Now ectors to store counts and column proportions
xT-x[,True]
xF-x[,False]
yT-x[,True]/colSums(x)
yF-x[,False]/colSums(x)
check length for dynamic looping
length(yT)
[1] 8
now create loop
for(i in 1:length(yT)){
+
pwr.2p2n.test(2*(asin(sqrt(yT[i]))-asin(sqrt(yF[i]))),n1=xT[i],n2=xF[i])
+ }
Error in pwr.2p2n.test(2 * (asin(sqrt(yT[i])) - asin(sqrt(yF[i]))), n1 =
xT[i], :
number of observations in the first group must be at least 2
this confuses me as if i enter the data as values the procedure works?
Thanks in advance
Er, the first row under 16 has a count of 1 in the True column and
it confuses you that you get an error saying that you need at least 2??
But what looks _really_ confused is what you are trying to do in the
first place: The p's you are passing to pwr.2p2n are the empirical
relative frequencies of the individual age groups. This sort of reverses
cause and effect (presumably the exposure does not cause middle age) and
it is pretty odd to compare a particular row in a table with everything
else jumbled together but worse, it is post-hoc power calculation, which
is just a plain Bad Idea (as several people have pointed out before).
--
O__ Peter Dalgaard �ster Farimagsgade 5, Entr.B
c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K
(*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918
~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907
--
Michael Pearmain
Senior Statistical Analyst
1st Floor, 180 Great Portland St. London W1W 5QZ
t +44 (0) 2032191684
[EMAIL PROTECTED]
[EMAIL PROTECTED]
Doubleclick is a part of the Google group of companies
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
--
O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B
c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K
(*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918
~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] print one character on several lines
?strwrap cat(strwrap(This is a very long character and I want to print it on several lines. This is a very long character and I want to print it on several lines., width=40),sep=\n) This is a very long character and I want to print it on several lines. This is a very long character and I want to print it on several lines. On Thu, Jun 19, 2008 at 5:33 PM, Hua Li [EMAIL PROTECTED] wrote: Hi All, I'm wondering how I can print one large/long character on several lines so that the output will not overflow a page. Setting fill be TRUE or even numbers does not help. An example is below: ipuFile - file(input.txt, w) cat(This is a very long character and I want to print it on several lines. This is a very long character and I want to print it on several lines.,fill = TRUE,file = ipuFile) close(ipuFile) Thanks! Hua __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Jim Holtman Cincinnati, OH +1 513 646 9390 What is the problem you are trying to solve? __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Plotting barplot and scatterplot on same device - x-axis problem
Is there anyway you could include the data so we can see what the problem is- I am getting better at this code reading stuff, but it reduces my time if I can just copy it into my R session and then fiddle. thanks Stephen On Fri, Jun 20, 2008 at 4:39 AM, Thomas Pedersen [EMAIL PROTECTED] wrote: Hi R-users I'm a relative newbie and uses R mostly for graphical purpose. I have a layout problem when plotting a scatterplot and a barplot using par(new=TRUE). The baseline of the x-axis is not positioned equal for the two plotting functions (see picture) and I have been unable to find out how this is changed. http://www.nabble.com/file/p18025066/pic.jpeg I have added the script if this is of interrest: par(mar = c(7, 4, 4, 2) + 0.1) barplot(rbind(data$Asn,data$Glu,data$NH3), beside=T, axes=TRUE, xlim=c(0,57), ylim=c(0,10)) par(new=TRUE) plot(1:14,data$Acidification.time, axes=FALSE, type=b, xlab=, ylab=, xlim=c(0.3,14.7), ylim=c(6,8)) axis(1,pos=6, labels=FALSE, at=c(0.3,1:14,14.7)) text(1:14, par(usr)[3], srt = 90, adj = 1, labels = data$Month, xpd = TRUE) axis(4,pos=14.7) All help will be greatly appreciated -- View this message in context: http://www.nabble.com/Plotting-barplot-and-scatterplot-on-same-device---x-axis-problem-tp18025066p18025066.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Let's not spend our time and resources thinking about things that are so little or so large that all they really do for us is puff us up and make us feel like gods. We are mammals, and have not exhausted the annoying little problems of being mammals. -K. Mullis [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using metric units in plots
On Fri, 2008-06-20 at 09:09 -0200, Alberto Monteiro wrote: Philip Rhoades wrote: This is a bit confusing - as far as I can see, ALL the pars use inches? I understand the US effect but shouldn't Metric units be supported directly? That's one of my complains, but it seems that this will take time. I don't believe it would be too hard to implement metric parameters in every function. But it is not too difficult to do this yourself: in2cm - function(x) return(x * 2.54) cm2in - function(x) return(x * 0.3937008) then use in2cm() or cm2in() depending on what you want to achieve. If you want a margin of 4cm all round the plot: op - par(mai = cm2in(rep(4, 4))) plot(1:10) par(op) HTH G Maybe Humanity must lose a few more people in airplane crashes or nuclear plant meltdowns before we ban those unscientific units from use. Alberto Monteiro __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% Dr. Gavin Simpson [t] +44 (0)20 7679 0522 ECRC, UCL Geography, [f] +44 (0)20 7679 0565 Pearson Building, [e] gavin.simpsonATNOSPAMucl.ac.uk Gower Street, London [w] http://www.ucl.ac.uk/~ucfagls/ UK. WC1E 6BT. [w] http://www.freshwaters.org.uk %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Draw curve for histogram
On Fri, Jun 20, 2008 at 2:47 AM, Anh Tran [EMAIL PROTECTED] wrote: Thanks. I think I've got it. However, the density is plotted, not the frequency. Is there a way to convert the density back to frequency. Thanks a bunch. an easy answer is that hist returns an object which you plot in any way you like. for example, x - rnorm(100) foo - hist(x, plot=FALSE) foo plot(foo$mids, foo$counts, type=l) [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Programming Concepts and Philosophy
However, on a more fundamental programming philosophy note, the fact that R does not allow multiple references to one object is a limitation. One of the fundamental principles of good programming is that there should be a one-to-one correspondence between instances in the program and objects in the real world (problem domain etc.), and having no references makes achieving this difficult (and quite impossible for more complex systems). This is a principle of object oriented programming, not good programming in general! Hadley -- http://had.co.nz/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] replacing segments of vector by their averages
Does this give you the results you are expecting:
m - c(0.3,0.3,0.3,0.1,0.1,0.5,0.5,0.5,0.5,0.15,0.15,0.3,0.5,0.8)
m 0.2
[1] TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE FALSE FALSE
TRUE TRUE TRUE
m.rle - rle(m 0.2)
offsets - 1 + c(0, head(cumsum(m.rle$lengths), -1))
# initialize the output results
results - numeric(length(m.rle$values))
results[] - NA
for (i in seq_along(m.rle$values)){
+ if (m.rle$values[i]){ #numbers 0.2
+ results[i] - mean(m[seq(offsets[i], length=m.rle$lengths[i])])
+ }
+ }
results
[1] 0.300NA 0.500NA 0.533
On Thu, Jun 19, 2008 at 4:55 AM, Daren Tan [EMAIL PROTECTED] wrote:
Given a vector of numeric of length n, I need to find segments that are =
0.2, compute the average of individual segments, and replace the original
values in each segment by their corresponding averages.
For example, there are three segments that are = 0.2, the average of 1st
segment is 0.3, 2nd is 0.5, and the 3rd is 0.533
c(0.3,0.3,0.3,0.1,0.1,0.5,0.5,0.5,0.5,0.15,0.15,0.3,0.5,0.8) [1] 0.30 0.30
0.30 0.10 0.10 0.50 0.50 0.50 0.50 0.15 0.15 0.30 0.50 0.80 m = 0.2 [1]
TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE FALSE FALSE TRUE[13]
TRUE TRUE
_
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
--
Jim Holtman
Cincinnati, OH
+1 513 646 9390
What is the problem you are trying to solve?
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] 3D histogram
Hii.. Could anyone please tell me how to draw 3D histogram in R I have a 20X3 matirx. Now I want 2 of the variable on X and Y axis .And Height of the bar should denote the value of third variable. Thanx Sumit [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] 3D histogram
Try
?hist
-and-
?plot.histogram
You should find what you need there.
Cheers,
Patrick
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of sumit gupta
Sent: Friday, June 20, 2008 8:46 AM
To: r-help@r-project.org
Subject: [R] 3D histogram
Hii..
Could anyone please tell me how to draw 3D histogram in R
I have a 20X3 matirx. Now I want 2 of the variable on X and Y axis .And
Height of the bar should denote the value of third variable.
Thanx
Sumit
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
This email message, including any attachments, is for th...{{dropped:6}}
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Howto access V-base only column in a data frame
on 06/19/2008 11:28 PM Rolf Turner wrote: On 20/06/2008, at 4:07 PM, Moshe Olshansky wrote: If you know the value of k then you could do the following: goodNames - paste(V,1:k,sep=) ind - which(colnames(df) %in% goodNames) df[,ind] (where df is your dataframe). P.S. I won't be surprised if df[,goodNames] is all right too (have not checked). What about df[,grep(^V,names(df))] ? (Leave off the ``^'' if you want any column whose name contains ``V'' (r.t. begins with ``V''). Unless I missed something in the original request, such that the only column to remove is 'var', why not: subset(df, select = -var) ? See ?subset HTH, Marc Schwartz __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Programming Concepts and Philosophy
Maybe I missed it, but I haven't seen in this tread mention of Venables and Ripley (2000) S Programming (Springer). I found it interesting and useful, though I have not used it as much as MASS -- partly because it is more specialized and it's coverage is not as broad. Spencer hadley wickham wrote: However, on a more fundamental programming philosophy note, the fact that R does not allow multiple references to one object is a limitation. One of the fundamental principles of good programming is that there should be a one-to-one correspondence between instances in the program and objects in the real world (problem domain etc.), and having no references makes achieving this difficult (and quite impossible for more complex systems). This is a principle of object oriented programming, not good programming in general! Hadley __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] 3D histogram
Actually, have a look at the rgl package and this link
http://www2.warwick.ac.uk/fac/sci/moac/currentstudents/peter_cock/r/3d_bar_chart/
It points to bar charts, but there is some valuable info on 3D histograms as
well.
