Re: [R] "no 'nobs' method available" error when using BIC selection in glmulti with genetic algorithm and lmer

On Tue, 25 Mar 2014, Alicia Ellis wrote: I am running glmulti with the lme function and selection using BIC. When I do this, I get the following error: In general, in such situations, it's easiest to use AIC() rather than BIC() and supply the correct log-number of observations: AIC(my_objec

[R] How to creat a dummy coding in R? (URGENT!)

Hi, it's so urgent that I really need your help on R. This following is part of my data, do u know how to create a dummy coding about it in R? My control group is Owner occupier. Many thanks for your big help!!!:) *AppHomeStatus* Owner occupier Living with parents Living with parents Private tenan

[R] ? ~ ADONIS

Hello, I am an R noivce, so excuse my simple questions . My data have 5 respone variales (each 109 rows) and three independent variables, each with two levels [Age Class(A,SA), Repro State(L,NL) and Sex of Calf(F,M. *some females do not have calves so NA)]. My data are not normally distributed wit

Re: [R] R mail list archive Google search function not work

On 26/03/14 12:51, David Winsemius wrote: On Mar 25, 2014, at 9:52 AM, Luo Weijun wrote: Dear Robert and R project team, I notice that the Google search function on the R mail list archives page has stopped working for quite a while, http://tolstoy.newcastle.edu.au/R/. Is there any solution o

Re: [R] R mail list archive Google search function not work

On Mar 25, 2014, at 9:52 AM, Luo Weijun wrote: > Dear Robert and R project team, > I notice that the Google search function on the R mail list archives page has > stopped working for quite a while, http://tolstoy.newcastle.edu.au/R/. > Is there any solution on this or this has been move to anoth

[R] Bootstrapping mean for two and more variables by group

Hi R User, Would you give me some hints on how I can calculate bootstrapping mean+-SE for each column based by group. I searched it but I could not get what I wanted. For example I have these data set data <- as.data.table(list(x1 = runif(200), x2 = runif(200), group = runif(200)>0.5)) I wante

Re: [R] How to select multiple cells in a matrix and perform an operation on corresponding cells in another matrix of the same size?

On 03/25/2014 11:36 PM, Vermeulen, Lucie wrote: Hi Jim, Thanks for your help! I tried it on my own data, but there seems to be a problem with NA values. For regions where there is no flow or pollutant, my cells are NA. Using your script below changed to include NA's in flowmat, I get the error

Re: [R] Digits in R

Thank you for the difference between print() and round(). I have never noticed that!! Best, KK On Tue, Mar 25, 2014 at 3:17 PM, William Dunlap wrote: > > The round() function lets you specify the number of decimal > > places directly: > > > > round(vars, 4) > > round() and print() don't alwa

Re: [R] Bars on stl() plot [RESOLVED]

A common R paradigm is to have a function do the computations, then separate functions to do the plotting and printing. So you look at the main function (e.g. stl) for the options related to the actual calculations, but then look for a function like plot.stl and/or print.stl for the options on the

Re: [R] Syntax for order()

Okay I feel spoilt all over again. :) John Kane Kingston ON Canada > -Original Message- > From: h.wick...@gmail.com > Sent: Tue, 25 Mar 2014 14:24:00 -0500 > To: jrkrid...@inbox.com > Subject: Re: [R] Syntax for order() > > If you want to continue to be spoiled, try: > > library(d

Re: [R] Syntax for order()

If you want to continue to be spoiled, try: library(dplyr) arrange(dat1, val) Hadley On Tue, Mar 25, 2014 at 2:20 PM, John Kane wrote: > Thank. > > Once I got Sarah's email I realised I should have been usling with(). > Hadley's ggplot syntax has spoiled/confused me. > > John Kane > Kingston

Re: [R] Syntax for order()

Thank. Once I got Sarah's email I realised I should have been usling with(). Hadley's ggplot syntax has spoiled/confused me. John Kane Kingston ON Canada > -Original Message- > From: seeliger.c...@epa.gov > Sent: Tue, 25 Mar 2014 19:02:22 + > To: r-help@r-project.org, jrkrid...@

Re: [R] Digits in R

> The round() function lets you specify the number of decimal > places directly: > > round(vars, 4) round() and print() don't always agree on meaning of "the number of digits". In addition, rounding is not a transitive operation - rounding a rounded number does not always give you a rounding of

Re: [R] Syntax for order()

>> dat1[order(val), ] # Gives Error in order(val) : object 'val' not found >> >> dat1[order(dat1[,2]), ] # Works just fine. > > dat1[order(dat1$val), ] > > unless you used attach(dat1). Better to avoid 'attach' altogether and go with the first suggestion. That can get rather unwieldy when orde

Re: [R] Syntax for order()

On 03/25/2014 02:36 PM, John Kane wrote: Has there been a change in the syntax for order() or am I just making some stupid mistake here? dat1 <-read.table(text=" name val Alex 4 Jim 10 Fred 8 Julie 44 ",sep="",header=TRUE,stringsAsFactors=FALSE) dat1[order(val), ] # Gives Error in order(val) :

