[R] R-Square for Robust Regression Model

May I know how to find the R-squared for robust regression model?   Thank you.   Hock Ann [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting

[R] Converting a dataframe column from string to datetime

Hi, I have a dataframe column of the form v<-c("Fri Feb 05 20:00:01.43000 2010","Fri Feb 05 20:00:02.274000 2010","Fri Feb 05 20:00:02.274000 2010","Fri Feb 05 20:00:06.34000 2010") I need to convert this to datetime form. I did the following.. lapply(v,function(x){strptime(x, "%a %b %d %H:%M:

Re: [R] [Help]:How to use "loop" to achieve this aim?

try:ch -- for(i in 1:22) { chrn <- paste("chr",i,sep="") chrn=MEDIPS.readAlignedSeqences(BSgenome="hg19", file="chrn",numrows= ) chrn=MEDIPS.genomeVector(data=chrn, bin_size=50,extend=250) ... ... write.table(frameschrn.frame500.step250, file="frames.chrn.meth.txt", sep="\T",

Re: [R] R 2.11.1 crashes

Hello Steve, You'll need to give more information for people to help you. 1) Is this the first time you installed R? Or was it a working R version that suddenly started having this problem? 2) Did you try uninstalling this version, downloading a new version, installing it - and seeing what happen

Re: [R] Converting a dataframe column from string to datetime

Is it okay with you? Reduce("rbind", lapply(lapply(v,function(x){strptime(x, "%a %b %d %H:%M:%OS %Y")}), as.character)) -- View this message in context: http://r.789695.n4.nabble.com/Converting-a-dataframe-column-from-string-to-datetime-tp2853709p2869793.html Sent from the R help mailing list a

Re: [R] barplots with 2 different scales

On 10/01/2010 09:19 AM, Jeremy Claisse wrote: Is there a way to create barplots with pairs of bars plotted on 2 different scales (i.e some bars would be plotted according to the scale on the y-axis on the left and other bars plotted according to a different scale on the right axis)? Hi Jeremy,

Re: [R] Converting a dataframe column from string to datetime

I think you want to use as.POSIXct to get the date value: > v<-c("Fri Feb 05 20:00:01.43000 2010","Fri Feb 05 20:00:02.274000 2010","Fri > Feb 05 20:00:02.274000 2010","Fri Feb 05 20:00:06.34000 2010") > x <- as.POSIXct(v, format= "%a %b %d %H:%M:%OS %Y") > x [1] "2010-02-05 20:00:01 EST" "2010-0

Re: [R] Inserting a plot into another

On 10/01/2010 01:01 AM, Filoche wrote: Hi everyone. I would like to know if it was possible to insert a plot into another one. For example I have a plot and I would like to add a smaller plot in the top right corner. Hi Phil, Take a look at the subplot function in TeachingDemos. Jim ___

[R] Issues loading rtiff 1.4.1 with R 2.6.2 on Windows

Dear R-users, I successfully installed rtiff on by R installation, but when I tried to load it, I got: >local({pkg <- select.list(sort(.packages(all.available = TRUE))) + if(nchar(pkg)) library(pkg, character.only=TRUE)}) Error in dyn.load(file, ...) : unable to load shared library 'C:/PROGRA~1/R

[R] Irregular time series plot

Hi, I am new to R and trying to plot a time series data with irregular interval. I was wondering how to read a data of the following format and plot it ? Time 00:00:00 00:05:00 00:10:00 00:15:00 00:20:00 00:30:00 01:00:00

[R] Interpreting the example given by Frank Harrell in the predict.lrm {Design} help

Dear list, I am relatively new to ordinal models and have been working through the example given by Frank Harrell in the predict.lrm {Design} help All of this makes sense to me, except for the responses, i,e how do i interpret them? i would be extremely grateful if someone could explain the re

Re: [R] Irregular time series plot

Hi List, I am some what new to R-world. I am trying to plot some vector data, each vector has a direction and magnitude, the data is taken from an array of points, some of the coverage area overlap, some do not. Due nature of the grid there are some points that lack data. Can any body recommend