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of sumit gupta
Sent: Friday, June 20, 2008 8:46 AM
To: r-help@r-project.org
Subject: [R] 3D histogram
Hii..
Could anyone please tell me how to draw 3D histogram in R
I have a 20X3 matirx. Now I want 2 of the variable on X and Y axis .And
Height of the bar should denote the value of third variable.
Thanx
Sumit
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
This email message, including any attachments, is for th...{{dropped:6}}
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Programming Concepts and Philosophy
I read the Wizard Book too. Absolutely classic! I agree about paying attention to performance, of course. Lisp programmers bend over backwards to write tail-recursive functions for similar performance reasons. So you have to pay attention to the language's idiosyncracies. But the time spent coding is usually much longer than the eventual run time. Learning to write well-designed code can do more to save time, even if the run time is slightly longer than optimal. If run time is an issue, then switching to C or Fortran etc. might be the best bet. But even in that case, using R for prototyping code can provide valueable insights. Cheers, Simon. Simon Blomberg, BSc (Hons), PhD, MAppStat. Lecturer and Consultant Statistician Faculty of Biological and Chemical Sciences The University of Queensland St. Lucia Queensland 4072 Australia T: +61 7 3365 2506 email: S.Blomberg1_at_uq.edu.au Policies: 1. I will NOT analyse your data for you. 2. Your deadline is your problem. The combination of some data and an aching desire for an answer does not ensure that a reasonable answer can be extracted from a given body of data. - John Tukey. -Original Message- From: Wacek Kusnierczyk [mailto:[EMAIL PROTECTED] Sent: Fri 20/06/2008 5:06 PM To: R help Cc: Simon Blomberg Subject: Re: [R] Programming Concepts and Philosophy Simon Blomberg wrote: I try to use a functional programming style. I define functions within functions when it is helpful in terms of information hiding. I avoid writing functions with side-effects as much as possible, so the only communication of the called function with the caller function is through the arguments and the returned value. I try to keep the code as simple and clear as possible (this is one of the things I fail at most). An appropriate amount of comments is also useful, especially when returning to old code after a long break. OOP is useful for really big projects, but I find OOP unnecessarily complicated for small jobs. I found Code Complete, by McConnell (http://www.cc2e.com/) to be very helpful. I'm sure there are other books around with similar tips. Before I switched to R, I used XLisp-Stat. I found learning Lisp to be a really good way to learn good programming practices. Good Lisp code is the closest thing you can get to poetry in computer programming. Lisp Style Design, by Miller and Benson was helpful. I'd like to see an S Style Design. i support this view. i found sicp (structure and interpretation of computer programs, by abelson sussman, a real classic in the field) particularly enlightening, although it certainly is a bit outdated in many respects -- but just a bit. functional programming style is great, but beware -- r will create (afaik, experts please correct me if this is wrong) a deep copy of about any object you send as an argument to a function (if only when it is actually used inside the function), and the result may be that the more beautiful the code, the more the performance sucks. in pure functional programming, a function cannot change any part of the object passed to it as an argument, so there's no need for making a local copy. in r everything can happen as you can deparse the call to a function inside the function body, and you can never tell whether the object you pass to a function will be changed or not, given only the function's signature. vQ [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] 3D histogram
Maybe I'm missing something, but where is the 3D here?
My tip is hist3d in package rgl. But there might be others,
it might worth to search the archive, I remember seeing this
question once.
Gabor
On Fri, Jun 20, 2008 at 08:55:36AM -0400, Richardson, Patrick wrote:
Try
?hist
-and-
?plot.histogram
You should find what you need there.
Cheers,
Patrick
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of sumit gupta
Sent: Friday, June 20, 2008 8:46 AM
To: r-help@r-project.org
Subject: [R] 3D histogram
Hii..
Could anyone please tell me how to draw 3D histogram in R
I have a 20X3 matirx. Now I want 2 of the variable on X and Y axis .And
Height of the bar should denote the value of third variable.
Thanx
Sumit
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
This email message, including any attachments, is for ...{{dropped:11}}
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Problem in Binning of a data set
sumit gupta [EMAIL PROTECTED] napsal dne 20.06.2008 14:44:52: Hii.. Could you please tell me how to draw 3D histogram in R I have a 20X3 matirx. Now I want 2 of the variable on X and Y axis .And Height of the bar should denote the value of third variable. See scatterplot3d, image, contour, persp and maybe some others. However I am not sure if 3D hist like in Excel can be plotted directly in R. For various graphing options see http://addictedtor.free.fr/graphiques/thumbs.php Regards Petr Thanx Sumit __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Optim() violates constraints
Zornitsa Luleva zornitsa.luleva at gmail.com writes: Hi, I am using the mle2 method of the package 'bbmle'. The method is calling as far as I understood it the optim method L-BFGS-B (this is the method I use). The latter one allows the user to impose box constraints on the variables, i.e. to give lower and upper bounds. It is important that the initial values satisfy the constraints. In my problem, it is the case. I do not know if there is something else to watch for, but the algorithm violates the constraints that I have given and therefore, my algorithm is not working. Do you have any idea what I can do about it? Thank you very much in advance! Zoe Well, bbmle is my package so technically you should be writing to me (bolker at ufl.edu) and not the list about it, but ... it's actually an optim() issue. Various people have hit this kind of problem in rare circumstances. http://bugs.r-project.org/cgi-bin/R/Analyses?id=3325;user=guest http://finzi.psych.upenn.edu/R/Rhelp02a/archive/13004.html http://finzi.psych.upenn.edu/R/Rhelp02a/archive/124619.html http://finzi.psych.upenn.edu/R/Rhelp01/archive/15859.html The usual advice is (1) to use the parscale option within the control argument to make sure the problem is scaled properly (this will usually fix most L-BFGS-B problems), (2) if necessary set the bounds just a little bit inside the true constraints. If this doesn't fix the problem, please post (as suggested in the posting guide) a minimal, self-contained, reproducible example ... Ben Bolker __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Multiple assign()
Hi,
Apologies in advance if this has been asked before, but I couldn't find
quite the same question
I'm trying to assign multiple values from a list into an environment. At the
moment, I'm doing this using 'mapply' but finding it slower than I would
like.
Is there a (quicker) function that will assign multiple values in a single
go (I guess, the analogue to 'mget')?
