x27;, 'l'), key = mykey)
>
> Defining the key externally modularizes the problem, lets one define
> the features one wants to contain, and simplifies the high-level
> xyplot() call.
>
> There is a type = 'a' (shorthand for panel.average()) that can be
> us
lass = "data.frame")
#adding another subject to introduce replicates
id3 <- data.frame(ID=as.factor(rep(3, 4)),time = c(1, 1.5, 2, 5.5),
y = c(1, 2.2, 3, 2))
dat <- rbind(dat, id3)
mean.y <- aggregate(formula = y ~ time, data = dat,
, "y"),
row.names = c(NA, -7L), class = "data.frame")
library(lattice)
xyplot(y ~ time|ID, data = dat, type = 'l')
xyplot(y ~ time, data = dat, group = ID, type = 'l')
library(ggplot2)
qplot(time, y, data = dat, facets = .~ID, geom = 'line')
qplot(ti
to make the desired within R's plotting device rather than in latex try:
par(mfrow = c(3, 2))
and you'll probably want to adjust other mar, parameters as well (e.g.
mar, cex.lab, etc).
Or, take advantage of the flexibility offered by the graphics package
by studying ?layout
hth,
Kingsford
On
re, and Tinn-R is now my favorite interface to R under Windows.
Yesterday I used the document comparison tool for the first time
(Tools > Differences) ...very nice.
Kingsford Jones
On Fri, Jul 23, 2010 at 10:55 AM, Bert Gunter wrote:
> Google on "tinn-r tutorial." However, I belie
On Thu, Jul 22, 2010 at 8:23 AM, Christopher David Desjardins
wrote:
> * Please cc me if you reply as I am a digest subscriber *
>
> Hi,
> I am wondering how I can run a multilevel survival model in R? Below is
> some of my data.
>
>> head(bi0.test)
> childid famid lifedxm sex age delta
Can't give more specific advice without more information (see the
posting guide), but I suspect you want to use nlme::lme, specifying a
weights argument to adjust for the heterogeneity.
Kingsford
On Wed, Jul 21, 2010 at 11:10 PM, Kline, Keith A wrote:
> I have heterogeneous variance in a two-way
not an xtable solution, but R2HTML::HTML has an impressive list of
methods, including HTML.infl:
lm.SR <- lm(sr ~ pop15 + pop75 + dpi + ddpi, data = LifeCycleSavings)
influencia <- influence.measures(lm.SR)
library(R2HTML)
methods(HTML)
HTML(influencia, 'influencia.html')
and open the html file i
see ?sp::overlay and section 5.2 of Applied Spatial Data Analysis with R
I see there is now also raster::overlay, but I can't claim experience
with that funciton (however my impression is that the raster package
is a powerful tool for working with potentially very large rasters in
R).
hth,
Kingsf
sponse and limited sample size (both terms of number of subjects and
conflation between error and interaction) makes me think fitting a
meaningful model is not trivial. Off the cuff, perhaps a beta or
binomial model or using logit-transformed Accuracy (noting that
nothing can retrieve the &#
t;Z"
However, given the long history of S/R, there must be logical or
philosophical obstacles to this...?
best,
Kingsford Jones
>> -Original Message-
>> From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
>> Behalf Of Christian Raschke
>&g
ite a bit. Here's a
recent conversation:
<http://comments.gmane.org/gmane.comp.lang.r.lme4.devel/3291>
hope it helps,
Kingsford Jones
>
> My working example is:
>
> library(nlme)
> library(lattice)
>
> Ortho <- Orthodont
> Ortho$year <- Ortho$age - 8 # make intercept
On Fri, Jul 2, 2010 at 8:16 AM, Hadley Wickham wrote:
>> ?formula in R 2.9.2 says in para 2:
>> "The %in% operator indicates that the terms on its left are nested
>> within those on the right. For example a + b %in% a expands to the
>> formula a + a:b. "
>
> Ooops, missed that. So b %in% a = a:b,
ives
the gist of concepts.
