Are you trying to look at the difference in the gamma distributions due to
variations in the shape and scale parameters? In this case, the following
approach might be more straightforward:
## assign parameter values
params - list(curve1=c(1,1),curve2=c(1,2),curve3=c(1,3))
## define function
I don't know that there is a single function, but you can perhaps apply a
sequence of available functions -
For instance, you can use fitdistr() in library(MASS) to estimate optimal
parameters for a candidate set of distributions; then look at each fit and also
compare the deviance among the
Hi Jason,
From your last e-mail I understood that you use Ubuntu, but it would
help if you mentioned that. But enough comments from me, to a
constructive answer :).
To get access to the most recent versions of R and a selection of the
packages you can add CRAN as a debian repository.
You will have to translate each character string
to a function separately.
Here I have a modified program :
library(zoo)
Z.index - as.Date(sample(12450:15500, 3000))
Z.data - matrix(rnorm(300), ncol = 1)
data1 - zoo(Z.data, Z.index)
fnc = function(data1)
{
selection2 =
...in addition. These are the lines in my sources.list for CRAN:
deb http://cran.at.r-project.org/bin/linux/debian etch-cran/
deb-src http://cran.at.r-project.org/bin/linux/debian etch-cran/
This repository holds R 2.7.1.
cheers,
Paul
Jason Lee schreef:
Hi,
I am aware this is somehow FAQ
Hi, my dependent variable is a proportion (prob.bind), and the independent
variables are factors for group membership (group) and a covariate
(capacity). I am interested in the effects of group, capacity, and their
interaction. Each subject is observed on all (4) levels of capacity (I use
capacity
and ofcourse (if using ubuntu) you need the ubuntu CRAN repository as
Dirk Eddelbuettel suggested and not the debian as I suggested. sorry.
Paul
Jason Lee schreef:
Hi,
I am aware this is somehow FAQ question but I ve been searching from R-cran
archive about the related matter and could not
Frank Harrell gave me a hint:
http://biostat.mc.vanderbilt.edu/twiki/pub/Main/StatReport/latexFineControl.pdf
but I'm still puzzled. Now I do know how to modify e.g cell colors in
a table (see below) but I still know how to modify the width parameter
of the column. Can anyone give a helping
Hello every R-User,
I would like to translate Rcmdr menu items to French (by example).
How can I do it ?
Thanks for all.
--
View this message in context:
http://www.nabble.com/Change-language-in-Rcmdr-tp18312496p18312496.html
Sent from the R help mailing list archive at Nabble.com.
Dear Jason,
I don't know if this interests you, but one thing you might want to do
while 'upgrading' (in fact it is just a new installation) is re-install
all the packages that were installed on your previous R version.
I made a small script to do so:
###
reinst.pack - function(pathToOldR){
Currently it needs 50+ mins to run on a 80 rows. I need to run it hundreds
of times :P
t(apply(unique_ids, 1, function(x) { sd(subset(m[, 5:20], m[,ID] == x)) } ))
_
[[alternative HTML version deleted]]
Hi all!
Writing a paper using a lot of boxplots I was asked to mark the
significant differences between plotted groups using stars on
top.
These stars are found freqeuntly in medical papers and printed
above boxplots when there is a significant difference (usually using a
bar to indicate which
Try aggregate. It takes only 8 seconds for the 80 rows in the
example below.
m - as.data.frame(matrix(rnorm(1600), ncol = 20))
m$ID - rbinom(nrow(m), 10, prob = 0.5)
system.time(
aggregate(m[, 5:20], list(ID = m$ID), sd)
)
user system elapsed
6.141.377.55
HTH,
Can R perform matrix algebra between ascii converted Esri grids? Possible
yes.
The question is a little more complex (from my point of view and
inexperience): I'm interested in perform cost surface and distance surface
analysis avoiding ArcGIS tools. Maybe R can deal with grid formatted as
Hi all,
Is there any reasonable way to initialize the gamma parameters for
maximum likelihood estimation using EM.
Any advice, pointer to paper URLs are greatly appreciated.
Some people mention this can be done
by drawing mixing proportions from Dirichlet distribution.
