Dear All,
I am using the function vuong of the package pscl to compare 2 non nested
glm models with a numeric response.
I did the following
m1-glm(y ~x ,data=xxx)
m2-glm(y ~z , data=xxx)
When calling the vuong function I get the following message:
vuong(m1,m2)
Error in predprob.glm(m1) : your
Dear friends,
when i use glm() to fit my data, i use
glm(formula = snail ~ vegtype + mhveg + humidity + elevation + soiltem, *family
= Gamma(link = inverse),* data =a,))
It shows: error in eval(expr, envir, enclos) : *gamma distribution don't
allow negative value*.
But i use
result-glm(formula
Robin Hankin [EMAIL PROTECTED] writes:
Hi
How do I generate all ways of ordering sets of indistinguishable items?
suppose I have two A's, two B's and a C.
Then I want
AABBC
AABCB
AACBC
ABABC
. . .snip...
BBAAC
. . .snip...
CBBAA
[there are 5!/(2!*2!) = 30 arrangements. Note
I think the 0 values for snail are hurting you.
Kees
On Sunday 15 October 2006 13:10, zhijie zhang wrote:
Dear friends,
when i use glm() to fit my data, i use
glm(formula = snail ~ vegtype + mhveg + humidity + elevation + soiltem,
*family = Gamma(link = inverse),* data =a,))
It shows:
I'd like to excute character strings such as z-plot( objects()[1]; eval(z)
and viola I'd have a plot of my first dataframe in the first frame.
Unfortunately this approach no longer works.
Help?
Lloyd L
[EMAIL PROTECTED]
[[alternative HTML version deleted]]
On 10/14/06, Cam [EMAIL PROTECTED] wrote:
For nonlinear mixed effects models, can you specify the use of mass points to
approximate the random effects distribution? How?
If you mean in nonlinear mixed effects models fit by the nlme function
the answer is no. The nlme function in the nlme
Try this:
eval(parse(text = pi + 3))
On 10/14/06, Lloyd Lubet [EMAIL PROTECTED] wrote:
I'd like to excute character strings such as z-plot( objects()[1]; eval(z)
and viola I'd have a plot of my first dataframe in the first frame.
Unfortunately this approach no longer works.
Help?
Lloyd
Em Sábado 14 Outubro 2006 11:15, Gabor Grothendieck escreveu:
Try using OLS starting values:
glm(Y~X,family=gaussian(link=log), start = coef(lm(Y~X)))
Ok, using a starting value the model work.
But, sometimes ago it work without any starting values. Why now I need a
starting values?
Thanks
Dear r-helpers,
xx - c(0.000, 0.210, 0.714, 0.514, 1.000, 0.190, 0.590, 0.152)
yy - c(0.000, 0.265, 0.256, 0.521, 0.538, 0.761, 0.821, 1.000)
aa - c(19, 19, 19, 21, 19, 21, 21, 21)
x0 - xx[c(1, 1, 2, 2, 2, 3, 3, 4, 4, 4, 5, 6, 6, 7)]
y0 - yy[c(1, 1, 2, 2, 2, 3, 3, 4, 4, 4, 5, 6, 6, 7)]
x1 -
The problem in your example is that 'lme' doesn't know how to
handle the Variety*nitro interaction when all 12 combinations are not
present. The error message singularity in backsolve means that with
data for only 11 combinations, which is what you have in your example,
you can only
Michael Kubovy wrote:
Dear r-helpers,
xx - c(0.000, 0.210, 0.714, 0.514, 1.000, 0.190, 0.590, 0.152)
yy - c(0.000, 0.265, 0.256, 0.521, 0.538, 0.761, 0.821, 1.000)
aa - c(19, 19, 19, 21, 19, 21, 21, 21)
x0 - xx[c(1, 1, 2, 2, 2, 3, 3, 4, 4, 4, 5, 6, 6, 7)]
y0 - yy[c(1, 1, 2, 2, 2, 3, 3,
Yuval Sapir wrote:
Hi,
I am often re-use commands in R by using the arrows to retype them and modify
for the new needs. This way, I don't need to write commands again, and I can
modify the command by inserting/deleting/re-writing the command. Today,
suddenly, re-writing change the
Michael Kubovy [EMAIL PROTECTED] writes:
Dear r-helpers,
xx - c(0.000, 0.210, 0.714, 0.514, 1.000, 0.190, 0.590, 0.152)
yy - c(0.000, 0.265, 0.256, 0.521, 0.538, 0.761, 0.821, 1.000)
aa - c(19, 19, 19, 21, 19, 21, 21, 21)
x0 - xx[c(1, 1, 2, 2, 2, 3, 3, 4, 4, 4, 5, 6, 6, 7)]
y0 - yy[c(1,
On Sun, 2006-10-15 at 11:21 -0400, Michael Kubovy wrote:
Dear r-helpers,
xx - c(0.000, 0.210, 0.714, 0.514, 1.000, 0.190, 0.590, 0.152)
yy - c(0.000, 0.265, 0.256, 0.521, 0.538, 0.761, 0.821, 1.000)
aa - c(19, 19, 19, 21, 19, 21, 21, 21)
x0 - xx[c(1, 1, 2, 2, 2, 3, 3, 4, 4, 4, 5, 6, 6, 7)]
On 10/14/06, Spencer Graves [EMAIL PROTECTED] wrote:
You want to estimate a different 'cs' variance for each level of
'trth', as indicated by the following summary from your 'fake data set':
tapply(dtf$x, dtf$trth, sd)
FALSE TRUE
1.532251 8.378206
Since var(x[trth])
On Sat, 2006-10-14 at 23:52 -0400, Mohsen Jafarikia wrote:
Hello everyone,
I have the following program to draw a barplot.