> random = ~1|R+N
>
> or direct me to an overview regarding notation of these formulas in lme
> (package nlme)? The help files weren't exactly clear to me on this subject.
IMO Pinheiro and Bates' companion book to nlme is a prerequisite for
efficient
nk the real 'a-ha' moments came by interactively exploring
objects within R. This was vastly facilitated by the use of str and
indexing tools ([, [[, $, @).
A mantra for R beginners might be "In R we work with objects, and str
reveals their essence" ;-)
Kingsford Jones
>
,
TARSIER, ZORILLA, GENSTAT, and STORM, among others.
best,
Kingsford Jones
On Thu, Feb 18, 2010 at 9:05 PM, wrote:
>
> I am old enough to have lived through this particular transition.
> Prior to the advent of SAS, trials were analyzed by in-house written
> programs (usually in F
e, and
>>> divide by n-1 when estimating a population standard deviation (your
>>> initial description had it backwards I think).
>>>
>>> On Tue, Feb 2, 2010 at 5:25 PM, Peng Yu wrote:
>>> > On Mon, Oct 19, 2009 at 12:53 PM, Kingsford Jones
>>
On Tue, Feb 2, 2010 at 10:25 AM, Peng Yu wrote:
> On Mon, Oct 19, 2009 at 12:53 PM, Kingsford Jones
> wrote:
>>> sum((x-mean(x))^2)/(n)
>> [1] 0.4894708
>>> ((n-1)/n) * var(x)
>> [1] 0.4894708
>
> But this is not a built-in function in R to do so, rig
imnames")=List of 2
# ..$ : chr [1:3] "(Intercept)" "age" "Residual"
# ..$ : chr [1:3] "Variance" "StdDev" "Corr"
# - attr(*, "title")= chr "Subject = pdLogChol(1 + age)"
(sigma2.age <- as.numeric(vc[2, 1]))
# [
By default orthogonal polynomial contrasts are used for ordered
factors. Drop the 'ordered = TRUE' and you will get treatment
contrasts.
hth,
Kingsford Jones
On Tue, Nov 3, 2009 at 8:52 AM, Jen-Chien Chang wrote:
> Hi,
>
> I am wondering if there is a way to display t
See the nlme library and accompanying book by Pinheiro and Bates. The
lme function is appropriate for linear mixed models with normal
errors, and the 'weights' argument provides flexible methods for
modeling error heterogeneity.
hth,
Kingsford
On Mon, Nov 2, 2009 at 12:10 PM, jinyan fan wrote:
Thank you for the response, Prof Ripley. Some comments below
On Fri, Oct 30, 2009 at 9:27 AM, Prof Brian Ripley
wrote:
> On Wed, 28 Oct 2009, Kingsford Jones wrote:
>
>> I thought I'd share this with the list since it appears to provide a
>> quick fix to some memory prob
ages of
using this method *please* post a response.
best,
Kingsford Jones
__
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
On Wed, Oct 28, 2009 at 9:23 AM, Tom Gottfried wrote:
> ?curve
>
> regards,
> Tom
and I was in the process of writing a curve example when I noticed Tom
sent this. Here it is:
set.seed(777)
x <- runif(100, 0, 100)
y <- 10*x + x^2 - .01*x^3 + rnorm(100, 0, 500)
fit <- lm(y ~ x + I(x^2) + I(x^3))
...which would complement the apropos fortune from John Fox:
> library(fortunes)
> fortune('dangerous')
If you give people a linear model function you give them something dangerous.
-- John Fox
useR! 2004, Vienna (May 2004)
On Tue, Oct 27, 2009 at 12:48 PM, Rolf Turner wrote:
>
> On
Within the plot.lars code, change the type argument to matplot from 'b' to 'l':
library(lars)
myplot.lars <- edit(plot.lars)
#change type = 'b' to type = 'l' in the call to matplot
data(diabetes)
object <- with(diabetes, lars(x,y))
myplot.lars(obj
Perhaps functional data analysis would be of interest. See, for
example, package fda.