But that is vague for me
Hello everyone,
I have biological data from a competition experiment where a free ligand is
titrated against the binding of a protein.
Now, I would like to fit a standard on-site binding curve to this data in order
to obtain the IC50 and Kd values.
Unfortunately I have not been able to find a
Hi
Try changing
for(i in 1:250){
jpeg(filename = graf01.jpg, width = 1024, height = 1024,
to
for(i in 1:250){
jpeg(filename = paste(graf, i, .jpg, sep=), width = 1024, height = 1024,
I think that should work, otherwise read up on the paste() function at
Schleuh wrote:
Hello every R-User,
I would like to translate Rcmdr menu items to French (by example).
How can I do it ?
The web page http://developer.r-project.org/Translations.html describes
what needs to be done. You should definitely contact the package author
(John Fox) first,
The new code you posted has introduced two more bugs yet
again.
Before posting again run your code in the debugger issuing this
command prior to testing fnc:
debug(fnc)
and then single step through the code. That way you can find
your own bugs. See ?debug
You can source aggregate.zoo from
Hello,
As far as I know, Rcmdr is already translated in French. It is thus just
a question of switching R to French.
Best,
Philippe Grosjean
Duncan Murdoch wrote:
Schleuh wrote:
Hello every R-User,
I would like to translate Rcmdr menu items to French (by example).
How can I do it ?
On Mon, 2008-07-07 at 11:19 +0200, Sebastian Merz wrote:
Hi all!
Writing a paper using a lot of boxplots I was asked to mark the
significant differences between plotted groups using stars on
top.
These stars are found freqeuntly in medical papers and printed
above boxplots when there is
It is probably not too difficult to do. You put the code that might
fail inside a try({...}) and then test for failure. If it fails,
you can send an email and then continue to the next file. The actual
code would be dependent on where the error(s) might be occurring and
what you want to do on
Dear R Users,
A bit of a simple question, but I could not find the answer thru google
(sorting lists r cran,how can i sort a list r cran) or RSiteSearch...
how can I sort a list ?
One imagines something like sort.list would do the job, but that's not the
one.
foo-list(a=10,b=2,c=3)
The function given below is one I've written to handle repeated
measures. I've also included the Help File. If you happen to see any
potential improvements, I would be open to suggestions.
###
### Function Code
###
'Bland.Altman' - function(x,y,alpha=.05,rep.meas=FALSE,subject,...){
[EMAIL PROTECTED] wrote:
Dear R Users,
A bit of a simple question, but I could not find the answer thru google
(sorting lists r cran,how can i sort a list r cran) or RSiteSearch...
how can I sort a list ?
One imagines something like sort.list would do the job, but that's not the
one.
foo[sort.list(unlist(foo))] may help you, but I think that this is not your
final solution.
Cheers,
miltinho astronauta
brazil
On 7/7/08, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote:
Dear R Users,
A bit of a simple question, but I could not find the answer thru google
(sorting lists r
-- begin included message
I'm having a problem with custom functions in rpart, and before I tear my
hair out trying to fix it, I want to make sure it's actually a problem. It
seems that, when you write custom functions for rpart (init, split and eval)
then rpart no longer cross-validates the
Dear Schleuh and Duncan,
The Rcmdr package does make provision for translation and in fact includes
translations from English into 10 other language. Philippe is being modest,
since he is the French translator.
Regards,
John
--
John Fox, Professor
Department of
Thanks for your help and suggestions.
Thats exactly what I did, i.e. a sin () and cos () code using daily
observations of soil temperature, and putting a variable vegetation types as
a covariate. Therefore, I can build contrasts to compare parameters of the
model such as an intercept,
l y pligly at gmail.com writes:
Hi everyone, when I use the two sample Kolmogorov¨CSmirnov ks2Test like this:
x=read.table(e:/x.txt)
y=rstable(1000,alpha,beta,gamma,delta)
I alway get results as follows:
Warning messages:
[snip]
Strangely,I got a total same result! I really want to
I have a simple regression using lm().
If I just want to check the coefficient, I can use summary(lm())$coef; if I
need the standard error, I can use summary(lm())$s, if I need the residuals,
I can use summary(lm())$res. OK. How can I get the R-squares and Adjusted
R-squares using $...?