MP-read.table(file='AR.out')
names(MP)-c('BN','BL','LR','Q')
Graph- barplot(MP$LR, main='LR Value', col='orange', border='black', space=
0.05, width=(MP$BL),
Hi,
I have R 2.3.1 installed by debian páckage.
I install only the base and recommended R packages from Debian source, all
others packages I install from the R source at CRAN.
But, I try to use library MASS, but I received this message:
library(MASS)
Error: This is R 2.3.1, package 'MASS'
See this thread on the R-Debian list:
https://stat.ethz.ch/pipermail/r-sig-debian/2006-October/000126.html
-Deepayan
On 10/15/06, Ronaldo ReisJunior [EMAIL PROTECTED] wrote:
Hi,
I have R 2.3.1 installed by debian páckage.
I install only the base and recommended R packages from Debian
Here is a completely different solution using gplot in sna. We create
an edge matrix, edges, and plot it.
library(sna)
edges - replace(matrix(0, 8, 8), cbind(match(x0, xx), match(x1, xx)), 1)
gplot(edges, coord = cbind(xx, yy), usearrows = FALSE,
vertex.col = c(black, white)[factor(aa)])
On
I frequently run R code using source() or just paste large chunks of
code into the console window. When there is an error in the code the
execution does not stop. Rather, there is a blue error message and the
remainder of the code continues to execute.
Questions:
1) Is there a way to change the
On 15 October 2006 at 14:45, Ronaldo ReisJunior wrote:
| I have R 2.3.1 installed by debian páckage.
|
| I install only the base and recommended R packages from Debian source, all
| others packages I install from the R source at CRAN.
We some 50 or more r-cran-* packages that you could
On 10/15/2006 1:19 PM, Fernando Saldanha wrote:
I frequently run R code using source() or just paste large chunks of
code into the console window. When there is an error in the code the
execution does not stop. Rather, there is a blue error message and the
remainder of the code continues to
On Sat, 14 Oct 2006, John Sorkin wrote:
R 2.2.0
windows XP
I am beginning to explore the mitools package contributed by Thomas
Lumley (thank you Thomas) and I have a few questions:
(1) In the examples given in the mitools documentation, the only family
argument used is family=binomial.
Dear r-helpers,
I have six panels: op(par(mfrow = c(2, 3), xaxt = 'n', yaxt = 'n',
pty = 's').
Each of them has a variable main = 'i', and xlab = '', ylab = ''
I would like to achieve two things:
(1) a common x-axis label under panel 5, and one label to the left of
panels 1 and 4
(2)
Dear all,
I want to compute the average of the three blocks for each x-variable which
is equal slide in the code below. How can I do that ?
block x1x2x3x4x5
12322 232423
12125 262139
1232422
Hello again,
Thanks for answering my questions.
If my program is now:
pdf('Test.pdf')
BL-c(1.97,8.04,2.54,10.53,4.85,1.73)
LR-c(0.85,0.86,8.33,04.18,6.26,2.40)
Q-c(0.00,0.00,1.92,01.92,4.48,0.00)
cols - ifelse(Q!=0, orange, green)
Graph- barplot(LR, main='LR Value',col=cols, border='black',
This will get you started
x - rnorm(20)
y - rnorm(20)
par(pty = 's', xaxt = 'n', yaxt = 'n', mfrow = c(2, 3),
mgp= c(1, 0, 0), mar = c(1.1, 2.1, 1.1, 0.1))
plot(y ~ x, main=1, xlab=, ylab=y1)
plot(y ~ x, main=2, xlab=, ylab=)
plot(y ~ x, main=3, xlab=, ylab=)
plot(y ~ x, main=4,
Try adding
text(31,3.8,expression(paste(alpha==5,%)),pos=3)
On 15/10/06, Mohsen Jafarikia [EMAIL PROTECTED] wrote:
Hello again,
Thanks for answering my questions.