Crispin
This email is confidential and intended solely for the u...{{dropped:12}}
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] reformatting R scripts for htmlize()
On Wed, 2008-06-18 at 11:49 +0200, Agustin Lobo wrote: Hi! I have a bunch of (mainly class) R scripts that I would like to convert into html pages (although if someone thinks that what I want to do is easier with latex or pdf, please tell me). Considering the format of my files, htmlize() seems the best option. The only problem is that I would need to write graphics to a file, thus converting parts like: plot(sel$hora, sel$COD_SP_C) #and check the time intervals plot(mishdift(sel$hora)) into: png(1.png);plot(sel$hora, sel$COD_SP_C);dev.off() #and check the time intervals png(2.png);plot(mishdift(sel$hora));dev.off() Any ideas on how to write an script (could be done in R itself?) that would automatically modify the current script into a htmlize-friendly script? One problem is that while R accepts png() providing a default name for the png file, htmlize() fails unless a name is provided. Hi Agustin, htmlize was intended to provide a simple way to produce output from R scripts that: 1) Looked familiar to the average stats consumer. 2) Required minimal modification from the R script that the average R user would write. The R2html function in the prettyR package, generously contributed by Phillipe Grosjean, goes some way toward integrating graphics into the output, whereas htmlize requires the user to add the graphic device commands. Because more complex commands are hard to anticipate: barpos-barplot(heights,...) dispbars(barpos,heights,...) es-emptyspace(...) legend(...) just writing a function that looks up the names of plotting functions and tries to add graphic device commands would only serve for very basic plots. One can't even hold the dev.off() until a non-plotting command appears, for these can easily occur within a group of plotting commands as in the above example. I tend to write the graphic device commands into the script, but leave them commented out until I am ready to run htmlize. I'm always happy to listen to suggestions on how the functions in the packages I maintain could be improved, however. Jim __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Plotting barplot and scatterplot on same device - x-axis problem
On Fri, 2008-06-20 at 01:39 -0700, Thomas Pedersen wrote: Hi R-users I'm a relative newbie and uses R mostly for graphical purpose. I have a layout problem when plotting a scatterplot and a barplot using par(new=TRUE). The baseline of the x-axis is not positioned equal for the two plotting functions (see picture) and I have been unable to find out how this is changed. Hi Thomas, You might find that barp in the plotrix package will do what you want as it centers the bars on integral values. Jim __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using metric units in plots
On Fri, 2008-06-20 at 11:26 +0100, Prof Brian Ripley wrote: ... In base graphics there are a very few par()s that use inches (and I am pretty sure that comes from the US unit as used in S, not the 'Imperial' one -- see e.g. Wikipedia). But those are rarely used. My recollection of the Imperial and US units was that inches were the same and only volumetric measures differed (despite the fact that the USA officially adopted decimal measures long ago but didn't get around to using them). Given the fairly rubbery definition of the inch, that coincidence was pretty surprising. And if you think inches are bad, check out points. Jim __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using metric units in plots
And if you think inches are bad, check out points. Not to mention pints Cheers, -p -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Howto reduce number of ticks in X, Y axis while still containing all the data
Gundala Viswanath gundalav at gmail.com writes: I'm aware of the need to include lattice library. I just didn't show it. Examples should be complete and self-running, as the posting guide says. However my code still cant' produce the same results as yours. My data.mat contain this form of output print(data.matrix) 11145 3545 8951 11097 16599 11100 8566 .. (upto 100 more) 11145 1.000 0.9979445 0.9966705 0.9855180 0.9775806 0.9949439 0.9579916 3545 0.9979445 1.000 0.9973328 0.9910627 0.9847413 0.9947414 0.9521648 8951 0.9966705 0.9973328 1.000 0.9882817 0.9829629 0.9938390 0.9558376 11097 0.9855180 0.9910627 0.9882817 1.000 0.9969120 0.9846531 0.9490246 16599 0.9775806 0.9847413 0.9829629 0.9969120 1.000 0.9785536 0.9383424 (up to 100 more) Send me the output of str(data.matrix). Or, much better, try to reproduce your problem with a simulated data set similar to the one I gave you. Dieter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Programming Concepts and Philosophy
On 20 июн, 11:06, Wacek Kusnierczyk [EMAIL PROTECTED] wrote: the result may be that the more beautiful the code, the more the performance sucks. Sad but true. Andrey __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Plotting barplot and scatterplot on same device - x-axis problem
Of course :) - here you go... http://www.nabble.com/file/p18028420/Data.txt Data.txt The data is tab-separated Thanks for the reply -- View this message in context: http://www.nabble.com/Plotting-barplot-and-scatterplot-on-same-device---x-axis-problem-tp18025066p18028420.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] how to write symbol (nabla) in R graph
Dear all, I still need help (I am a newbie to R). I looked on the plotmath help and could not find how Unicode can be used. And I am in a Windows platform which I don't know if it is relevant. Can anyone help? Here is a simple example plot(1:10,1:10) can anyone provide the code to insert a nabla anywhere on it? thanks -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Dieter Menne Sent: Friday, June 20, 2008 3:03 AM To: [EMAIL PROTECTED] Subject: Re: [R] how to write symbol (nabla) in R graph Nuno Prista nmprista at fc.ul.pt writes: Can anyone of you tell me how to write a nabla symbol in an R graph? I have not tested it, but according to http://www.gnu.org/software/plotutils/manual/html_chapter/plotutils_10.html nabla is Unicode [0321] Check documentation on plothmath how to use it. Note: the documents cited in plotmath are huge, and it would be nice to have something like the gnu-reference I google for a short list. Dieter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] fligner.test
Hi all I have a question regarding the Fligner-Killeen test. I am using - a PC with Windows XP (Build 20600.xpsp080413-2111 (Service Pack 3); - the following R version: sessionInfo() R version 2.7.0 (2008-04-22) i386-pc-mingw32 I have a vector LENGTH and a factor RELATION that are distributed like this: table(LENGTH, RELATION) RELATION LENGTH object subject 1 9 51 2 25 18 3 36 23 4 23 14 5 17 13 6 12 7 7 10 5 8 3 7 9 4 3 10 3 5 11 4 2 12 2 0 13 0 2 16 2 1 22 0 1 49 1 0 53 1 0 I wanted to run a Fligner test to see whether the lengths for the two relations differ in terms of their variance. This is what I found, though: # fligner.test(LENGTH[RELATION==subject], LENGTH[RELATION==object]) Fligner-Killeen test of homogeneity of variances data: LENGTH[RELATION == subject] and LENGTH[RELATION == object] Fligner-Killeen:med chi-squared = 18.3552, df = 14, p-value = 0.1911 fligner.test(LENGTH[RELATION==object], LENGTH[RELATION==subject]) Fligner-Killeen test of homogeneity of variances data: LENGTH[RELATION == object] and LENGTH[RELATION == subject] Fligner-Killeen:med chi-squared = 16.8838, df = 13, p-value = 0.2047 fligner.test(LENGTH~RELATION) Fligner-Killeen test of homogeneity of variances data: LENGTH by RELATION Fligner-Killeen:med chi-squared = 0.626, df = 1, p-value = 0.4288 # The order of the vectors etc. changes the results??? Needless to say this does not happen with var.test or ... Is this normal; if so, which one is the one to report? Thx, STG __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] how to write symbol (nabla) in R graph
You appear to have missed https://stat.ethz.ch/pipermail/r-help/2008-June/165435.html On Fri, 20 Jun 2008, Nuno Prista wrote: Dear all, I still need help (I am a newbie to R). I looked on the plotmath help and could not find how Unicode can be used. And I am in a Windows platform which I don't know if it is relevant. Can anyone help? Here is a simple example plot(1:10,1:10) can anyone provide the code to insert a nabla anywhere on it? thanks -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Dieter Menne Sent: Friday, June 20, 2008 3:03 AM To: [EMAIL PROTECTED] Subject: Re: [R] how to write symbol (nabla) in R graph Nuno Prista nmprista at fc.ul.pt writes: Can anyone of you tell me how to write a nabla symbol in an R graph? I have not tested it, but according to http://www.gnu.org/software/plotutils/manual/html_chapter/plotutils_10.html nabla is Unicode [0321] Check documentation on plothmath how to use it. Note: the documents cited in plotmath are huge, and it would be nice to have something like the gnu-reference I google for a short list. Dieter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Programming Concepts and Philosophy
on 06/20/2008 10:04 AM hadley wickham wrote: If you do nothing to your code, in 18 months time its performance will have doubled because computers will have become faster. Your code will not get easier to understand by itself. I suspect a good fortunes candidate... :-) Marc __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Programming Concepts and Philosophy
2008/6/20 hadley wickham [EMAIL PROTECTED]: 2008/6/20 [EMAIL PROTECTED] [EMAIL PROTECTED]: On 20 июн, 11:06, Wacek Kusnierczyk [EMAIL PROTECTED] wrote: the result may be that the more beautiful the code, the more the performance sucks. Sad but true. If you do nothing to your code, in 18 months time its performance will have doubled because computers will have become faster. Your code But that doesn't seem to be true anymore (if we are talking single CPU), and it seems not to have been true for at least a few years (e.g., http://www.eecs.berkeley.edu/Pubs/TechRpts/2006/EECS-2006-183.html for instance, their figure 2 in p. 6). will not get easier to understand by itself. No it won't. Best, R. Hadley -- http://had.co.nz/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Ramon Diaz-Uriarte Statistical Computing Team Structural Biology and Biocomputing Programme Spanish National Cancer Centre (CNIO) http://ligarto.org/rdiaz Phone: +34-91-224-6900 ext. 3019 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] The Green Book and its relevance to R
I bogged down about half way through reading the Green Book, in part because it became increasingly difficult to understand how some of the ideas related to R, as opposed to S (which I have not used). Does any reader know whether there is a document that points out differences between S and R that would be helpful in reading the Green Book? Ideally, perhaps, I need a crib sheet to help relate Programming with data to R, as opposed to S. And, incidentally, in the opinion of those who have read all three, which of the books, blue, green, or white (or maybe V R S programming?), would be most recommended as the next book for one who would move beyond advanced beginner status? (Programming experience in Fortran, APL, Python, small-system assembly language, but not C). Ben Fairbank San Antonio, Texas [EMAIL PROTECTED] [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] fligner.test