Kingsford
On Fri, Oct 23, 2009 at 4:46 PM, Dylan Beaudette
wrote:
> Hi,
>
> I have fit a series of ols() models, by group, in this manner:
>
> l <- ols(y ~ rcs(x, 4))
>
> ... where the series of 'x' values in
help(gnls, pack=nlme)
hth,
Kingsford Jones
On Thu, Oct 22, 2009 at 4:36 PM, Michael A. Gilchrist wrote:
> Hello,
>
> I've been fitting a random effects model using nlme to some data, but I am
> discovering that the variation in my random effect is very small. As a
> res
Mixed models based on likelihood methods can often handle missing
observations within subjects, but they not do well with missing
individual elements in the design matrices (think unit nonresponse vs
item nonresponse in the survey world). Continuing with the example I
recently sent to you
set.see
dom=~1|school)
f2 <- update(f1, . ~ year.c*tmt)
summary(f1)$corFixed['year', '(Intercept)']
# [1] -0.997
summary(f2)$corFixed['year.c', '(Intercept)']
# [1] 0
A possibility is that the data are not of the expected classes. What
does str(long) report?
h
= 2, lty = 2)
abline(f2, col = 3, lty = 3)
legend('topleft', c('male', 'female'), lty = 2:3, col = 2:3)
For some fancier plots see the ggplot2 examples here:
http://had.co.nz/ggplot2/stat_smooth.html
hth,
Kingsford Jones
On Tue, Oct 20, 2009 at 1:20 PM, Marsha Me
On Tue, Oct 20, 2009 at 5:09 AM, r-quantide wrote:
[snip]
> . Is there any methods/functions to obtain the variance components
> for the station factor too? (please, give me some references, at least.)
Pinheiro and Bates 2000 is (practically) a prerequisite for
intelligent use of the nlme
ease, give me some references, at least.)
>
With the proper design (i.e. enough data in the appropriate levels)
you might specify something like:
random = ~N + station - 1|spliceOrHoming
To get estimates of the between group variation for each of the levels
of the station factor, as well a
Peng,
It's generally useful to know the class of the object you are working
with, and the methods available for that class. This would have led
you to the 'loadings' help page.
> class(pca_result$loadings)
[1] "loadings"
> methods(class='loadings')
[1] print.loadings*
Non-visible functions a
> sum((x-mean(x))^2)/(n)
[1] 0.4894708
> ((n-1)/n) * var(x)
[1] 0.4894708
hth,
Kingsford
On Mon, Oct 19, 2009 at 9:30 AM, Peng Yu wrote:
> It seems that var() computes sample variance. It is straight forward
> to compute population variance from sample variance. However, I feel
> that it is sti
ce covariate such as ~age, there is no need for updating of the
variance covariate during optimization.
hth,
Kingsford Jones
>
> Thanks.
>
> Mike
>
> On Fri, 16 Oct 2009, Dieter Menne wrote:
>
>>
>>
>>
>> Michael A. Gilchrist wrote:
>>>
>&g
see
https://stat.ethz.ch/pipermail/r-sig-ecology/2008-May/000160.html
hth,
Kingsford
On Tue, Oct 13, 2009 at 6:00 AM, Anne-Katrin Link wrote:
> Normal 0 21 false false
> false
> MicrosoftInternetExplorer4
>
>
> Dear R-helpers,
>
> I was wond
ance parameter space.