Is
If I understand correctly, try:
names(summary(lm(...)))
On Mon, Jul 7, 2008 at 10:38 AM, rlearner309 [EMAIL PROTECTED] wrote:
I have a simple regression using lm().
If I just want to check the coefficient, I can use summary(lm())$coef; if I
need the standard error, I can use summary(lm())$s,
Or str(summary(lm(..)))
ir. Thierry Onkelinx
Instituut voor natuur- en bosonderzoek / Research Institute for Nature and
Forest
Cel biometrie, methodologie en kwaliteitszorg / Section biometrics, methodology
and
PS: I forgot to mention that, since the summary() of an lm() object
is created by the function summary.lm(), you can find out the detail
by looking under Value: at
?summary.lm
Ted.
On 07-Jul-08 14:28:23, Ted Harding wrote:
On 07-Jul-08 13:38:12, rlearner309 wrote:
I have a simple
rlearner309 wrote:
I have a simple regression using lm().
model - lm(dist ~ speed, data = cars)
sModel - summary(model)
If I just want to check the coefficient, I can use summary(lm())$coef; if I
need the standard error, I can use summary(lm())$s, if I need the residuals,
It is
Suppose I have a vector of data.
Is there a method in R to help us automatically
suggest which distributions fits to that data
(e.g. normal, gamma, multinomial etc) ?
- Gundala Viswanath
Jakarta - Indonesia
See
https://stat.ethz.ch/pipermail/r-help/2008-June/166259.html
for example,
I have spent a fair amount of time looking for a package that is automated
to run glm (binomial) regression models with all possible subsets of my
independent variables. Something akin to Lumley's leaps package, but can
be applied to glms, not just lms; or something similar to Stata's brute
force
I do this kind of thing under control of make. If you organize the
individual pieces as separate targets then make -k will keep going and
make -j can be used to run things in parallel. R can be made to throw
an error with something like this:
egTarget:
@$(MKDIR) $(FLAGS)
Hi All,
I'm trying trying to draw a colour wheel (a slice of hcl space) in R.
Running the code below doesn't give me what I expect - there's some
oddly bright colours of the wrong hue around c(0, 0) and I see three
coloured circles (a small magenta, a medium sized yellow and a large
cyan). Am I
Dear R users,
I want to do some plots which depends on conditions (7 conditions)
I had collected all the conditions in a vector Cond(c1,c2,c3,c4,c5,c6,c7)
All the conditions are logic (TRUE/FALSE).
If c1 or c2 are FALSE I want to have only one Plot. Then I want to have a
break (something like
Hi Pedro,
Hmm, that's probably a bug in the way that ggplot2 is drawing the
lines. The good news is that the next version of ggplot has a much
more flexible theming system, so to get the same effect as your grid
code, all you'll need to do is:
theme_set(axis.line = theme_segment(colour = black)
The lasso2 and lars packages use l1 constraints in their routines. Depending
on what you are trying to accomplish, they may do what you want, or looking at
their code could give additional ideas.
Hope this helps,
--
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
The function ks.test(x,y, ...) performs a Kolmogorov-Smirnov test on a set
of sample values x against a distribution y. Both x and y must be
cumulative distributions; y can be either a vector of cumulative values or
a predefined distribution such as pnorm().
David Reinke
Senior Transportation
It sounds like an IF-THEN-ELSE should do the job. What happens in the
c1 c4 are FALSE, or some other combination? Is your description the
priority order that the tests are to be done in?
On Mon, Jul 7, 2008 at 10:45 AM, mysimbaa [EMAIL PROTECTED] wrote:
Dear R users,
I want to do some
David Reinke wrote:
The function ks.test(x,y, ...) performs a Kolmogorov-Smirnov test on a set
of sample values x against a distribution y. Both x and y must be
cumulative distributions; y can be either a vector of cumulative values or
a predefined distribution such as pnorm().