Stefan Th. Gries stgries at gmail.com writes: Hi all I have a question regarding the Fligner-Killeen test. I am using - a PC with Windows XP (Build 20600.xpsp080413-2111 (Service Pack 3); - the following R version: sessionInfo() R version 2.7.0 (2008-04-22) i386-pc-mingw32 I have a vector LENGTH and a factor RELATION that are distributed like this: table(LENGTH, RELATION) RELATION LENGTH object subject [snip] fligner.test(LENGTH[RELATION==subject], LENGTH[RELATION==object]) Fligner-Killeen test of homogeneity of variances data: LENGTH[RELATION == subject] and LENGTH[RELATION == object] Fligner-Killeen:med chi-squared = 18.3552, df = 14, p-value = 0.1911 fligner.test(LENGTH[RELATION==object], LENGTH[RELATION==subject]) Fligner-Killeen test of homogeneity of variances data: LENGTH[RELATION == object] and LENGTH[RELATION == subject] Fligner-Killeen:med chi-squared = 16.8838, df = 13, p-value = 0.2047 fligner.test(LENGTH~RELATION) Fligner-Killeen test of homogeneity of variances data: LENGTH by RELATION Fligner-Killeen:med chi-squared = 0.626, df = 1, p-value = 0.4288 # The order of the vectors etc. changes the results??? Needless to say this does not happen with var.test or ... Is this normal; if so, which one is the one to report? I think you misunderstood the manual page for fligner.test. I believe that all of the following should give identical results (corresponding to the last test in your examples): fligner.test(list(LENGTH[RELATION==subject], LENGTH[RELATION==object])) fligner.test(list(LENGTH[RELATION==object], LENGTH[RELATION==subject])) fligner.test(LENGTH,RELATION) fligner.test(LENGTH~RELATION) __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] The Green Book and its relevance to R
On Fri, Jun 20, 2008 at 11:33 AM, Ben Fairbank [EMAIL PROTECTED] wrote: I bogged down about half way through reading the Green Book, in part because it became increasingly difficult to understand how some of the ideas related to R, as opposed to S (which I have not used). Does any reader know whether there is a document that points out differences between S and R that would be helpful in reading the Green Book? Ideally, perhaps, I need a crib sheet to help relate Programming with data to R, as opposed to S. And, incidentally, in the opinion of those who have read all three, which of the books, blue, green, or white (or maybe V R S programming?), would be most recommended as the next book for one who would move beyond advanced beginner status? (Programming experience in Fortran, APL, Python, small-system assembly language, but not C). You may want instead to wait for John's forthcoming book Software for Data Analysis: Programming with R. It was supposed to be out by now but there apparently have been delays (John says the delays have not been from his side) and Amazon.com now lists it as being available on Jul. 18 Ben Fairbank San Antonio, Texas [EMAIL PROTECTED] [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Comparison between R and MATLAB
Shubha Vishwanath Karanth [EMAIL PROTECTED] wrote in message news:[EMAIL PROTECTED] Can I get a comparison between R and MATLAB? How is R efficient than MATLAB? Or what are the weaknesses of R compared to MATLAB? Don't forget to compare licenses and cost. Matlab's rigid and unreasonable license is the main reason I use R now. Several years ago the Mathworks refused to let a post doc and me share a MatLab license -- they wanted all single-user licenses to be named users even if each of us only needed MatLab a few hours a month. I asked if they had a math model for what we got for a license, but they didn't care that there was a huge disconnect between what they wanted to sell and our usage needs. I quit using MatLab, converted my project from MatLab to R, and now steer as many people to R as possible. The Mathworks refuses to acknowledge that life-science users of math tools are not like physical science users. Biologists can spend weeks or months on experiments and then occasionally need high-end math tools for analysis. A single shared network MatLab license outside of academia is outrageously expensive. A single network concurrent license for Matlab and the Image processing, Signal Processing and PDE toolboxes costs $18,800 -- I received that quote just yesterday since we still have a few people that use existing MatLab code. MatLab may be a good product, but the Mathworks is unreasonable in how they license it. We are a non-profit, basic life scientific research institute and the Mathworks sells us the same license as for-profit businesses. Only degree-granting universities are eligible for academic pricing apparently. efg Earl F Glynn Bioinformatics Stowers Institute for Medical Research __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Comparison between R and MATLAB
The easy way around that is to create an account, Mathworks, with a common group that all who will use MatLab belong, then su - Mathworks should satisfy the license manager. Clint BowmanINTERNET: [EMAIL PROTECTED] Air Dispersion Modeler INTERNET: [EMAIL PROTECTED] Air Quality Program VOICE: (360) 407-6815 Department of Ecology FAX:(360) 407-7534 USPS: PO Box 47600, Olympia, WA 98504-7600 Parcels:300 Desmond Drive, Lacey, WA 98503-1274 On Fri, 20 Jun 2008, Earl F. Glynn wrote: Shubha Vishwanath Karanth [EMAIL PROTECTED] wrote in message news:[EMAIL PROTECTED] Can I get a comparison between R and MATLAB? How is R efficient than MATLAB? Or what are the weaknesses of R compared to MATLAB? Don't forget to compare licenses and cost. Matlab's rigid and unreasonable license is the main reason I use R now. Several years ago the Mathworks refused to let a post doc and me share a MatLab license -- they wanted all single-user licenses to be named users even if each of us only needed MatLab a few hours a month. I asked if they had a math model for what we got for a license, but they didn't care that there was a huge disconnect between what they wanted to sell and our usage needs. I quit using MatLab, converted my project from MatLab to R, and now steer as many people to R as possible. The Mathworks refuses to acknowledge that life-science users of math tools are not like physical science users. Biologists can spend weeks or months on experiments and then occasionally need high-end math tools for analysis. A single shared network MatLab license outside of academia is outrageously expensive. A single network concurrent license for Matlab and the Image processing, Signal Processing and PDE toolboxes costs $18,800 -- I received that quote just yesterday since we still have a few people that use existing MatLab code. MatLab may be a good product, but the Mathworks is unreasonable in how they license it. We are a non-profit, basic life scientific research institute and the Mathworks sells us the same license as for-profit businesses. Only degree-granting universities are eligible for academic pricing apparently. efg Earl F Glynn Bioinformatics Stowers Institute for Medical Research __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Combine colors and shading lines
Josh, Check into add=TRUE :-) All you need to do is insert add=TRUE to the second chart to superimpose it on the first chart. You might also consider making the second bar a different shade of color rather than using shadding lines, then it would only be one plot. data(HairEyeColor) a - as.table( apply(HairEyeColor, c(1,2), sum) ) a1-a[1:2,] barplot(a1, type=n, col=c(red,red,blue,blue,purple,purple,green,green), beside = TRUE ) barplot(a1, col=1, density=c(0,7,0,7,0,7,0,7), beside = TRUE, add=TRUE ) Josh Roofchop wrote: Hi, basically I am trying to create a grouped bar graph with each group a different color and a bar in each group to have shading lines. Basically combine the 2 graphs created below. Thanks, Josh data(HairEyeColor) a - as.table( apply(HairEyeColor, c(1,2), sum) ) a1-a[1:2,] par(mfcol=c(1,2), bg=white) barplot(a1, type=n, col=c(2,2,4,4,6,6,3,3), beside = TRUE, ) barplot(a1, col=1, density=c(0,7,0,7,0,7,0,7), beside = TRUE, ) http://www.nabble.com/file/p18033630/graph.JPG graph.JPG -- View this message in context: http://www.nabble.com/Combine-colors-and-shading-lines-tp18033630p18035111.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Comparison between R and MATLAB
for many tasks, gnu octave (a 'matlab clone', no offense to gnu folks intended) is quite sufficient, and *free* (+ open source). you can run some of matlab code in octave. you should also check if sage (http://www.sagemath.org/) can do the job for you, it's stuffed with all sorts of maths utilities, with friendly python frontend, etc. and once you're at python's, check numpy, scipy, and matplotlib, which do lots of good work too. all open source, of course. vQ Clint Bowman wrote: The easy way around that is to create an account, Mathworks, with a common group that all who will use MatLab belong, then su - Mathworks should satisfy the license manager. Clint Bowman INTERNET: [EMAIL PROTECTED] Air Dispersion ModelerINTERNET: [EMAIL PROTECTED] Air Quality Program VOICE: (360) 407-6815 Department of Ecology FAX:(360) 407-7534 USPS: PO Box 47600, Olympia, WA 98504-7600 Parcels:300 Desmond Drive, Lacey, WA 98503-1274 On Fri, 20 Jun 2008, Earl F. Glynn wrote: Shubha Vishwanath Karanth [EMAIL PROTECTED] wrote in message news:[EMAIL PROTECTED] Can I get a comparison between R and MATLAB? How is R efficient than MATLAB? Or what are the weaknesses of R compared to MATLAB? Don't forget to compare licenses and cost. Matlab's rigid and unreasonable license is the main reason I use R now. Several years ago the Mathworks refused to let a post doc and me share a MatLab license -- they wanted all single-user licenses to be named users even if each of us only needed MatLab a few hours a month. I asked if they had a math model for what we got for a license, but they didn't care that there was a huge disconnect between what they wanted to sell and our usage needs. I quit using MatLab, converted my project from MatLab to R, and now steer as many people to R as possible. The Mathworks refuses to acknowledge that life-science users of math tools are not like physical science users. Biologists can spend weeks or months on experiments and then occasionally need high-end math tools for analysis. A single shared network MatLab license outside of academia is outrageously expensive. A single network concurrent license for Matlab and the Image processing, Signal Processing and PDE toolboxes costs $18,800 -- I received that quote just yesterday since we still have a few people that use existing MatLab code. MatLab may be a good product, but the Mathworks is unreasonable in how they license it. We are a non-profit, basic life scientific research institute and the Mathworks sells us the same license as for-profit businesses. Only degree-granting universities are eligible for academic pricing apparently. efg Earl F Glynn Bioinformatics Stowers Institute for Medical Research __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- --- Wacek Kusnierczyk, MD PhD Email: [EMAIL PROTECTED] Phone: +47 73591875, +47 72574609 Department of Computer and Information Science (IDI) Faculty of Information Technology, Mathematics and Electrical Engineering (IME) Norwegian University of Science and Technology (NTNU) Sem Saelands vei 7, 7491 Trondheim, Norway Room itv303 Bioinformatics Gene Regulation Group Department of Cancer Research and Molecular Medicine (IKM) Faculty of Medicine (DMF) Norwegian University of Science and Technology (NTNU) Laboratory Center, Erling Skjalgsons gt. 1, 7030 Trondheim, Norway Room 231.05.060 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Unexpected Behavior (potentially) in t.test
Greetings,
I have stumbled across some unexpected behavior (potential a bug) in, what I
suspect to be R's (2.6.2 on Ubuntu Linux) t.test function; then again the
problem may exist in my code. I have shutdown R and started it back up,
re-run the code and re-experienced the error. I have searched on Google for
the abnormal termination error message (stderr 10 * .Machine$double.eps *
max(abs(mx), abs(my))) stop(data are essentially constant) but only found
one instance, http://tolstoy.newcastle.edu.au/R/e2/help/07/06/18179.html,
but the discussion there did not seem particularly helpful.