If my program is now:
pdf('Test.pdf')
BL-c(1.97,8.04,2.54,10.53,4.85,1.73)
LR-c(0.85,0.86,8.33,04.18,6.26,2.40)
Dear R-users,
I have a frustrating problem that I am hoping has a simple fix. I am running a
series of lmer models from the lme4 package of the general form:
model-lmer(y~x1 + x2 . + xn +
(1|site),data=dataframe,family=poisson,method=Laplace,control=list(usePQL=FALSE,msVerbose=TRUE))
On 2006-10-13 10:55, David Barron wrote:
First, produce two barplots for comparison:
par(mfrow=c(2,1) )
barplot(VADeaths,beside=TRUE)
barplot(VADeaths)
The same information is in both plots; in the top, it is displayed as
5 separate bars for each group, and in the stacked plot it is
Thanks Richard,
That is roughly what I did. However, (1) the distance between the
rows is still quite large compared to the distance between the
columns; (2) (less important) I still have two ylab, one for each row.
On Oct 15, 2006, at 5:12 PM, Richard M. Heiberger wrote:
This will get you
Hi,
I tried to run the following script with R 2.4.0. The data stuff is commented
out because data are already in memory.
#db - read.csv(normais.csv, sep=;, quote=, header=T)
sink(normais-chi.txt, append=T, type = output, split=T)
#sink(normais-chi.txt, append=T)
table(db$agua, db$mBerg)
Hello everybody,
I have two series of intervals, and I'd like to output the shared
regions.
For example:
series1-cbind(Start=c(10,21,40,300),End=c(20,26,70,350))
series2-cbind(Start=c(25,60,210,500),End=c(40,100,400,1000))
series1
Start End
[1,]10 20
[2,]21 26
[3,]40 70
I would do something like this in lattice. It defaults to something prettier
and gives more control if you don't want the defaults.
tmp - data.frame(x=rnorm(120), y=rnorm(120), a=factor(rep(1:6, 20)))
xyplot(y ~ x | a, data=tmp)
xyplot(y ~ x | a, data=tmp, aspect=1, layout=c(3,2),
On 10/15/06, Douglas Bates [EMAIL PROTECTED] wrote:
On 10/14/06, Spencer Graves [EMAIL PROTECTED] wrote:
You want to estimate a different 'cs' variance for each level of
'trth', as indicated by the following summary from your 'fake data set':
tapply(dtf$x, dtf$trth, sd)
FALSE
Not the most efficient and requires integer values (maybe less than
1M). My results show an additional overlap at 40 - start end were
the same -- does this count? If not, just delete rows that are the
same in both columns.
series1-cbind(Start=c(10,21,40,300),End=c(20,26,70,350))
I cannot reproduce Fig. 13.2 in MASS4.
plot(gehan.surv,fun='cloglog')
Warning message:
2 x values = 0 omitted from logarithmic plot in: xy.coords(x, y,
xlabel, ylabel, log)
and the x-axis is badly scaled.
I was wondering if someone can help
Regards
Ross Darnell
Thanks to prior help from the list, I've made progress in adapting a
univariate log-likelihood function to a bivariate one for Box-Cox
transformations. However, I'm having trouble plotting values of the
log-likelihood function (z) for given range of lambda(1) and lambda(2).
The current result
In gsubfn I replace matches with strings that represent calls to a function
and then perform paste(eval(parse(text= ...)), collapse = ) on the result.
One user of gsubfn is using it with very long strings (over 20,000 characters)
and the parse is giving an input buffer overflow. Here is an
Ryacas is an R interface to the free yacas computer algebra
system. Ryacas allows one to send R expressions,
unprocessed yacas strings and certain other R objects to a
separate yacas process from R and get back the result. It
also has facilities for manipulating yacas strings and R
expressions
On 10/8/06, Egert, Bjoern [EMAIL PROTECTED] wrote:
Hello,
Is there a way in R to construct an (error correcting) binary code
e.g. for an source alphabet containing integers from 1 to say 255
with the property that each pair of distinct codewords of length m
is at Hamming distance
41 matches
Mail list logo