David Reinke
On Mon, Jul 7, 2008 at 10:18 AM, Eric Vander Wal [EMAIL PROTECTED] wrote:
I have spent a fair amount of time looking for a package that is automated
to run glm (binomial) regression models with all possible subsets of my
independent variables. Something akin to Lumley's leaps package, but can
Eric Vander Wal ejvander at lakeheadu.ca writes:
I have spent a fair amount of time looking for a package that is automated
to run glm (binomial) regression models with all possible subsets of my
independent variables. Something akin to Lumley's leaps package, but can
be applied to glms,
so, someone know where can I find the data.mgus dataset and the data.mgus?
This data set are used in the :
Robert A. Kyle, Terry M. Therneau, S. Vincent Rajkumar, Janice R. Offord,
Dirk R. Larson, Matthew F. Plevak, and L. Joseph Melton III. A long-term
study of prognosis in monoclonal
Daniel Malter daniel at umd.edu writes:
Hi, my dependent variable is a proportion (prob.bind), and the independent
variables are factors for group membership (group) and a covariate
(capacity). I am interested in the effects of group, capacity, and their
interaction. Each subject is
Hi,
There is an object, .Last.value to which the result of the most recent
evaluation is assigned. This is similar to ans in Matlab. In Matlab
ans can be very useful and time-saving, but typing the larger R
version is somewhat clunky and takes away from the usefulness.
Is it possible to
hadley wickham [EMAIL PROTECTED] wrote in message
news:[EMAIL PROTECTED]
there's some
oddly bright colours of the wrong hue around c(0, 0) and I see three
coloured circles (a small magenta, a medium sized yellow and a large
cyan). Am I doing something wrong or is there a bug in the hcl
R experts,
I have three columns. c1 and c2 are numeric variables whereas c3 are the
clusters classes (nominal variable, 10 different: cluster1, cluster2,
cluster3, cluster4, cluster5 ). I'd like to plot c1 against c2 (easy!)
in a 2D plot and put different color depending to the cluster class
Jon Zadra wrote:
Hi,
There is an object, .Last.value to which the result of the most
recent evaluation is assigned. This is similar to ans in Matlab.
In Matlab ans can be very useful and time-saving, but typing the
larger R version is somewhat clunky and takes away from the usefulness.
Try this:
makeActiveBinding(ans, function() .Last.value, .GlobalEnv)
NULL
yy - 3
ans
[1] 3
On Mon, Jul 7, 2008 at 2:03 PM, Jon Zadra [EMAIL PROTECTED] wrote:
Hi,
There is an object, .Last.value to which the result of the most recent
evaluation is assigned. This is similar to ans in
Gabor Grothendieck wrote:
Try this:
makeActiveBinding(ans, function() .Last.value, .GlobalEnv)
NULL
yy - 3
ans
[1] 3
OK, you win.
AND Luke won't kill you because he wrote that stuff...
--
O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B
c/ /'_ ---
Dear Josep,
Does it do the work for you?
# Example data
set.seed(123)
mydata=data.frame(c1=rnorm(100),c2=rnorm(100),cluster=sample(1:10,100,replace=TRUE))
attach(mydata)
# Plot
plot(c1,c2,col=cluster,pch=16,xlab=Your legend here,ylab=Your legend
here)
HTH,
Jorge
On Mon, Jul 7, 2008 at 1:51
I agree with Ben. Theoretically, Laplace (lmer) provides a better
approximation.
Chunhao
Quoting Ben Bolker [EMAIL PROTECTED]:
Daniel Malter daniel at umd.edu writes:
Hi, my dependent variable is a proportion (prob.bind), and the independent
variables are factors for group membership
All,
Tuesday week (July 15th) Mike Driscoll I will be presenting
A Gentle Introduction to R and its Applications in Business
Intelligence at the SDForum Business Intelligence SIG in Palo Alto,
California.
One motivation is to judge interest in starting a Use R Group in the
Bay Area. We will
on 07/07/2008 01:42 PM Jim Porzak wrote:
All,
Tuesday week (July 15th) Mike Driscoll I will be presenting
A Gentle Introduction to R and its Applications in Business
Intelligence at the SDForum Business Intelligence SIG in Palo Alto,
California.