I've included all of my code, amateurish though it may be. I have not
isolated the faulty part, and to me it all looks pretty simple, so I'm not
sure where I'm going wrong. For background, the goal of this code is to run
a simulation to explore the problem space of inflation of Type I error when
decisions to run or not to run more participants are made by preliminary
looks at the data (as in Wagenmakers, 2007). This code is meant to examine
the problem space given that there is no true difference between the groups
(as is the case when both a generated from random draws from the normal
distribution). I run an initial number of subjects in two groups (t1N) then,
if p is .25 on the t-test I add t2N more subjects to each group. Then I
perform the t.test again. If the p was .25 at time 1 I stop. Plainp is
simply storing the p-values from t2 (if it was performed) or from t1 (if t2
was not performed). In the code I provide t1 starts at 16 since this is
about when the problem becomes more frequent. Please note that it takes
quite a long while to fail, and depending on what the true cause is it may
not fail at all. On my system it is failing before t1N advances to 17.
Any suggestions as to how to avoid the error and instructions as to the
cause of it would be appreciated. Thank you for your input and patience.
logit - function(p)
{
# compute and return logit of p;
# if p=.5 then logit==0 else sign(logit)==(p.5)
return( log(p/(1-p)) )
}
antilogit - function(x)
{
# compute and return antilogit of x;
# this returns a proportion p for which logit(p)==x;
return( exp(x)/(1+exp(x)) )
}
plainp - c() #Clear the plainp value
t1Nsim - (100/5) * 1000 * 10 # random chance should provide 1 cases at
t1
contthreshold - .25 #p value below which we run more subjects
t1pvals - rep(NA,t1Nsim) #clear the pvalues
t2pvals - rep(NA,t1Nsim) #clear the pvalues
t1N - 10 #for debugging
t2N - 5 #for debugging
for (t1N in 16:50) #Outer loop testing possible values for t1N
for (t2N in 1:50) #Inner loop testing possible values for t2N
{
print(paste(Checking with ,t1N, initial samples and ,t2N, extra
samples,sep=)) #feedback
for (lcv in 1:t1Nsim) #Run simulation t1Nsim times...
{
if (lcv %% 2 == 0) {print(paste((lcv/t1Nsim)*100,%,sep=))} #feedback
Cgroup - rnorm(t1N) #Initial random draw for Group1
Tgroup - rnorm(t1N) #Initial random draw for Group 2
currentp - t.test(Cgroup,Tgroup)[[p.value]] #Get t1 p value
t1pvals[lcv] - currentp #Store t1 p value
#If p = .05 or = continue threshold then run more subjects
if ((currentp = contthreshold) (currentp = .05)) {
Cgroup - c(Cgroup,rnorm(t2N)) #Add t2N subjects to group 1
Tgroup - c(Tgroup,rnorm(t2N)) #Add t2N subjects to group 2
currentp - t.test(Cgroup,Tgroup)[[p.value]] #Get t2 p value
t2pvals[lcv] - currentp #store t2 p value
}
}
plainp - ifelse(!is.na(t2pvals),{t2pvals},{t1pvals}) #Make sure we are
looking at the right ps
table(t1pvals = .05); round(summary(t1pvals),4) #debugging
hist(t1pvals) #debugging
table(plainp = .05); round(summary(plainp),4) #debugging
hist(plainp, probability=TRUE,main=paste(t1N,then,t2N)) #Histogram of
interest
abline(a=1.00,b=0) #Baseline probability
dev.copy(jpeg,filename=paste(Sim with ,t1N, start samples and ,t2N,
extra samples.jpg,sep=),height=600,width=800,bg=white) # Create the
image
dev.off() #Save the image
chi - rbind(table(t1pvals = .05),table(plainp = .05)) #debugging
chisq.test(chi) #debugging
explore - data.frame(t1=t1pvals,t2=t2pvals,picked=plainp) #debugging
t.test(explore$picked,explore$t1) #debugging
t.test(logit(explore$picked),logit(explore$t1)) #debugging
}
---
Russell Pierce
Psychology Department
Graduate Student - Cognitive
(951) 827-2553
University of California, Riverside, 92521
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Problem with date-x-axis in lattice
On 6/20/08, Henning Wildhagen [EMAIL PROTECTED] wrote: Hello list, i am trying to plot a continous variable y against a date variable, both in one dataframe named df, using a code like this library(lattice) plot1-xyplot(y~date, data=df, type=b) date is of class Date, of course, format=%d.%m.%Y, and spans two calendar years. The problem is that the x-axis is labeled with only one tick mark corresponding to the year with century (%Y) of the second calendar year. Is there a way to define the increment of the x-axis tick marks? Could you provide a reproducible example? In general, the algorithm that computes tick locations for date-time scales often performs inadequately. Presumably the algorithm could be improved, but I don't know how (the current code is ripped off from traditional graphics, which has similar problems). It may be simpler to just specify 'at' locations manually in the 'scales' argument (see ?xyplot). -Deepayan __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Comparison between R and MATLAB
hi, my 0.2$ the rpy python module is excellent, in addition to those Wacek mentioned. another free alternative, particularly for graphics is scilab: http://www.scilab.org/ thanks, kevin - Original Message - From: Wacek Kusnierczyk [EMAIL PROTECTED] Date: Friday, June 20, 2008 2:47 pm Subject: Re: [R] Comparison between R and MATLAB for many tasks, gnu octave (a 'matlab clone', no offense to gnu folks intended) is quite sufficient, and *free* (+ open source). you can run some of matlab code in octave. you should also check if sage (http://www.sagemath.org/) can do the job for you, it's stuffed with all sorts of maths utilities, with friendly python frontend, etc. and once you're at python's, check numpy, scipy, and matplotlib, which do lots of good work too. all open source, of course. vQ Clint Bowman wrote: The easy way around that is to create an account, Mathworks, with a common group that all who will use MatLab belong, then su - Mathworks should satisfy the license manager. Clint BowmanINTERNET: [EMAIL PROTECTED] Air Dispersion Modeler INTERNET: [EMAIL PROTECTED] Air Quality Program VOICE: (360) 407-6815 Department of Ecology FAX:(360) 407-7534 USPS: PO Box 47600, Olympia, WA 98504-7600 Parcels:300 Desmond Drive, Lacey, WA 98503-1274 On Fri, 20 Jun 2008, Earl F. Glynn wrote: Shubha Vishwanath Karanth [EMAIL PROTECTED] wrote in message news:[EMAIL PROTECTED] MAILSRV02.Amba.com... Can I get a comparison between R and MATLAB? How is R efficient than MATLAB? Or what are the weaknesses of R compared to MATLAB? Don't forget to compare licenses and cost. Matlab's rigid and unreasonable license is the main reason I use R now. Several years ago the Mathworks refused to let a post doc and me share a MatLab license -- they wanted all single-user licenses to be named users even if each of us only needed MatLab a few hours a month. I asked if they had a math model for what we got for a license, but they didn't care that there was a huge disconnect between what they wanted to sell and our usage needs. I quit using MatLab, converted my project from MatLab to R, and now steer as many people to R as possible. The Mathworks refuses to acknowledge that life-science users of math tools are not like physical science users. Biologists can spend weeks or months on experiments and then occasionally need high-end math tools for analysis. A single shared network MatLab license outside of academia is outrageously expensive. A single network concurrent license for Matlab and the Image processing, Signal Processing and PDE toolboxes costs $18,800 -- I received that quote just yesterday since we still have a few people that use existing MatLab code. MatLab may be a good product, but the Mathworks is unreasonable in how they license it. We are a non-profit, basic life scientific research institute and the Mathworks sells us the same license as for-profit businesses. Only degree-granting universities are eligible for academic pricing apparently. efg Earl F Glynn Bioinformatics Stowers Institute for Medical Research __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R- project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R- project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- --- Wacek Kusnierczyk, MD PhD Email: [EMAIL PROTECTED] Phone: +47 73591875, +47 72574609 Department of Computer and Information Science (IDI) Faculty of Information Technology, Mathematics and Electrical Engineering (IME) Norwegian University of Science and Technology (NTNU) Sem Saelands vei 7, 7491 Trondheim, Norway Room itv303 Bioinformatics Gene Regulation Group Department of Cancer Research and Molecular Medicine (IKM) Faculty of Medicine (DMF) Norwegian University of Science and Technology (NTNU) Laboratory Center, Erling Skjalgsons gt. 1, 7030 Trondheim, Norway Room 231.05.060 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting- guide.htmland provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing
Re: [R] Problem with date-x-axis in lattice
There is an example in the examples section of ?xyplot.zoo in the zoo package of using panel.axis. It works largely the same way even if you don't use zoo. On Fri, Jun 20, 2008 at 6:06 AM, Henning Wildhagen [EMAIL PROTECTED] wrote: Hello list, i am trying to plot a continous variable y against a date variable, both in one dataframe named df, using a code like this library(lattice) plot1-xyplot(y~date, data=df, type=b) date is of class Date, of course, format=%d.%m.%Y, and spans two calendar years. The problem is that the x-axis is labeled with only one tick mark corresponding to the year with century (%Y) of the second calendar year. Is there a way to define the increment of the x-axis tick marks? Cheers Henning -- [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Programming Concepts and Philosophy
hadley wickham wrote: 2008/6/20 [EMAIL PROTECTED] [EMAIL PROTECTED]: If you do nothing to your code, in 18 months time its performance will have doubled because computers will have become faster. Your code will not get easier to understand by itself. Very nicely put .. and true too! __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Question about nlmer
Hi R user, I have a question about nlmer. Can I specify the multilevel random effects in the the nlmer? For example, level 1 is hospital and level 2 is patient, so nlmer(response~SSfol(Dose,Time,lke,lka,lcl)~(lke+lka+lcl|hospital)~(lke+lka+lcl|patient%in%hospital), data=health, start=c(lke=-2.5,lka=0.5,lcl=-3),verb=1)) I can do it in the nlme but I still don't know how to get it in nlmer! many thanks in advance Chunhao __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] World Ocean Database files
Has anyone written a script or function to read data from NODCs World Ocean Database files? (I know there are simple Fortran and C programs to read these files, but the output is not suitable for easy analysis) Thanks, Franz _ Dr. Franz J. Mueter School of Fisheries and Ocean Sciences, Juneau Center University of Alaska Fairbanks 11120 Glacier Highway Juneau, Alaska 99801-8677 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Plotting barplot and scatterplot on same device - x-axis problem
As an alternative to the other suggestions,
I've found it just as easy to make the bar plot using plot() .