- It seems the issue of counting the number of
parameters being estimated will be an issue when
comparing models that differ in their random
effects.
best,
Kingsford Jones
>
> -- Bert
>
> hth,
>
> Kingsford
>
>
>
>> Many thanks
On Mon, Oct 5, 2009 at 8:52 AM, Umesh Srinivasan
wrote:
> Hi all,
[snip]
>
> Fixed effects:
> Estimate Std. Error z value Pr(>|z|)
> (Intercept) -138.8423 0.4704 -295.1 < 2e-16 ***
> SpeciesCr -0.9977 0.6259 -1.6 0.11091
> SpeciesDb -1.2140 0.6945 -1.7 0.0
see ?curve
e.g.
qftn <- function(x) 1 + 2*x - .1*x^2
curve(qftn, 0, 10)
hth,
Kingsford
On Mon, Oct 5, 2009 at 9:42 AM, Juliano van Melis wrote:
> Good day for all,
>
> I'm a beginner aRgonaut, thus I'm having a problem to plot a quadratic model
> of regression in a plot.
> First I wrote:
>
>>
itting process. Also,
the general definition of AIC uses likelihoods not SS residuals.
Also, using the SS resids you are once again back to a linear
transormation of the MSE estimate...
Kingsford
> What do you / other R list members think?
>
> Regards
>
> On Thursday 03 Septembe
On Mon, Sep 7, 2009 at 12:42 AM, Gundala Viswanath wrote:
> How do people usually use the result of density function (e.g. dnorm)?
> Especially when its value can be greater than 1.
>
> What do they do with such density >1?
>
>> dnorm(2.02,2,.24)
> [1] 1.656498
There are countless uses. E.g., wh
for example...
x <- y <- seq(.1, 2, .1)
ftn <- function(x, y) x - .25*x^2
z <- outer(x, y, ftn)
persp(x, y, z, theta = 330, phi = 30)
hth,
Kingsford
On Sun, Sep 6, 2009 at 8:28 AM, Steve
Lianoglou wrote:
> Hi,
>
> On Sat, Sep 5, 2009 at 5:16 AM, gallon li wrote:
>> Basially I have the observa
On Mon, Sep 7, 2009 at 10:34 AM, Alain Zuur wrote:
>
>
>
> rapton wrote:
>>
>> Hello,
>>
>> I am using R to analyze a large multilevel data set, using
>> lmer() to model my data, and using anova() to compare the fit of various
>> models. When I run two models, the output of each model is generated
There are many ways to measure prediction quality, and what you choose
depends on the data and your goals. A common measure for a
quantitative response is mean squared error (i.e. 1/n * sum((observed
- predicted)^2)) which incorporates bias and variance. Common terms
for what you are looking for
ellipse with elongation
determined by the covariance.
hth,
Kingsford
> Tim Handley
> Fire Effects Monitor
> Santa Monica Mountains National Recreation Area
> 401 W. Hillcrest Dr.
> Thousand Oaks, CA 91360
> 805-370-2347
>
>
>
&
This will
generally have non-zero off-diagonals, implying the fixed effects
estimates are correlated. The values you're inquiring about are the
scaled estimates of those off-diagonals.
hth,
Kingsford Jones
>
> ##More detailed information
> ##function calls:
> sppl.i.xx = gls(all.all.rc
Hi Ben,
Pinheiro and Bates 2000 is the "real" documentation for nlme. See the
Cell Culture Bioassay example starting on pg 163 for a demonstration
of fitting crossed random effects using pdIdent and pdBlocked objects.
hth,
Kingsford
On Tue, Sep 1, 2009 at 6:44 AM, bamsel wrote:
>
> Hello R user
ations are uniformly
> distributed.
>
> Hope this helps,
> Ravi.
>
>
>
> Ravi Varadhan, Ph.D.
> Assistant Professor,
> Division of Geriatric Medicine and Gerontology
> School of Medicine
> Johns Hopki
28, 2009 at 7:36 PM, Kingsford
Jones wrote:
> R <- matrix(runif(1), ncol=100)
>
> hth,
>
> Kingsford Jones
>
> On Fri, Aug 28, 2009 at 7:26 PM, Ning Ma wrote:
>> Hi,
>>
>> How can I generate a random 100x100 correlation matrix, R={r_ij},
>> whe
R <- matrix(runif(1), ncol=100)
hth,
Kingsford Jones
On Fri, Aug 28, 2009 at 7:26 PM, Ning Ma wrote:
> Hi,
>
> How can I generate a random 100x100 correlation matrix, R={r_ij},
> where about 10% of r_ij are greater than 0.9
>
&
hould be MakeColName(...)