One motivation is to judge interest in starting
The earlier messages suggest that you have automatically produced help
files (from package.skeleton) and haven't edited them. I'd suggest
moving them to a temporary directory until you're ready to edit them
properly.
ok, that get's me a little bit closer to a minimal working example as
This is what I would like to do and it works just fine. Is there a way to
shorten this code so I don't have to subset a subset of a subset?
d-subset(subset(subset(subset(x, River.Mile=202), River.Mile3),
Lagrangian==Yes), EventType==Regular)
Stephen
--
Let's not spend our time and resources
You didn't say how you were doing the install, but the directory name
looks like one that was used by R CMD check (.../dynalc.Rcheck/dynalc).
Are you trying to install from a directory created by it? You should
normally install from your original source directory.
Duncan Murdoch
On
Try this:
d- subset(x,
River.Mile = 202 River.Mile 3 Langrangian ==
Yes EventType == Regular)
On Mon, Jul 7, 2008 at 4:19 PM, stephen sefick [EMAIL PROTECTED] wrote:
This is what I would like to do and it works just fine. Is there a way to
shorten this code so I don't have
On 7/7/2008 3:19 PM, stephen sefick wrote:
This is what I would like to do and it works just fine. Is there a way to
shorten this code so I don't have to subset a subset of a subset?
d-subset(subset(subset(subset(x, River.Mile=202), River.Mile3),
Lagrangian==Yes), EventType==Regular)
You
Marc Schwartz wrote:
R groupies in San Francisco?
I have this mental image of a bunch of geeks dressed in tie-dyed
shirts, jeans and sandals, sitting on the corner of Haight-Ashbury
listening to the Grateful Dead while coding on their laptops.
That sounds pretty much like Berkeley when I was
stephen sefick wrote:
This is what I would like to do and it works just fine. Is there a way to
shorten this code so I don't have to subset a subset of a subset?
d-subset(subset(subset(subset(x, River.Mile=202), River.Mile3),
Lagrangian==Yes), EventType==Regular)
Stephen
is your friend:
On Mon, Jul 7, 2008 at 1:05 PM, Earl F. Glynn [EMAIL PROTECTED] wrote:
hadley wickham [EMAIL PROTECTED] wrote in message
news:[EMAIL PROTECTED]
there's some
oddly bright colours of the wrong hue around c(0, 0) and I see three
coloured circles (a small magenta, a medium sized yellow and a
Hi, All:
Version 1.2.4 of the Functional Data Analysis (fda) package is now
available on CRAN. In this version, both 'smooth.basis' and
'smooth.basisPar' have been modified to make them easier to use. They
have more useful defaults and they return an object of class
'fdSmooth', with
on 07/07/2008 02:30 PM Peter Dalgaard wrote:
Marc Schwartz wrote:
R groupies in San Francisco?
I have this mental image of a bunch of geeks dressed in tie-dyed
shirts, jeans and sandals, sitting on the corner of Haight-Ashbury
listening to the Grateful Dead while coding on their laptops.
Duncan Murdoch [EMAIL PROTECTED] [Mon, Jul 07, 2008 at 09:24:07PM CEST]:
You didn't say how you were doing the install, but the directory name
looks like one that was used by R CMD check (.../dynalc.Rcheck/dynalc).
No, that was an attempt to install during a call to R CMD check.
--
On Mon, Jul 7, 2008 at 12:51 PM, Josep Maria Campanera Alsina
[EMAIL PROTECTED] wrote:
R experts,
I have three columns. c1 and c2 are numeric variables whereas c3 are the
clusters classes (nominal variable, 10 different: cluster1, cluster2,
cluster3, cluster4, cluster5 ). I'd like to plot
Duncan Murdoch [EMAIL PROTECTED] [Mon, Jul 07, 2008 at 09:57:50PM CEST]:
Does a plain install succeed?
No, the error messages look familiar:
* Installing to library '/usr/local/lib/R/site-library'
* Installing *source* package 'dynalc' ...
** libs
WARNING: no source files found
chmod: Zugriff
HI Sebasian,
I don't think I have ever seen this type of presentation. Could you provide a
reference to a journal article that uses this? It might make it easier to
visualize exactly what you want.
--- On Mon, 7/7/08, Sebastian Merz [EMAIL PROTECTED] wrote:
From: Sebastian Merz [EMAIL
I am wondering if it is possible to perform the following two basic
functions with primitive R functions. I know I could write functions for
either, but it seems as though they are probably built-in somewhere.