Assuming I've run hist()-sudh, then do
plot(sudh$breaks[1:length(sudh$breaks)-1],sudh$counts,type='h',lwd={pick_a_width_you_like))
Then it's easy to drop some scatterplot points or lines on top of that.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Combine colors and shading lines
Well perhaps we can take the mystery of why it work for me, but not you, off line :-) I'm using R 2.6.1 on a WinXP platform. You could try just using shades of color like this: data(HairEyeColor) a - as.table( apply(HairEyeColor, c(1,2), sum) ) a1-a[1:2,] barplot(a1, type=n, col=c(red,pink,blue,lightblue,purple, lavender,green,lightgreen), beside = TRUE ) -- View this message in context: http://www.nabble.com/Combine-colors-and-shading-lines-tp18033630p18036907.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Comparison between R and MATLAB
Kevin J. Thompson wrote: hi, my 0.2$ the rpy python module is excellent, in addition to those Wacek mentioned. another free alternative, particularly for graphics is scilab: http://www.scilab.org/ for scilab there is the rscilab module, so that we are with r again. vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] World Ocean Database files
Hi Franz: we have a web service that will get you the Pacific. Look at http:// coastwatch.pfel.noaa.gov/erddap/tabledap/pmelWOD5np.html it will show you how to use form the URL request, and by changing the file ender you can change the format. To use in R, you would so something like (say for a csv file): download.file(url=http://coastwatch.pfel.noaa.gov/erddap/tabledap/ WOD5np.csv?SOME CONSTRAINTS, destfile=/users/frans/wodb.csv) wodb-read.csv(file=wodb.csv) There are a variety of different format available. We are essentially reserving in a different way the service provide by the PMEL Dapper service. HTH, -Roy PS - I believe ODV also has access to the WODB, but not directly into R. On Jun 20, 2008, at 1:25 PM, Franz J Mueter wrote: Has anyone written a script or function to read data from NODC’s World Ocean Database files? (I know there are simple Fortran and C programs to read these files, but the output is not suitable for easy analysis) Thanks, Franz _ Dr. Franz J. Mueter School of Fisheries and Ocean Sciences, Juneau Center University of Alaska Fairbanks 11120 Glacier Highway Juneau, Alaska 99801-8677 __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting- guide.html and provide commented, minimal, self-contained, reproducible code. ** The contents of this message do not reflect any position of the U.S. Government or NOAA. ** Roy Mendelssohn Supervisory Operations Research Analyst NOAA/NMFS Environmental Research Division Southwest Fisheries Science Center 1352 Lighthouse Avenue Pacific Grove, CA 93950-2097 e-mail: [EMAIL PROTECTED] (Note new e-mail address) voice: (831)-648-9029 fax: (831)-648-8440 www: http://www.pfeg.noaa.gov/ Old age and treachery will overcome youth and skill. From those who have been given much, much will be expected __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Plotting barplot and scatterplot on same device - x-axis problem
You could try using the arguments type, lwd and lend in the call to plot(). For example: plot(1:10, type=h, lend=2, lwd=10) points((1:10)*1.1, type=b) type=h creates vertical lines under each observation, lwd controls the thickness of the lines, and lend=2 draws square ends on the lines. I hope this helps, Francisco Thomas Pedersen wrote: Hi R-users I'm a relative newbie and uses R mostly for graphical purpose. I have a layout problem when plotting a scatterplot and a barplot using par(new=TRUE). The baseline of the x-axis is not positioned equal for the two plotting functions (see picture) and I have been unable to find out how this is changed. http://www.nabble.com/file/p18025066/pic.jpeg I have added the script if this is of interrest: par(mar = c(7, 4, 4, 2) + 0.1) barplot(rbind(data$Asn,data$Glu,data$NH3), beside=T, axes=TRUE, xlim=c(0,57), ylim=c(0,10)) par(new=TRUE) plot(1:14,data$Acidification.time, axes=FALSE, type=b, xlab=, ylab=, xlim=c(0.3,14.7), ylim=c(6,8)) axis(1,pos=6, labels=FALSE, at=c(0.3,1:14,14.7)) text(1:14, par(usr)[3], srt = 90, adj = 1, labels = data$Month, xpd = TRUE) axis(4,pos=14.7) All help will be greatly appreciated __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] handling the output of strsplit
Hi, Simple question, but I did not figure out how to find the answer on my own (wrong choice of keywords on my part). I have a character variable for time of day that has entries looking like 6h30, 7h40, 12h25, 23h, etc. For the sake of this message, say h = c(3h30, 6h30, 9h40, 11h25, 14h00, 15h55, 23h) I could not figure out how to use chron to import this into times, so I tried to extract the hours and minutes on my own. I used strsplit and got a list: h2 = strsplit(h, h) h2 [[1]] [1] 3 30 [[2]] [1] 6 30 [[3]] [1] 9 40 [[4]] [1] 11 25 [[5]] [1] 14 00 [[6]] [1] 15 55 [[7]] [1] 23 It is where I am stuck. I would have like to extract a vector of hours from this list, and a vector of minutes, to reconstruct a time of day. But the only command I know, unlist, makes a long vector of h, min, h, min, h, min. For this in particular, but lists in general, how can one extract the first item of each element in the list, then the second item of each element, etc.? Thanks in advance, Denis __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] handling the output of strsplit
Denis Chabot wrote: Hi, Simple question, but I did not figure out how to find the answer on my own (wrong choice of keywords on my part). I have a character variable for time of day that has entries looking like 6h30, 7h40, 12h25, 23h, etc. For the sake of this message, say h = c(3h30, 6h30, 9h40, 11h25, 14h00, 15h55, 23h) I could not figure out how to use chron to import this into times, so I tried to extract the hours and minutes on my own. I used strsplit and got a list: h2 = strsplit(h, h) h2 [[1]] [1] 3 30 [[2]] [1] 6 30 [[3]] [1] 9 40 [[4]] [1] 11 25 [[5]] [1] 14 00 [[6]] [1] 15 55 [[7]] [1] 23 It is where I am stuck. I would have like to extract a vector of hours from this list, and a vector of minutes, to reconstruct a time of day. But the only command I know, unlist, makes a long vector of h, min, h, min, h, min. For this in particular, but lists in general, how can one extract the first item of each element in the list, then the second item of each element, etc.? sapply(h2, `[`, 1) [1] 3 6 9 etc. sapply(h2, `[`, 2) [1] 30 30 40 etc. ? `[` vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] omnibus LR in multinomial model
If one estimates a model using multinom, is it possible to perform the
omnibus LR test ( the analogue to omnibus F in linear models ) using
the output
from multinom ? The residual deviance is there but I was hoping I could
somehow pull out the deviance based on just using an intercept ?