-- I was happy to see promotion of "<-". Reading code using '=' for
both object assignment and argument setting is a little like
fingernails on a blackboard...again and again and...
-- It's nice that people have made these guides available
example(plotmath)
hth,
Kingsford Jones
On Sat, Jul 25, 2009 at 6:25 AM, Buckmaster,
Sarah wrote:
> Hi everyone,
>
> I have a question about calculating r-squared in R. I have tried searching
> the archives and couldn't find what I was looking for - but apologies if
> there
a couple more options:
> ls("package:glmnet")
[1] "coef.glmnet" "glmnet" "jerr"
"nonzeroCoef" "plot.glmnet"
[6] "plotCoef""predict.elnet" "predict.glmnet"
"predict.lognet" "predict.multnet"
[11] "print.glmnet"
> # or
> ls(pos = 2)
[1] "coef.glmnet" "glmnet"
See the Bayesian Task View
http://cran.r-project.org/web/views/Bayesian.html
which will lead you to the arm and bayesm packages, among others.
hth,
Kingsford
On Tue, Jul 28, 2009 at 1:54 AM, nikolay12 wrote:
>
> Hello,
>
> I need to implement a hierarchical model for Bayesian multinomial logist
geom_segment() +
labs(x="Area", y="Povs")
pb1
hth,
Kingsford Jones
On Thu, Jul 23, 2009 at 5:13 PM, John Kane wrote:
>
> I have just started using ggplot2 and I seem to be doing something stupid
> in writing ggplot2 commands on more than one line.
>
> I
On Thu, Jul 23, 2009 at 12:36 PM, Kingsford
Jones wrote:
>
> As you might have suspected from the lmer t-value close to 0, the
> associated p-value is about .5.
you can ignore the sentence above -- it's a two sided test and the
t-value is not that close to 0...
>
> hth,
lme:
fit2 <- aov(Value ~ Group + Error(SS), data = smallDS)
#or
library(nlme)
fit3 <- lme(Value ~ Group, data = smallDS, random = ~1|SS)
As you might have suspected from the lmer t-value close to 0, the
associated p-value is about .5.
hth,
Kingsford Jones
> My subjects are divide
ture. My opinion is that code is much clearer if modeling and
plotting calls do not implicitly rely on a non-standard data
structure.
hth,
Kingsford Jones
On Tue, Jul 14, 2009 at 8:54 AM, FMH wrote:
> Hi,
>
> I have an original data frame with 8 columns of variables, which are stored
the r-sig-mixed-models list.
hoping it helps,
Kingsford Jones
On Fri, Jul 10, 2009 at 9:27 AM, Djibril
Dayamba wrote:
> Hello,
> I would appreciate if somebody could help me clear my mind about the below
> issues.
> I have a factorial experiment to study the effects of Grazing an
nd there should not be
> any zero distances. Any idea?
The error does suggest the function thinks there are duplicates in
lonlat. Have you tried, for example, sum(duplicated(lonlat))? Or you
could add a small amount of random noise to one of the coordi
Assuming you are referring to ESRI shapefiles, options can be found in
the following packages: maptools, rgdal, and shapefiles
See the Spatial Task View for more info:
http://cran.r-project.org/web/views/Spatial.html
hth,
Kingsford
On Tue, Jul 7, 2009 at 12:28 PM, Sunny wrote:
> I am new with R
try
do.call(rbind, yourByList)
hth,
Kingsford Jones
On Wed, Jun 24, 2009 at 9:34 PM, Stephan Lindner wrote:
> Dear all,
>
>
> I have a code where I subset a data frame to match entries within
> levels of an factor (actually, the full script uses three difference
> factors do
try:
dfr <- data.frame(A=rnorm(50), B=runif(50),
X=factor(sample(c('L1','L2'),50,repl=TRUE)))
by(dfr[, 1:2], dfr$X, mean)
hth,
Kingsford Jones
On Tue, Jun 23, 2009 at 7:57 PM, R_help Help wrote:
> Hi,
>
> To set a simple an clear picture of what I'
see
?"["
and notice the 'drop' argument.