1) Fill out a vector to a desired length with missing values or zeros. So,
Eric Turkheimer 写道:
I am wondering if it is possible to perform the following two basic
functions with primitive R functions. I know I could write functions for
either, but it seems as though they are probably built-in somewhere.
1) Fill out a vector to a desired length with missing values or
Here is a solution:
1. c(x, rep(NA, n-length(x)))
2. which(x==2, arr.ind=TRUE)
Cheers
Andy
__
Andy Jaworski
518-1-01
Process Laboratory
3M Corporate Research Laboratory
-
E-mail: [EMAIL PROTECTED]
Tel: (651) 733-6092
Fax: (651) 736-3122
Eric Turkheimer
Thanks for your answers. I appreciate your help. I tried the glmmML.
However, it seems glmmML does not allow for a quasibinomial fit as I did
with the models I used. I have large overdispersion which I account for
using a quasibinomial with scaling parameter. Further, I have 360
observations - is
Dear Eric,
Try this:
# First function
f1=function(x,k) c(x,rep(NA,k-length(x)))
x-c(3,4,5)
f1(x,5)
# Second function
f2=function(x,val){
res=which(x==val,arr.ind=T)
paste(res,collapse=',',sep='')
}
x-matrix(1:9,ncol=3)
f2(x,2)
HTH,
Jorge
On Mon, Jul 7, 2008 at 5:07 PM, Eric Turkheimer
Eric Turkheimer wrote:
I am wondering if it is possible to perform the following two basic
functions with primitive R functions. I know I could write functions for
either, but it seems as though they are probably built-in somewhere.
1) Fill out a vector to a desired length with missing
hadley wickham [EMAIL PROTECTED] wrote in message
news:[EMAIL PROTECTED]
On Mon, Jul 7, 2008 at 1:05 PM, Earl F. Glynn [EMAIL PROTECTED]
wrote:
hadley wickham [EMAIL PROTECTED] wrote in message
news:[EMAIL PROTECTED]
Well, I do have fixup = FALSE, which the documentation indicates
should
Hadley:
I'm trying trying to draw a colour wheel (a slice of hcl space) in R.
Running the code below doesn't give me what I expect - there's some
oddly bright colours of the wrong hue around c(0, 0) and I see three
coloured circles (a small magenta, a medium sized yellow and a large
cyan). Am
Marc Schwartz wrote:
That sounds pretty much like Berkeley when I was there in 2000. I
really should get to visit there again and buy some more tie-dyed
t-shirts for my nieces
We could have useR! 2009 there...that would give you a reason to visit.
That would be 2010. Rennes already has
On Mon, Jul 7, 2008 at 4:30 PM, Earl F. Glynn [EMAIL PROTECTED] wrote:
hadley wickham [EMAIL PROTECTED] wrote in message
news:[EMAIL PROTECTED]
On Mon, Jul 7, 2008 at 1:05 PM, Earl F. Glynn [EMAIL PROTECTED]
wrote:
hadley wickham [EMAIL PROTECTED] wrote in message
news:[EMAIL PROTECTED]
Daniel Malter daniel at umd.edu writes:
Thanks for your answers. I appreciate your help. I tried the glmmML.
However, it seems glmmML does not allow for a quasibinomial fit as I did
with the models I used. I have large overdispersion which I account for
using a quasibinomial with scaling
If you replace this by
hcl$colour - hcl(hcl$h, hcl$c, hcl$l, fixup = FALSE)
with(hcl, plot(x, y, col=colour, pch=20))
Then, the resulting wheel has three overlapping holes corresponding to
the colors previously fixed.
Oops, thanks for pointing that out.
Also, as hue/chroma correspond to
On Mon, 7 Jul 2008, hadley wickham wrote:
If you replace this by
hcl$colour - hcl(hcl$h, hcl$c, hcl$l, fixup = FALSE)
with(hcl, plot(x, y, col=colour, pch=20))
Then, the resulting wheel has three overlapping holes corresponding to
the colors previously fixed.