Re: [R] Format of Output of Residuals

Hi: CW.lm <- lm(weight ~ Diet, ChickWeight) resid.CW.lm <- resid(CW.lm) as.data.frame(resid(CW.lm))[1:10, ] # (nope) [1] -60.645455 -51.645455 -43.645455 -38.645455 -26.645455 -9.645455 [7] 3.354545 22.354545 46.354545 68.354545 # convert residuals to one column matrix, then convert t

Re: [R] Irregular time series plot

Sorry about this, I used your item as prototype to get the email address. Dave. > Hi List, > > I am some what new to R-world. > > I am trying to plot some vector data, each vector has a direction and > magnitude, the data is taken from an array of points, some of the coverage > area overlap, some

[R] function which can apply a function by a grouping variable and also hand over an additional variable, e.g. a weight

Hi, I was wondering if there is an easy way to accomplish the following in R: Often I want to apply a function, e.g. weighted.quantile from the Hmisc package to grouped subsets of a data.frame (grouping variable) but then I also need to hand over the weights which seems not possible with summary

Re: [R] Interpreting the example given by Frank Harrell in the predict.lrm {Design} help

John, Don't conclude that one category is the most probable when its probability of being equaled or exceeded is a maximum. The first category would always be the winner if that were the case. When you say y=best remember that you are dealing with a probability model. Nothing is forcing you to

Re: [R] Interpreting the example given by Frank Harrell in the predict.lrm {Design} help

Frank, Thats great thanks for the advice, i appreciate that brier score, AUC etc are a better method of validation and discrimination but when it comes to predictions of new data > d <- data.frame(x1=c(.1,.5),x2=c(.5,.15)) > predict(f, d, type="fitted.ind") > > y=good y=better

Re: [R] Issues loading rtiff 1.4.1 with R 2.6.2 on Windows

Probably there are not many people on this list left with such an ancient installation. Please try R-2.12.0 alpha. Uwe Ligges On 01.10.2010 11:49, Oderbolz Daniel wrote: Dear R-users, I successfully installed rtiff on by R installation, but when I tried to load it, I got: local({pkg<- sele

Re: [R] RGL and Windows 7

On 01/10/2010 2:12 AM, Sven Wagner wrote: Hi! For saving 3d plots I make use of the "rgl.snapshot" command provided within the rgl-Package. So far there was no problem using Windows XP, but under Windows 7 the result is a black image, however in the png-format (see attachment http://r.789695.n

Re: [R] function which can apply a function by a grouping variable and also hand over an additional variable, e.g. a weight

You might want to check out the plyr package. Hadley On Fri, Oct 1, 2010 at 6:05 AM, Werner W. wrote: > Hi, > > I was wondering if there is an easy way to accomplish the following in R: > Often I want to apply a function, e.g. weighted.quantile from the Hmisc > package > to grouped subsets of a

Re: [R] Fitting with error on data

On 27-Sep-10 08:55:13, Maayt wrote: > As this forum proved to be very helpful, I got another question... > I'd like to fit data points on which I have an error, dx and dy, > on each x and y. What would be the common procedure to fit this > data by a linear model taking into account uncertainty on e

[R] Accessing Element of a Table

I have the following structure: > str(propn) table [1:2(1d)] 0.674 0.326 - attr(*, "dimnames")=List of 1 ..$ label: chr [1:2] "o" "x" > print(propn) label o x 0.6738347 0.3261653 How can I access the value of "o" and "x" I tried this but fail > print(propn$label[,"o"]; -

Re: [R] Interpreting the example given by Frank Harrell in the predict.lrm {Design} help

Why assign them at all? Is this a "forced choice at gunpoint" problem? Remember what probabilities mean. Frank - Frank Harrell Department of Biostatistics, Vanderbilt University -- View this message in context: http://r.789695.n4.nabble.com/Interpreting-the-example-given-by-Frank-Harrell