So in your example try
dat[1, , drop=FALSE]
hth,
Kingsford
On Tue, Jun 23, 2009 at 1:13 AM, Bogaso wrote:
>
> Let say, I have following matrix :
>
> dat <- matrix(rnorm(40), 2, 20)
>
> Now I want to partition this like this :
>
> dat1 <- dat[1,]
> da
try:
'x' %in% colnames(df)
hth,
Kingsford
On Mon, Jun 22, 2009 at 9:17 PM, R_help Help wrote:
> Hi,
>
> I have a matrix or data.frame (df). When I would like to check if a column
> named "x" exists, it becomes my habit to do the following:
>
> if (length(which(colnames(df)=="x"))>0)
>
> Is there
he spatial Task View
http://cran.r-project.org/web/views/Spatial.html
and an active spatial mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/R-SIG-Geo/
hth,
Kingsford Jones
On Mon, Jun 22, 2009 at 1:01 PM, John
Lipkins wrote:
> Hey,
>
> A basic question. Is there anyone tha
1 1 010
3 1 1 010
attr(,"assign")
[1] 0 1 1 2 2
attr(,"contrasts")
attr(,"contrasts")$f1
[1] "contr.treatment"
attr(,"contrasts")$f2
[1] "contr.treatment"
hth,
Kingsford Jones
On Fri, Jun 19, 2009 at
Hi Dajiang,
try
plot(1, main=expression(beta[1]))
and, more generally, see
?plotmath
or
demo(plotmath)
Kingsford Jones
On Sun, Jun 7, 2009 at 4:43 PM, Dajiang Jeff Liu wrote:
> Dear All,
> I want to ask how to make latex symbol \beta_1 into the title of the page.
> The usual bq
position of the firefox
search bar so that on my windows box I can Ctrl-Tab to firefox, then
Ctrl-K to search R sites.
hth,
Kingsford Jones
On Wed, May 20, 2009 at 3:05 PM, Kynn Jones wrote:
> Thank you all very much for the so many useful ideas and resources.
> KJ
>
> [[alte
The model has multiple levels of random effects, so you need to tell
qqnorm.lme which one you're interested in.
e.g.
qqnorm(m1, ~ranef(., level=1))
hth,
Kingsford Jones
On Thu, Apr 23, 2009 at 11:03 AM, Patrick Zimmerman wrote:
> Hello,
>
> I am trying to do some plotting t
,
Kingsford Jones
On Thu, Apr 23, 2009 at 7:15 AM, calpeda wrote:
>
> Hi all,
>
> When you want to draw a surface with a mathematics program you need of two
> vectors x and y and a matrix z. Then you plot the surface.
> For example:
> x=[1 2 3];
> y=[5 6 7];
> z=[1 2 3
>
ensities. Also,
you may need to adjust the ylim and xlim arguments if the densities
from your two samples are dissimilar.
As for converting the histogram to a bar plot -- I think that's an
aberration best left in Excel...
hope it helps,
Kingsford Jones
On Wed, Apr 22, 2009 at 2:56 AM,
The attachment didn't come through, but try:
example(filled.countour)
#or
library(lattice)
example(levelplot)
hth,
Kingsford Jones
On Tue, Apr 21, 2009 at 9:46 PM, wrote:
> I wonder whether it is possible in R to generate color-coded 3D plots, like
> the attached example.
&g
See ?lmer and notice model gm1 in the examples.