Oops, thanks for pointing
I found and loaded the survey package. ?rake and ?postStratify seem
promising. Are there other packages/procedures I've missed? Are there
online references that an R newbie could use to feel comfortable
applying these procedures to a survey? How about a reference discussing
the details of
The answer to your first question is
sum(x)8sum(y) - sum(x*y)
and for the second one
x %*% R %*% y - sum(x*y*diag(R))
--- On Thu, 3/7/08, Murali Menon [EMAIL PROTECTED] wrote:
From: Murali Menon [EMAIL PROTECTED]
Subject: [R] multiplication question
To: [EMAIL PROTECTED]
Received:
Hi,
is there an easy way to get the calculated weights in a regression equation?
for e.g.
if my model has 2 variables 1 and 2 with coefficient .05 and .6
how can I get the computed values for a test dataset for each coefficient?
data
var1,var2
10,100
so I want to get .5, 60 back in
Dear Dhruv,
Try this:
# data set
set.seed(123)
X=matrix(rpois(10,10),ncol=2)
X
[,1] [,2]
[1,]8 15
[2,]9 11
[3,] 145
[4,] 104
[5,] 10 13
# outcome
t(apply(X,1,function(x,betas){
if(length(x)!=length(betas)) stop(x and betas are of different length!)
y=x*betas
y
Dear all,
I am trying to fit a multiple linear regression model to a table of data. My
data.frame is like this ...
fit.data - data.frame(y, x1, x2, x3, x4, x5, x6), then I use the linea
regression command ...
lm(formula = y ~ x1 + x2 + x3 + x4 + x5 + x6, data = fit.data)
however, for some
If that is so, i.e. x1=-x2, then they do not convey different meaning and
cannot be estimated. Think about it that way you leave the house 8 hours
after midnight. This is identical to saying that you leave the house 16
hours before midnight. This conveys the exact (!) same information and
neither
thanks Jorge. I appreciate your multiple improvements.
This still involves hard coding the co-efficients. I wonder if this is what
glm and lm are doing.
for e.g.
m-lm(K~a+b,data=data)
m$coefficients would have 0 for all variables except a and b and then R must be
multiplying the weights
For the first case, just extend the vector:
x-c(3,4,5)
x
[1] 3 4 5
x[5] - NA
x
[1] 3 4 5 NA NA
the second would use 'which'
On Mon, Jul 7, 2008 at 5:07 PM, Eric Turkheimer [EMAIL PROTECTED] wrote:
I am wondering if it is possible to perform the following two basic
functions with
Hi, is there any package/function in Bioconductor that can do this: if given
the chromosome positions of a fragment, find out all genes within, and with
the information about which strand is the sense strand. And vice versa.
Thanks a lot.
-
Appreciate your time attention!
--
View this
This message goes away when I empty the data directory. The problem must be
around there.
Error in scan(file, what, nmax, sep, dec, quote, skip, nlines, na.strings, :
line 12 did not have 19 elements
--
Johannes Hüsing There is something fascinating about science.
So Mr.Anoymous, why don't you inquire on the Bioconductor list to find out
instead of here?
-- Bert Gunter
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On
Behalf Of runner
Sent: Monday, July 07, 2008 8:59 PM
To: r-help@r-project.org
Subject: [R] list genes w/n a
#Quick one hopefully. Shouldn't dnorm be returning the pdf? Last time
I checked,
#a probability shouldn't be greater than 1 as produced by:
curve(dnorm(x,0,.1),from=-1,to=t)
#Shouldn't I be getting an axis more like that produced by:
f=function(x,m,s){
y=rep(NA,length(x))
Hi runner...
runner [EMAIL PROTECTED] writes:
Hi, is there any package/function in Bioconductor that can do this:
As Bert says, this should be directed to the Bioconductor mailing
list. Let's have any follow-up conversation there. But...
if given the chromosome positions of a fragment, find
dnorm() computes the density, so it may be 1; pnorm() computes the
distribution function.
--- On Tue, 8/7/08, Mike Lawrence [EMAIL PROTECTED] wrote:
From: Mike Lawrence [EMAIL PROTECTED]
Subject: Re: [R] odd dnorm behaviour (?)
To: Rhelp [EMAIL PROTECTED]
Received: Tuesday, 8 July, 2008,
100 matches
Mail list logo