Re: [R] RGL and Windows 7

Thanks, but your suggestions don't solve the problem. Though, the plot is storable via the rgl.postscript command, but this increases computation time and memory requirements. -- View this message in context: http://r.789695.n4.nabble.com/RGL-and-Windows-7-tp2844487p2910131.html Sent from the R

Re: [R] RGL and Windows 7

On 01/10/2010 9:53 AM, Sven Wagner wrote: Thanks, but your suggestions don't solve the problem. Though, the plot is storable via the rgl.postscript command, but this increases computation time and memory requirements. rgl.postscript is limited in the kinds of scenes it can render, so check care

Re: [R] Accessing Element of a Table

On 2010-10-01 7:43, Gundala Viswanath wrote: I have the following structure: str(propn) table [1:2(1d)] 0.674 0.326 - attr(*, "dimnames")=List of 1 ..$ label: chr [1:2] "o" "x" print(propn) label o x 0.6738347 0.3261653 How can I access the value of "o" and "x" I

Re: [R] Fitting with error on data

There is the lmodel2 package... http://cran.r-project.org/web/packages/lmodel2/vignettes/mod2user.pdf Geometric mean regression has been discussed on this list in the past, for example: https://stat.ethz.ch/pipermail/r-help/2005-June/072927.html I've used that approach with nls (rightly or wrongl

[R] Fwd: Interpreting the example given by Frank Harrell in the predict.lrm {Design} help

Frank and list, The reason I am trying to assign them is because I have a data set where i have arrived at the most likely model that describes the data and now I have another dataset where I know the factors but not the response. Therefore, surely I need to assign the predicted values to a r

Re: [R] plotting wind rose data (Karl Ropkins)

David, Following on from Jim Lemon's suggest that polar plots might be more what you need, there are both wind rose and polar plot functions in the openair package that might be of use (particularly windRose and polarFreq). They will not do everthing you are after without some careful condition

[R] Question about Reduce

Hello! In the example below the Reduce() function by default assigns "a" to be the last accumulated value and "b" to be the current value in "x". I could not find this documented anywhere as the default settings for the Reduce() function. Does any sort of documentation for this behavior exist? x

Re: [R] Scatterplot matrix - Pearson linear correlation and Density Ellipse

On 2010-09-30 15:42, ashz wrote: Hi, I have modified a known script to generate a scatterplot matrix: panel.cor = function(x, y, digits=2, prefix="Rho=", cex.cor) { usr = par("usr"); on.exit(par(usr)) par(usr = c(0, 1, 0, 1)) r = abs(cor(x, y, use="pairwise.complete.obs", metho

[R] Need to incorporate the use of na.rm into custom function

Hi, Take a matrix with missing values: > X = matrix(rnorm(10), ncol = 5) > X[2,4]=NA > X [,1] [,2] [,3] [,4] [,5] [1,] -0.1566427 -0.7382232 -1.0564624 -0.8412139 0.9370319 [2,] -1.0289865 -0.8452054 -0.1349459 NA -0.1749113 I want to apply a custom fu

Re: [R] Need to incorporate the use of na.rm into custom function

You can use na.omit on x after it is passed into your apply function if na.rm == T, or simply pass your na.rm to functions that use it, such as sum. Hope that helps, Jeff. On Fri, Oct 1, 2010 at 11:07 AM, Ochsner, Scott A wrote: > Hi, > > Take a matrix with missing values: > >> X = matrix(rnorm

[R] Creating R objects in Java

How do you call R methods from Java? I want to create a GUI using Swing in Jaa that calls R methods in Java. -- View this message in context: http://r.789695.n4.nabble.com/Creating-R-objects-in-Java-tp2904497p2904497.html Sent from the R help mailing list archive at Nabble.com. _

Re: [R] colored rasterImage()

Doh! Of course! Thanks for this. I convinced myself that the input image to rasterImage() had to be scaled 0-1. I think I started down that path by trying the following with as.raster() ... > m <- matrix(data = rep(seq(0,3, length = nx), ny), ncol = nx, nrow = ny, byrow = TRUE) > r <- as

[R] Small p-value good or bad?