As with glm, a binomial lmer model can have the response specified "as
a two-column matrix with the columns giving the numbers of successes
and failures".
hth,
Kingsford Jones
On Fri, Apr 10, 2009 at 2:48 PM, Sean Zhang wrote:
>
point you can just do
> max(nchar(shadvector))
[1] 9
hth,
Kingsford Jones
>> shadvlength <- lapply(shadvector,nchar)
>> shadmaxind <- which.max(shadvlength) ## Maximum element
>> shadmax <- nchar(shadvector[shadmaxind])
>> shadmax
> [1] 9
&
See 'mar' under ?par
e.g.,
x <- y <- -100:100
z <- outer(x, y, function(x,y) sqrt(x^2 + y^2))
par(mar=c(0,0,0,0))
image(x,y,z)
hth,
Kingsford Jones
On Wed, Apr 8, 2009 at 9:07 PM, Bob Meglen wrote:
> I am using several scripts that employ various packages to proce
rgument to
specify linear combinations of the coefficients to be tested to be 0.
Kingsford
On Sun, Mar 29, 2009 at 11:57 AM, Kingsford Jones
wrote:
> Hi Dwight,
>
> The answer likely depends on how you are fitting the model. Have a
> look at the multcomp package and its vignettes to see i
Hi Dwight,
The answer likely depends on how you are fitting the model. Have a
look at the multcomp package and its vignettes to see if it can handle
the model class you are interested in.
hth,
Kingsford Jones
On Sun, Mar 29, 2009 at 11:11 AM, Krehbiel, Dwight
wrote:
> Dear colleag
lts are tests for
differences of each method from Alcohol.Spray. There are many other
options for setting up the design matrix to test hypotheses of
interest, and for making adjustments for multiple testing.
Hope that helps,
Kingsford Jones
On Sun, Mar 29, 2009 at 11:01 AM, Dan Kelley wrote:
>
.051269
Standard Deviations: 2.327 0.22643
One way to extract the standard deviations shown by the print method above is:
> diag(sqrt(getVarCov(fm1)))
(Intercept) age
2.3270339 0.2264276
Warning message:
In sqrt(getVarCov(fm1)) : NaNs produced
And to get
)[50])[1,4]
>
> Error in `[.default`((coef(summary(lm(t(returns2) ~ factors)))[50]), 1,
> :
> incorrect number of dimensions
Use of the 'str' function will reveal you are indexing a list element,
so try
x,y, peaks)
z2 <- 10 * round(c(z) + abs(min(z)) + 1)
jet.colors = colorRampPalette(c("#7F", "blue", "#007FFF",
"cyan", "#7FFF7F", "yellow", "#FF7F00", "red", "#7F"))
color <- jet.colors(160)[z2]
;wheat3"
> ...
>> ##chr [1:4] "tomato1" "yellow1" "green" "blue"
>>
>> attach(dd)
>> seqiplot(data.seq[1:4,], withlegend=FALSE, ylab="Seal ID",
> + axes = F, title = "30-09-2008", cpal=mycols)
> There wer
een",..: 3 4 2 1
> str(as.character(mycols$color.names))
chr [1:4] "tomato1" "yellow1" "green" "blue"
hth,
Kingsford
>
> Ross
>
>
>
> Kingsford Jones wrote:
>>
>> One option for creating your own palette is
>>
For permutations a couple of options are 'permutations' in package
gtools, and 'urnsamples' in package prob
hth,
Kingsford Jones
On Fri, Mar 13, 2009 at 6:35 AM, Dale Steele wrote:
> I'm doing a permutation test and need to efficiently generate all
> distinct
he only thing i can do is
> create my own palette, but i'm having limited success in trying to work out
> how to do this.