Sample code is below from the CAR book but I wasn't sure how to do it
based on that example. Thanks for any insights.
library(car)
library(nnet)
attach(Womenlf)
participation - ordered(partic, levels=c('not.work', 'parttime',
'fulltime'))
print(participation)
mod.multinom - multinom(participation ~ hincome + children)
print(mod.multinom)
print(str(mod.multinom))
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] handling the output of strsplit
Denis Chabot wrote: Hi, Simple question, but I did not figure out how to find the answer on my own (wrong choice of keywords on my part). I have a character variable for time of day that has entries looking like 6h30, 7h40, 12h25, 23h, etc. For the sake of this message, say h = c(3h30, 6h30, 9h40, 11h25, 14h00, 15h55, 23h) I could not figure out how to use chron to import this into times, so I tried to extract the hours and minutes on my own. I used strsplit and got a list: h2 = strsplit(h, h) h2 [[1]] [1] 3 30 [[2]] [1] 6 30 [[3]] [1] 9 40 [[4]] [1] 11 25 [[5]] [1] 14 00 [[6]] [1] 15 55 [[7]] [1] 23 It is where I am stuck. I would have like to extract a vector of hours from this list, and a vector of minutes, to reconstruct a time of day. But the only command I know, unlist, makes a long vector of h, min, h, min, h, min. For this in particular, but lists in general, how can one extract the first item of each element in the list, then the second item of each element, etc.? you can also want to convert this representation to something cron-readable: times(gsub(([0-9]+)h([0-9]*), \\1:0\\2:0, h)) [1] 03:30:00 06:30:00 etc. (the first 0 in the replacement accommodates for missing minutes digits, the second for seconds) vQ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] handling the output of strsplit
We construct a times object by replacing the letter h with a : and then pasting a :00 on the end. Then replace any occurrence of :: with :00: . Its now in the format that times recognizes so we can just convert that to times and apply hours() and minutes() to get the components: library(chron) h2 - times(sub(::, :00:, paste(sub(h, :, h), 00, sep = :))) hours(h2) [1] 3 6 9 11 14 15 23 minutes(h2) [1] 30 30 40 25 0 55 0\ Another possibility is to use gsubfn in package gsubfn. It matches the string such that it captures the hour and minutes in the two backreferences and then pastes them together with a :00 at the end. It then replaces :: with :00: and converts that to times. hours() and minutes() could be used, as before, to get the components. library(gsubfn) times(gsubfn(([^h]+)h(.*), ~ sub(::, :00:, paste(..., 00, sep = :)), h, backref = -2)) [1] 03:30:00 06:30:00 09:40:00 11:25:00 14:00:00 15:55:00 23:00:00 Here is another approach using strapply in the gsubfn package. We use the same pattern but this time convert each component to numeric: times(strapply(h, ([^h]+)h(.*), ~ as.numeric(x) / 24 + sum(as.numeric(y), na.rm = TRUE)/(24*60), backref = -2, simplify = c)) [1] 03:30:00 06:30:00 09:40:00 11:25:00 14:00:00 15:55:00 23:00:00 On Fri, Jun 20, 2008 at 6:14 PM, Denis Chabot [EMAIL PROTECTED] wrote: Hi, Simple question, but I did not figure out how to find the answer on my own (wrong choice of keywords on my part). I have a character variable for time of day that has entries looking like 6h30, 7h40, 12h25, 23h, etc. For the sake of this message, say h = c(3h30, 6h30, 9h40, 11h25, 14h00, 15h55, 23h) I could not figure out how to use chron to import this into times, so I tried to extract the hours and minutes on my own. I used strsplit and got a list: h2 = strsplit(h, h) h2 [[1]] [1] 3 30 [[2]] [1] 6 30 [[3]] [1] 9 40 [[4]] [1] 11 25 [[5]] [1] 14 00 [[6]] [1] 15 55 [[7]] [1] 23 It is where I am stuck. I would have like to extract a vector of hours from this list, and a vector of minutes, to reconstruct a time of day. But the only command I know, unlist, makes a long vector of h, min, h, min, h, min. For this in particular, but lists in general, how can one extract the first item of each element in the list, then the second item of each element, etc.? Thanks in advance, Denis __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] handling the output of strsplit
Most helpful Gabor, Many thanks, Denis Le 08-06-20 à 18:58, Gabor Grothendieck a écrit : We construct a times object by replacing the letter h with a : and then pasting a :00 on the end. Then replace any occurrence of :: with :00: . Its now in the format that times recognizes so we can just convert that to times and apply hours() and minutes() to get the components: library(chron) h2 - times(sub(::, :00:, paste(sub(h, :, h), 00, sep = :))) hours(h2) [1] 3 6 9 11 14 15 23 minutes(h2) [1] 30 30 40 25 0 55 0\ Another possibility is to use gsubfn in package gsubfn. It matches the string such that it captures the hour and minutes in the two backreferences and then pastes them together with a :00 at the end. It then replaces :: with :00: and converts that to times. hours() and minutes() could be used, as before, to get the components. library(gsubfn) times(gsubfn(([^h]+)h(.*), ~ sub(::, :00:, paste(..., 00, sep = :)), h, backref = -2)) [1] 03:30:00 06:30:00 09:40:00 11:25:00 14:00:00 15:55:00 23:00:00 Here is another approach using strapply in the gsubfn package. We use the same pattern but this time convert each component to numeric: times(strapply(h, ([^h]+)h(.*), ~ as.numeric(x) / 24 + sum(as.numeric(y), na.rm = TRUE)/(24*60), backref = -2, simplify = c)) [1] 03:30:00 06:30:00 09:40:00 11:25:00 14:00:00 15:55:00 23:00:00 On Fri, Jun 20, 2008 at 6:14 PM, Denis Chabot [EMAIL PROTECTED] wrote: Hi, Simple question, but I did not figure out how to find the answer on my own (wrong choice of keywords on my part). I have a character variable for time of day that has entries looking like 6h30, 7h40, 12h25, 23h, etc. For the sake of this message, say h = c(3h30, 6h30, 9h40, 11h25, 14h00, 15h55, 23h) I could not figure out how to use chron to import this into times, so I tried to extract the hours and minutes on my own. I used strsplit and got a list: h2 = strsplit(h, h) h2 [[1]] [1] 3 30 [[2]] [1] 6 30 [[3]] [1] 9 40 [[4]] [1] 11 25 [[5]] [1] 14 00 [[6]] [1] 15 55 [[7]] [1] 23 It is where I am stuck. I would have like to extract a vector of hours from this list, and a vector of minutes, to reconstruct a time of day. But the only command I know, unlist, makes a long vector of h, min, h, min, h, min. For this in particular, but lists in general, how can one extract the first item of each element in the list, then the second item of each element, etc.? Thanks in advance, Denis __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Scatter plot transparency
Hi all, I'm putting a few plots together and wondering what format would be best to export a few scatter plots to Illustrator to make a figure. I'm thinking about overlaying some plot in Illustrator, so the export file type has to be transparent for Illustrator (version 10). I tried PNG and TIFF, but it does not seems to have transparency that is recognized by Illustrator (or Photoshop for that matter). EMF (meta data file) on the other hand is very good. The only problem is that every dot on the plot becomes a vector, which slows the program down considerably (I have about 200k dots on a graph). So, is there a good way to import these plot in as picture so I can use them as layer for Illustrator (Photoshop would be fine too). Thank you all. -- Regards, Anh Tran [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Scatter plot transparency
Hi Anh, I don´t know if I understood your point fine. I generate a scatterplot, and open it on adobe photoshop 7.0 with tranparent background. setwd(c:\\temp) x-runif(100) y-rnorm(100) png(transparent_scatterplot.png, 800, 600, bg=transparent) plot(y~x) dev.off() I hope this help, miltinho Brazil On 6/20/08, Anh Tran [EMAIL PROTECTED] wrote: Hi all, I'm putting a few plots together and wondering what format would be best to export a few scatter plots to Illustrator to make a figure. I'm thinking about overlaying some plot in Illustrator, so the export file type has to be transparent for Illustrator (version 10). I tried PNG and TIFF, but it does not seems to have transparency that is recognized by Illustrator (or Photoshop for that matter). EMF (meta data file) on the other hand is very good. The only problem is that every dot on the plot becomes a vector, which slows the program down considerably (I have about 200k dots on a graph). So, is there a good way to import these plot in as picture so I can use them as layer for Illustrator (Photoshop would be fine too). Thank you all. -- Regards, Anh Tran [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] omnibus LR in multinomial model
Is this what you were trying to do?
See intercept model and anova below.
HTH
Steve McKinney
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED]
On Behalf Of [EMAIL PROTECTED]
Sent: Friday, June 20, 2008 3:47 PM
To: [EMAIL PROTECTED]
Subject: [R] omnibus LR in multinomial model
If one estimates a model using multinom, is it possible to perform the
omnibus LR test ( the analogue to omnibus F in linear models ) using
the output
from multinom ? The residual deviance is there but I was hoping I
could
somehow pull out the deviance based on just using an intercept ?
Sample code is below from the CAR book but I wasn't sure how to do it
based on that example. Thanks for any insights.
library(car)
library(nnet)
attach(Womenlf)
participation - ordered(partic, levels=c('not.work', 'parttime',
'fulltime'))
print(participation)
mod.multinom - multinom(participation ~ hincome + children)
print(mod.multinom)
print(str(mod.multinom))
mod.multinom0 - multinom(participation ~ 1)
# weights: 6 (2 variable)
initial value 288.935032
final value 250.246281
converged
anova(mod.multinom, mod.multinom0)
Model Resid. df Resid. Dev TestDf LR stat.
Pr(Chi)
1 1 524 500.4926 NA NA
NA
2 hincome + children 520 422.8819 1 vs 2 4 77.61064
5.551115e-16
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-
guide.html
and provide commented, minimal, self-contained, reproducible code.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] clicking on plot and recording XY coords
Dear all,
I need to run a interactive procedure where the user
will need click on the screen (over a XY plot)
and I need to record the XY coordinate which the
user clicked. Roughly I wrote a short code below.
You see that I suppose that the user will choose
four coordinates inside the region of intersection
between three segmentes. On each click, I would like to
record the position clicked in a vector.
Any help are welcome.
Miltinho
-
number.clicks-4
for (i in 1:number.clicks)
{
plot(0,0, type=n)
seg1-arrows(-0.5,-1,0.5,0, col=1)
seg2-arrows(0,-1,-0.3,0.3, col=2)
seg3-arrows(0.2,-0.7,-0.5,0, col=4)
# here I would like click on PLOT
# and record de XY position
# before go to next aquisition
}
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] clicking on plot and recording XY coords
?locator
On Fri, Jun 20, 2008 at 11:25 PM, milton ruser [EMAIL PROTECTED] wrote:
Dear all,
I need to run a interactive procedure where the user
will need click on the screen (over a XY plot)
and I need to record the XY coordinate which the
user clicked. Roughly I wrote a short code below.