Dear R-community, I have a short question: How do I interpret the result of a likelihood ratio test correctly? I am fitting a parametric survival model (with aftreg {eha}) and the output tells me the overall p-value of my model is < 0.001. My simple question is: Does the result mean my model fits

[R] help regarding the package installation

hii everyone! Recently i have started working with R and it would be nice if anyone can help me with this. I am vista user (32 bit). I wanted to install package in my parent directory i.e .Library. whenever I try to install nnet (package) it is showing me the following error: > install.packages(

Re: [R] Inserting a plot into another

hi I'll take a look at it. - [url=http://moviesonlineworld.com]watch free movies online[/url] -- View this message in context: http://r.789695.n4.nabble.com/Inserting-a-plot-into-another-tp2720936p2877931.html Sent from the R help mailing list archive at Nabble.com. _

[R] help regarding the package installation

hii everyone! Recently i have started working with R and it would be nice if anyone can help me with this. I am vista user (32 bit). I wanted to install package in my parent directory i.e .Library. whenever I try to install nnet (package) it is showing me the following error: > install.packag

[R] Looping through different arguments

If for example I have garchFit(~garch(1,1) but I want to loop through all the different combinations of ARMA/GARCH/APARCH. Another model could be ~arma(2,1)+apaarch(1,1). How do I transition between garch(1,1) and arma(2,1)+apaarch(1,1) using a for loop. -- View this message in context: http://

Re: [R] Interpreting the example given by Frank Harrell in the predict.lrm {Design} help

The reason I am trying to assign them is because I have a data set where i have arrived at the most likely model that describes the data and now I have another dataset where I know the factors but not the response. Therefore, surely I need to assign the predicted values to a response in order

[R] 'all subsets' fitting algorithm for Bayesian approach

Hi R experts I am just wondering if something is already available (or easily adaptable) to do the following. I am planning to build linear models for all possible combinations of terms, so for example if the terms are sent into a function as this string " X1 + X2 + X3 + X4 + X1:X2" I would

Re: [R] Converting a dataframe column from string to datetime

You’re working too hard. Use this: tms <- as.POSIXct(strptime(v, "%a %b %d %H:%M:%OS %Y")) Take note of the fact that there are two types of datetime objects: POSIXct and POSIXlt. Your unlist() gave what seemed a strange result because you used on an “lt” object. Had you given it a “ct” ob

Re: [R] R 2.11.1 crashes

Tal Galili gmail.com> writes: > You'll need to give more information for people to help you. > > 1) Is this the first time you installed R? Or was it a working R version > that suddenly started having this problem? > 2) Did you try uninstalling this version, downloading a new version, > install

Re: [R] help regarding the package installation

On 01/10/2010 7:39 AM, Neeti wrote: hii everyone! Recently i have started working with R and it would be nice if anyone can help me with this. I am vista user (32 bit). I wanted to install package in my parent directory i.e .Library. whenever I try to install nnet (package) it is showing me the

Re: [R] Need to incorporate the use of na.rm into custom function

Jeff, Thanks for the help. I should have thought of passing na.rm to sum. This worked nicely. Scott Scott A. Ochsner, PhD One Baylor Plaza BCM130, Houston, TX 77030 Voice: (713) 798-6227 Fax: (713) 790-1275 -Original Message- From: jsp...@gmail.com [mailto:jsp...@gmail.com] On Beha

Re: [R] Creating R objects in Java

On 10/1/10 9:18 AM, lord12 wrote: How do you call R methods from Java? I want to create a GUI using Swing in Jaa that calls R methods in Java. Look in the documentation for the rJava package -- Abhijit Dasgupta, PhD Director and Principal Statistician ARAASTAT Ph: 301.385.3067 E: adasgu...@

Re: [R] help regarding the package installation

Thank you so much... it is working fine -- View this message in context: http://r.789695.n4.nabble.com/help-regarding-the-package-installation-tp2894726p2925020.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mail

Re: [R] R-Square for Robust Regression Model

The usual way, I suppose: (1 - RSS (model with only a constant)/RSS(full model)). However, it's not particularly meaningful to do this, because points are weighted differently depending on the model. This means that the usual interpretation as the proportion of unexplained variation is wrong; and

[R] mhtplot?