>
>
> Kingsford Jones wrote:
>>
>> Try
>>
>> #install.packages('RColorBrewer')
>> example(brewer.pal, pack='RCo
Try
#install.packages('RColorBrewer')
example(brewer.pal, pack='RColorBrewer')
hth,
Kingsford Jones
On Fri, Mar 13, 2009 at 3:20 AM, Ross Culloch wrote:
>
> Dear all,
>
> This seems like a simple problem but i've searched the help files and tried
> var
Also, see
# install.packages('sp')
example('spplot', package='sp')
Kingsford Jones
On Wed, Mar 11, 2009 at 9:38 AM, Greg Snow wrote:
> Another possibility is the my.symbols function in the TeachingDemos package.
> You can define a polygon of your arrow (o
unfortunately the issues are
compounded by the sparseness of your data in the predictor space.
hth,
Kingsford Jones
On Mon, Mar 9, 2009 at 4:44 PM, Menelaos Stavrinides wrote:
> I am running an lme model with the main effects of four fixed variables (3
> continuous and one categorical – see belo
y area (although the latter may be
difficualt, depending on the spatial layout of your study). I don't
know of a regression tool in R that allows for estimation of the
spatial correlation strructure at levels higher than than the
observations.
Kingsford Jones
On Mon, Mar 9, 2009 at 7:28 AM, Joh
n subjects are
temporally or spatially correlated.
Kingsford Jones
On Mon, Mar 9, 2009 at 1:15 PM, Paul Gribble wrote:
> After much research I've listed a couple of ways to do repeated measures
> anova here:
>
> http://gribblelab.org/2009/03/09/repeated-measures-anova-using-
e|Subject,
weights=varPower())
plot(f1, distance~fitted(.)|Subject, abline=c(0,1))
intervals(f1)
hth,
Kingsford Jones
>any other suggestion on dealing with this
> problem is welcome.
>
> Thanks,
>
> --
> View this message in context:
> http://www.nabble.com/ANOVA-tp2235
: M
: B
[1] 259
--
: H
: B
[1] 169
hth,
Kingsford Jones
On Wed, Mar 4, 2009 at 8:17 PM, Pele wrote:
>
> Hi R users,
>
> I have an R object with the following attributes:
>
>> str(s
On Mar 4, 2009, at 10:26 PM, Kingsford Jones wrote:
>
> see
>
> https://stat.ethz.ch/pipermail/r-help/2008-January/151694.html
>
> hth,
> Kingsford Jones
>
> On Wed, Mar 4, 2009 at 7:30 PM, Fuchs Ira wrote:
>> How can I print the definition of a function that is in
see
https://stat.ethz.ch/pipermail/r-help/2008-January/151694.html
hth,
Kingsford Jones
On Wed, Mar 4, 2009 at 7:30 PM, Fuchs Ira wrote:
> How can I print the definition of a function that is in the base package?
>
> for example, if I type:
>
> which.min
>
> I get
>
&g
Does cex.axis not work in that it reduces the size for both x and y
axes? If that's the case try calling plot with axes=FALSE, and then
add axes seperately with the axis function.
Kingsford Jones
On Wed, Mar 4, 2009 at 1:59 PM, Tiffany Vidal
wrote:
> I am trying to reduce the font si
try
dat <- as.data.frame(replicate(100, rnorm(10)))
hth,
Kingsford Jones
>
> Thanks~
>
> [[alternative HTML version deleted]]
>
> __
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-hel
RSiteSearch('trpaths')
will lead you to potential solutions...
On Fri, Feb 27, 2009 at 7:18 PM, wrote:
> I am running an R script with Tinn-R (2.2.0.1) and I get the error message
>
> Error in source(.trPaths[4], echo = TRUE, max.deparse.length = 150) :
> object ".trPaths" not found
>
> Any
X11() on my Vista machine running 2.8.1 seems to work the same as
windows(). From the help page, the only difference I see is that
'X11' (and 'x11') have only width, height and pointsize arguments
('windows' has another 13).
Kingsford
On Wed, Feb 25, 2009 at 8:58 PM, Ted Harding
wrote:
> There
1 - 100 of 161 matches
Mail list logo