You see that I suppose that the user will choose
four coordinates inside the region of intersection
between three segmentes. On each click, I would like to
record the position clicked in a vector.
Any help are welcome.
Miltinho
-
number.clicks-4
for (i in 1:number.clicks)
{
plot(0,0, type=n)
seg1-arrows(-0.5,-1,0.5,0, col=1)
seg2-arrows(0,-1,-0.3,0.3, col=2)
seg3-arrows(0.2,-0.7,-0.5,0, col=4)
# here I would like click on PLOT
# and record de XY position
# before go to next aquisition
}
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
--
Jim Holtman
Cincinnati, OH
+1 513 646 9390
What is the problem you are trying to solve?
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] clicking on plot and recording XY coords
Thanks Jim.
I included your suggestion on the script and run fine.
But how can I skip (record X and Y as NULL) on some steps?
On this example it don´t occour, but when working with real data I will need
bypass some acquisitions. Is there a way of do it on a for() looping? I
noticed that if I click on right button of mouse the locator() ask for
continue or stop. But some times I just want to record NULL for the
position.
Thanks a lot,
Miltinho
number.clicks-4
my.coords-NULL
for (i in 1:number.clicks)
{
plot(0,0, type=n)
seg1-arrows(-0.5,-1,0.5,0, col=1)
seg2-arrows(0,-1,-0.3,0.3, col=2)
seg3-arrows(0.2,-0.7,-0.5,0, col=4)
coord-locator(1, type=p)
my.coords-rbind(my.coords, cbind(x=coord$x, y=coord$y))
}
my.coords
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] clicking on plot and recording XY coords
Jim,
In fact, if I click stop the for() looping and stop, and I need to
continue on the for().
By other side, is there a way of I ask for the user acquire point (with a
dialog box with Yes or No options), and if the user anwer Yes I collect the
points, otherwise I go for the next step of for() looping?
sorry for do it so trouble.
Kind regards
miltinho
On 6/21/08, jim holtman [EMAIL PROTECTED] wrote:
I am not sure how you would record a NULL. I assume that if you click
'stop', then the result returned is a NULL and you can test for that.
Once you start collecting points, you should not have a NULL in the
series.
On Fri, Jun 20, 2008 at 11:56 PM, milton ruser [EMAIL PROTECTED]
wrote:
Thanks Jim.
I included your suggestion on the script and run fine.
But how can I skip (record X and Y as NULL) on some steps?
On this example it don´t occour, but when working with real data I will
need
bypass some acquisitions. Is there a way of do it on a for() looping? I
noticed that if I click on right button of mouse the locator() ask for
continue or stop. But some times I just want to record NULL for the
position.
Thanks a lot,
Miltinho
number.clicks-4
my.coords-NULL
for (i in 1:number.clicks)
{
plot(0,0, type=n)
seg1-arrows(-0.5,-1,0.5,0, col=1)
seg2-arrows(0,-1,-0.3,0.3, col=2)
seg3-arrows(0.2,-0.7,-0.5,0, col=4)
coord-locator(1, type=p)
my.coords-rbind(my.coords, cbind(x=coord$x, y=coord$y))
}
my.coords
--
Jim Holtman
Cincinnati, OH
+1 513 646 9390
What is the problem you are trying to solve?
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] cutting out numbers from vectors
i have a vector with a string of number e.g [1] 0113001 001130011000 001130012000 001130013000 001130016000 [6] 001130018000 i want a vector with the same numbers except with the last three digits of every factor cut off. e.g [1] 01130010 001130011 001130012 001130013 001130016 [6] 001130018 how do i accomplish this? -- View this message in context: http://www.nabble.com/cutting-out-numbers-from-vectors-tp18034157p18034157.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Combine colors and shading lines
Hi, basically I am trying to create a grouped bar graph with each group a different color and a bar in each group to have shading lines. Basically combine the 2 graphs created below. Thanks, Josh data(HairEyeColor) a - as.table( apply(HairEyeColor, c(1,2), sum) ) a1-a[1:2,] par(mfcol=c(1,2), bg=white) barplot(a1, type=n, col=c(2,2,4,4,6,6,3,3), beside = TRUE, ) barplot(a1, col=1, density=c(0,7,0,7,0,7,0,7), beside = TRUE, ) http://www.nabble.com/file/p18033630/graph.JPG graph.JPG -- View this message in context: http://www.nabble.com/Combine-colors-and-shading-lines-tp18033630p18033630.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Combine colors and shading lines
I tried the add=TRUE but get Warning messages: 1: parameter add could not be set in high-level plot() function Josh HBaize wrote: Josh, Check into add=TRUE :-) All you need to do is insert add=TRUE to the second chart to superimpose it on the first chart. You might also consider making the second bar a different shade of color rather than using shadding lines, then it would only be one plot. data(HairEyeColor) a - as.table( apply(HairEyeColor, c(1,2), sum) ) a1-a[1:2,] barplot(a1, type=n, col=c(red,red,blue,blue,purple,purple,green,green), beside = TRUE ) barplot(a1, col=1, density=c(0,7,0,7,0,7,0,7), beside = TRUE, add=TRUE ) Josh Roofchop wrote: Hi, basically I am trying to create a grouped bar graph with each group a different color and a bar in each group to have shading lines. Basically combine the 2 graphs created below. Thanks, Josh data(HairEyeColor) a - as.table( apply(HairEyeColor, c(1,2), sum) ) a1-a[1:2,] par(mfcol=c(1,2), bg=white) barplot(a1, type=n, col=c(2,2,4,4,6,6,3,3), beside = TRUE, ) barplot(a1, col=1, density=c(0,7,0,7,0,7,0,7), beside = TRUE, ) http://www.nabble.com/file/p18033630/graph.JPG graph.JPG -- View this message in context: http://www.nabble.com/Combine-colors-and-shading-lines-tp18033630p18036266.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Question about copula-GARCH model
Hello everyone, I am learning about copulas and also do some MATLAB/R coding to get better understanding of how copulas work. Recently I have started coding simple copula-GARCH models, that is I fit say AR(1)-GARCH(1,1)-normal models to univariate time series, and then I want to fit the copula (two-stage procedure). What I have problem with is connecting these two estimation stages. After I have estimated AR-GARCH univariate models, what do I take from these models and put into log-likelihood estimation of the copula? Do I take residuals from AR-GARCH models, or do I use estimated parameters of these models to produce samples that I then use in copula estimation stage? I read a few papers that use copula-GARCH models, but it is not clear from them how to estimate copula model. In one of the papers it says: Let u=F(x; theta(x)) and v=F(y; theta(y)), where theta(x) and theta(y) are the vectors of parameters of each marginal distribution... and then one uses u and v in copula log-likelihood minimization. I am so embarassed, but I still do not get it. If I estimated the GARCH model parameters, how do I get these F(x; theta(x)) and F(y; theta(y))? Probably very simple and totally obvious thing, but I just do not get it. :-( Could you please help me understand? How do I do it in MATLAB or R? THanks in advance! -- Jonas Malmros __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Convert character string to number
Hi, I would like to convert a character vector xxx - c(1/2, 1/4) to yyy - c(0.5, 0.25) , but as.numeric didn't work for me. Could anyone give me a hint please? Thanks, Ken __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Adding columns of Aggregates to existing dataframe
Hello, I have a dataframe ID1 ID2 A1B3 A1B4 A1B3 A1B3 A2B1 A2B1 A2B4 A3B2 A3B2 A5B1 A5B1 A5B6 A5B4 A6B2 I want to add extra columns to the dataframe CountID1 and CountID2 which is the actual count of values such as A1 etc ie ID1 ID2CountID1CountID2 A1B3 4 3 A1B4 4 4 A1B3 4 3 A1B3 4 3 A2B1 3 4 A2B1 3 4 A2B4 3 3 A3B2 2 3 A3B2 2 3 A5B1 4 4 A5B1 4 4 A5B6 4 1 A5B4 4 4 A6B2 1 3 I know this can be done by first creating temporary aggregate dataframes then merging with the original. Is there an easier way if i want to calculate many aggregates without having to merge many temp tables. Thanks. -- View this message in context: http://www.nabble.com/Adding-columns-of-Aggregates-to-existing-dataframe-tp18039838p18039838.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] unable to update the matrix values within a function
Hi,
I don't understand why this doesn't work:
matTest - matrix(nrow=3, ncol=3)
testMove - function(I, J){
for(i in 1:I){
for(j in 1:J){
matTest[i, j] - i+j
}
}
}
testMove(2, 3)
matTest
Why the elements of the matrix matTest are still NA? How could I fix it?
Thanks,
Ken
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] stepAIC {MASS}
In a generalized linear model with k covariates, there are 2(kth power) - 1 possible models (excluding interactions). Awhile ago a posting to R-help suggested Model Selection and Multimodel Inference, 2nd ed, by Burnham and Anderson as a good source for understanding model selection. They recommend (page 71) computing AIC differences over all candidate models in the set of possible models. After looking at the help page for stepAIC and checking MASS, I am not certain which AICs are estimated by stepAIC. Comments will be appreciated. Nathan __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