Hello All: I was wondering why many plot options are not working with mhtplot. I could not find much info about this function on the web too. Any comments, any detailed manual ... Thanks, MJK [[alternative HTML version deleted]] __ R-help@r-pr

Re: [R] Question about Reduce

On Fri, 1 Oct 2010, Dimitri Liakhovitski wrote: Hello! In the example below the Reduce() function by default assigns "a" to be the last accumulated value and "b" to be the current value in "x". I could not find this documented anywhere as the default settings for the Reduce() function. Does an

[R] add a new column to data frame

Hi, I am wondering if anyone can propose a simple/best way to do the following: Let's say I have a data frame dat <- cbind(expand.grid(mode=c('right','left'),time=0:3,id=c('p1','p2','p3')),y=c(3,5,rep(4,6),6,2,rep(3,6),4,4,rep(2,6))) dat mode time id y 1 right0 p1 3 2 left0 p1

Re: [R] 'all subsets' fitting algorithm for Bayesian approach

u... You are reinventing the wheel. In fact, several wheels: the statistical literature already has several different approaches worked out for this. For example, George Box and David Steinberg did one about 20 years ago, and it has been incorporated as one of the options in the JMP DOE model c

[R] Facets in ggplot2

>Hello, > >I'm trying to introduce myself to ggplot2. I'm using syntax from the help >file, but pasting in my own data. I don't understand the error message I'm >getting. Can anyone clue me in? A Google search of this error statement >didn't return anything I could recognize as useful. >

[R] How to Install R Commander?

Hi, I am trying to install R commander. I used the command: install.packages("Rcmdr", dependencies = TRUE) It gives me this: Warning in install.packages("Rcmdr", dependencies = TRUE) : argument 'lib' is missing: using 'C:\Users\Karimi\Documents/R/win-library/2.11' trying URL 'http://cran.opens

Re: [R] Facets in ggplot2

Try this, qplot(outcome, counts, data=d.AD, facets=.~ treatment) HTH, baptiste __ 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 c

[R] cleaning up a vector

I calculated a large vector. Unfortunately, I have some measurement error in my data and some of the values in the vector are erroneous. I ended up wih some Infs and NaNs in the vector. I would like to filter out the Inf and NaN values and only keep the values in my vector that range from 1 to 2

Re: [R] cleaning up a vector

Try this: x[is.finite(x)] On Fri, Oct 1, 2010 at 2:51 PM, wrote: > I calculated a large vector. Unfortunately, I have some measurement error > in my data and some of the values in the vector are erroneous. I ended up > wih some Infs and NaNs in the vector. I would like to filter out the Inf

Re: [R] add a new column to data frame

Here are two ways: dat0 = subset(dat,time==0) one = as.data.frame(as.table(by(dat0,dat0$id, function(x)as.character(x$mode)[which.max(x$y)]))) names(one) = c('id','type') merge(dat,one) two = sapply(split(dat0,dat0$id), function(x)as.character(x$mode)[which.max(

Re: [R] cleaning up a vector

Mike, Small, reproducible examples are always useful for the rest of the us. x <- c(0, NA, NaN, 1 , 10, 20, 21, Inf) x[!is.na(x) & x >=1 & x<= 20] Is that what you're looking for? mlar...@rsmas.miami.edu wrote: I calculated a large vector. Unfortunately, I have some measurement error in my d

Re: [R] cleaning up a vector

On Fri, Oct 1, 2010 at 10:51 AM, wrote: > I calculated a large vector.  Unfortunately, I have some measurement error > in my data and some of the values in the vector are erroneous.  I ended up > wih some Infs and NaNs in the vector.  I would like to filter out the Inf > and NaN values and only k

Re: [R] How to Install R Commander?

Reinstall R and select the option for tcltk support in the installer. Uwe Ligges On 01.10.2010 19:42, kreamysaverz wrote: Hi, I am trying to install R commander. I used the command: install.packages("Rcmdr", dependencies = TRUE) It gives me this: Warning in install.packages("Rcmdr", dependen

Re: [R] cleaning up a vector

On Oct 1, 2010, at 12:51 PM, mlar...@rsmas.miami.edu wrote: > I calculated a large vector. Unfortunately, I have some measurement error > in my data and some of the values in the vector are erroneous. I ended up > wih some Infs and NaNs in the vector. I would like to filter out the Inf > and Na

Re: [R] cleaning up a vector

Complementing: findInterval(x[is.finite(x)], 1:20) On Fri, Oct 1, 2010 at 2:55 PM, Henrique Dallazuanna wrote: > Try this: > > x[is.finite(x)] > > > > On Fri, Oct 1, 2010 at 2:51 PM, wrote: > >> I calculated a large vector. Unfortunately, I have some measurement error >> in my data and some o

Re: [R] add a new column to data frame

Thank you Phil. The only problem with the code is when the 2 y values are equal, it should default to "right". Your code would default to the first maximum. But it's ok, I see the logic here and can figure it out. I wondered whether there is some one-line thing that can do this, I guess not po

[R] [Fwd: Re: cleaning up a vector]

It turns out I didn't have to filter out the 1-20 values. The code of x[is.finite(x)] did the trick. Thanks!!! Mike Original Message Subject: Re: [R] cleaning up a vector From:"Henrique Dallazuanna" Date:Fri, October 1, 2010

Re: [R] how to avoid NaN in optim()

You do not have to worry about re-defining your function to handle the constraints on parameters. You can let the optimizer worry about it. lik <- function(nO, nA, nB, nAB){ loglik <- function(par) { p=par[1] q=par[2] r <- 1 - p - q -(2 * nO * log

Re: [R] add a new column to data frame

Try this: merge(dat, factor(with(dat[!dat$time,], tapply(y, id, function(x)ifelse(all(mean(x) == x), 1, which.max(x, labels = c('right', 'left')), by.x = 'id', by.y = 0) On Fri, Oct 1, 2010 at 3:15 PM, array chip wrote: > Thank you Phil. The only problem with the code is when the 2 y values

Re: [R] Small p-value good or bad?

T. Smithson yahoo.de> writes: > > Dear R-community, > > I have a short question: How do I interpret the result of a > likelihood ratio test correctly? > > I am fitting a parametric survival model (with aftreg {eha}) and the > output tells me the overall p-value of my model is < 0.001. My > sim

[R] Pass Arguments to R with an LSF submit

I'm trying to run R in batch mode on an LSF managed cluster. In simple settings, I can do it just fine. The trouble I'm having is when I try to pass arguments to the batch job. For example, bsub R CMD BATCH --args 1 3 commandfile.R & LSF doesn't like the &, and it doesn't run. I'm hoping one

[R] gridExtra question

  Hi: I get a couple of warnings  when trying to download gridExtra: install.packages("gridExtra",repos=http://R-Forge.R-project.org)  Warning: unable to access index for repository http://R-Forge.R-project.org/bin/windows/contrib/2.10 Warning message: In getDependencies(pkgs, dependencies, avail

Re: [R] gridExtra question

Well, a quick check of http://r-forge.r-project.org/bin/windows/contrib/ shows that there is no 2.10 directory, possibly because it's not very new, 2.12 is scheduled for release in 2 weeks. Felipe Carrillo wrote: Hi: I get a couple of warnings when trying to download gridExtra: install.pack

Re: [R] gridExtra question

Forgot to mention you should be able to install from a CRAN mirror. Felipe Carrillo wrote: Hi: I get a couple of warnings when trying to download gridExtra: install.packages("gridExtra",repos=http://R-Forge.R-project.org) Warning: unable to access index for repository http://R-Forge.R-proj

Re: [R] gridExtra question

Is there some reason you don't want the CRAN version? -Ista On Fri, Oct 1, 2010 at 3:08 PM, Felipe Carrillo wrote: > > Hi: > I get a couple of warnings when trying to download gridExtra: > install.packages("gridExtra",repos=http://R-Forge.R-project.org) > > Warning: unable to access index for

Re: [R] gridExtra question

I must be blind, CRAN was  my first try and didn't see it there. It is Friday and time to take a break I guess :-)   Felipe D. Carrillo Supervisory Fishery Biologist Department of the Interior US Fish & Wildlife Service California, USA > >From: Ista Zahn >To: Felipe Carrillo >Cc: r-h...@st

Re: [R] mhtplot?

Mohsen Jafarikia gmail.com> writes: > I was wondering why many plot options are not working with mhtplot. I could > not find much info about this function on the web too. Any comments, any > detailed manual ... I'm afraid this one gets the usual answers: 1. what does "not work" mean? (Please

[R] Contrasts for MANOVA

Can anyone tell me how to run contrasts for MANOVA?  Thanks! [[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

Re: [R] Interpreting the example given by Frank Harrell in the predict.lrm {Design} help

I have this discussion fairly often with doctors that I work with. The issue is that you can certainly predict from a model, but you can predict on different scales. Let's consider the simpler case of just 2 outcomes (disease yes/no): Let's say you have 4 patients that you want to predict the

Re: [R] gridExtra question

It looks like the list of packages is not refreshing on my pc because If I go to packages > install packages I don't see it there next to 'gridBase' but I went to the CRAN website and there it is right next to 'gridBase'.  I had to manually download the Windows binary from there, saved it to my des

[R] How to apply vector value function to a multidimensional array indexed by the remaining dimensions?

Hi, I am looking for some generalization of colSums and rowSums for general vector valued functions, and for arrays of more than 2 dimensions. So as a concrete example, suppose I have a 3 dimensional array, given by x = array(1:100,c(3,4,5)). and I want to sum the 3rd index of x to obain a 3

[R] How to generate scatterplot - with a twist

Hi. I would like to make a scatterplot where all of the points are evenly spaced from each other - however, they are all the same size and occupy the entire graph. For example: x = rep(c(1:10), 10) y = rep(c(10:1), each = 10) plot(x, y, pch = 0) Gives me a scatter plot with 100 square points eac

Re: [R] [Help]:How to use "loop" to achieve this aim?

It doesn't work... where should change? Thanks. -- View this message in context: http://r.789695.n4.nabble.com/Help-How-to-use-loop-to-achieve-this-aim-tp2819894p2922193.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project

[R] writing an R code for a given model

Dear R help list, I am desperately looking for any reference explaining by examples how to write R codes in order to fit the parameters of a given model using maximum likelihood or any other criteria function. I know the general structure: First write a code for the maximum likelihood function an

Re: [R] writing an R code for a given model

Hi Abderrahim, I find this book particularly helpful: http://www.meb.ki.se/~yudpaw/likelihood/likelihood-index.htm Shige On Fri, Oct 1, 2010 at 12:15 PM, abderrahim youssef wrote: > Dear R help list, > > I am desperately looking for any reference explaining by examples how to > write  R codes i

Re: [R] [Help]:How to use "loop" to achieve this aim?

Correcting Karena's solution: for(i in 1:22) { chrn <- paste("chr",i,sep="") chrn=MEDIPS.readAlignedSeqences(BSgenome="hg19", file=chrn,numrows= ?) # no quotes around chrn chrn=MEDIPS.genomeVector(data=chrn, bin_size=50,extend=250) frames=? # I don't know how you get this variable ... ou

Re: [R] How to generate scatterplot - with a twist

On Oct 1, 2010, at 10:41 AM, thernubblet wrote: > > Hi. I would like to make a scatterplot where all of the points are evenly > spaced from each other - however, they are all the same size and occupy the > entire graph. For example: > > x = rep(c(1:10), 10) > y = rep(c(10:1), each = 10) > plot(x

Re: [R] can I add line breaks to the paste() function?

Thanks for the help. This solves my problem - I wanted to print out errors and warnings on separate lines with a single call. Thanks, David On Thu, Sep 30, 2010 at 3:42 PM, Jeremy Miles wrote: > Try using cat instead.  Then "\n" is the new line character. > > E.g. >  cat("1st line\n2nd line\n")

[R] maximum likelihood problem

I am trying to figure out how to run maximum likelihood in R. Here is my situation: I have the following equation: equation<-(1/LR-(exp(-k*T)*LM)*(1-exp(-k))) LR, T, and LM are vectors of data. I want to R to change the value of k to maximize the value of equation. My attempts at optim and opt

Re: [R] How to generate scatterplot - with a twist

If it is important to have points rather than just create the grid, then you could do something using the my.symbols function in the TeachingDemos package. One of the examples on the help page fills the plot with hexagons, the calculations for squares should be simpler. -- Gregory (Greg) L. S

Re: [R] maximum likelihood problem

Do you want to do a nonlinear least-squares estimation (which is MLE if the errors are Gaussian)? If so, you have to define a function that takes the parameter (k) and data matrix (LR, T, LM), as arguments, and returns a scalar, which is the residual sum of squares. Then you can optimize (minimiz

[R] [R-pkgs] ff version 2.2.0

Dear R community, The next release of package ff is available on CRAN. With kind help of Brian Ripley it now supports the Win64 and Sun versions of R. It has three major functional enhancements: a) new fast in-memory sorting and ordering functions (single-threaded) b) ff now supports on-disk so

Re: [R] writing an R code for a given model

Shige Song gmail.com> writes: > > Hi Abderrahim, > > I find this book particularly helpful: > http://www.meb.ki.se/~yudpaw/likelihood/likelihood-index.htm > > Shige > > On Fri, Oct 1, 2010 at 12:15 PM, abderrahim youssef > googlemail.com> wrote: > > Dear R help list, > > > > I am desperately

[R] plm: lag() and diff() do not (always) recognize a gap in the time dimension

Hello! I came accross a strange behavior of the plm package. When using an unbalanced panel with years lag() and diff() do not recognize a break in the time dimension. It does, however, if there is only one more year after the break. This is strange, right? Consider the following example: > lib

Re: [R] How to apply vector value function to a multidimensional array indexed by the remaining dimensions?

On Fri, 1 Oct 2010, yunjiangster wrote: Hi, I am looking for some generalization of colSums and rowSums for general vector valued functions, and for arrays of more than 2 dimensions. So as a concrete example, suppose I have a 3 dimensional array, given by x = array(1:100,c(3,4,5)). and I want

Re: [R] Interpreting the example given by Frank Harrell in the predict.lrm {Design} help

Well put Greg. The job of the statistician is to produce good estimates (probabilities in this case). Those cannot be translated into action without subject-specific utility functions. Classification during the analysis or publication stage is not necessary. Frank - Frank Harrell Departme

[R] How many R packages are not free?

Hello Everyone,   Just finished reading A Handbook of Statistical Analyses using R by Everitt and Hothorn. I'll begin by saying that I quite liked the book. It's both little and mighty in the sense that it's very compact but contains a tremendous amount of useful material.   The last chapter of

[R] element wise conditional assignment in r

Hi, I am looking for a one-liner code for the following situation say I have a vector r of 0 and 1's, and another vector v of equal length. I want to assign v[i]-1 to v[i] if r[i]=1, for all i. How would I do that using mapply or any other batch processing keywords? thanks. John -- View this

[R] Suppressing printing in the function

Hello! I wrote a function that returns a data frame. Nowhere in the function do I say print(my.data.frame), but when I run the function - the data frame is printed on the console. Is there any way to suppress it? Thank you! -- Dimitri Liakhovitski Ninah Consulting www.ninah.com ___

Re: [R] Suppressing printing in the function

?invisible - Phil Spector Statistical Computing Facility Department of Statistics UC Berkeley

Re: [R] element wise conditional assignment in r

John - Is this what you're looking for? r = sample(c(0,1),10,replace=TRUE) r [1] 0 1 0 1 1 0 0 1 0 1 v = 1:10 ifelse(r == 1,v-1,v) [1] 1 1 3 3 4 6 7 7 9 9 - Phil Spector Statistical Computing Facility

  1   2   >