Re: [R] Syntax for order()

I "knew" it was almost certainly something really stupid. Thanks very much. John Kane Kingston ON Canada > -Original Message- > From: sarah.gos...@gmail.com > Sent: Tue, 25 Mar 2014 14:40:50 -0400 > To: jrkrid...@inbox.com > Subject: Re: [R] Syntax for order() > > dat1[order(dat1$val

Re: [R] Syntax for order()

dat1[order(dat1$val), ] unless you used attach(dat1). Sarah On Tue, Mar 25, 2014 at 2:36 PM, John Kane wrote: > Has there been a change in the syntax for order() or am I just making some > stupid mistake here? > > dat1 <-read.table(text=" > name val > Alex 4 > Jim 10 > Fred 8 > Julie 44 > ",s

[R] Syntax for order()

Has there been a change in the syntax for order() or am I just making some stupid mistake here? dat1 <-read.table(text=" name val Alex 4 Jim 10 Fred 8 Julie 44 ",sep="",header=TRUE,stringsAsFactors=FALSE) dat1[order(val), ] # Gives Error in order(val) : object 'val' not found dat1[order(dat1[,2

Re: [R] How to get a subset with a date such as Date=11/03/2013 HE=02*?

Sorry I thought I was being clear. These is how the time values in columns are downloaded from online (http://ets.aeso.ca/). When there is an extra hour in the date there are two hour ending twos in the that day (HE02 and HE02*). I did not create the data this way. What is a good way of dealing

[R] tripack package

Hi, I'm trying to label the points on my voronoi diagram, but I'm not sure how to do this with the tripack library. Best, Monaly [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r

[R] Principal Components Loadings

Hello All, I have a dataset "bodysize.Rdata" from Journal of Statistics Education Data Archive, which I have attached here. I am trying to do principal components analysis on it using princomp, and it seems to be working fine. However, I am really struggling in interpretating the loadings of PC

Re: [R] install gam in LINUX R

Hi Prof. Brian, Thanks. The full info is pretty long: 23941 continue 1 Warning: Label 23941 at (1) defined but not used linear.f:2557.5: 23937 continue 1 Warning: Label 23937 at (1) defined but not used linear.f:2553.5: 23935 continue 1 Warning: Label 23935 at (1) defined but not

Re: [R] Digits in R

Thank you Qiang Kou , it worked :) Appreciate it. From: Qiang Kou To: Pavneet Arora/UK/RoyalSun@RoyalSun Cc: R help Date: 25/03/2014 13:37 Subject:Re: [R] Digits in R Have you tried "round(vars, digits = 4)" ? KK On Tue, Mar 25, 2014 at 7:17 AM, Pavneet Arora < pa

[R] "no 'nobs' method available" error when using BIC selection in glmulti with genetic algorithm and lmer

I am running glmulti with the lme function and selection using BIC. When I do this, I get the following error: no 'nobs' method is available I am running this on R version 3.0.3 and on a server with multiple cores and a ton of memory. The model seems to work fine if I do selection with AIC whic

[R] Residuals of tobit{AER} and testing distribution normality

Hallo. What are the residuals returned by resid() in this code? library(AER) m <- tobit(y ~ x1 + x2, data=dat) rr <- resid(m2, type = "response") Can I use them to test the normality of the random variable distribution this way? qqnorm(rr) shapiro.test(rr) And is it correct to handle heteroske

Re: [R] Bars on stl() plot

... where you should expect the info -- in ?plot.stl Pointer: Learn about S3 methods -- e.g. by reading An Intro to R or web tutorial of your choice. Cheers, Bert Bert Gunter Genentech Nonclinical Biostatistics (650) 467-7374 "Data is not information. Information is not knowledge. And knowledge

Re: [R] Bars on stl() plot [RESOLVED]

On Tue, 25 Mar 2014, Greg Snow wrote: Look at ?plot.stl and read the section on "range.bars". Basically the bars are all the same height in user coordinates, so it gives a feeling of the relative scale of each panel. Thanks, Greg. I was not aware of plot.stl so I appreciate your making me a

Re: [R] problem with previous code

Hi Elio, I guess the error is here:     as.vector(sapply(lst2,rownames)) #still a list length(unique(as.vector(sapply(lst2,rownames))) )# length of list #22 uNrownames <- unique(unlist(sapply(lst2,rownames)))  length(uNrownames) #[1] 90 res <- matrix(0,nrow=length(uNrownames),ncol=length(uN

Re: [R] Bars on stl() plot

Look at ?plot.stl and read the section on "range.bars". Basically the bars are all the same height in user coordinates, so it gives a feeling of the relative scale of each panel. On Tue, Mar 25, 2014 at 11:32 AM, Rich Shepard wrote: > This command produced the attached plot: > dalles.disch.stl

[R] Bars on stl() plot

This command produced the attached plot: dalles.disch.stl <- stl(dalles.disch.no.na, "per") There are narrow, vertical, grey bars along the right axis for each plot and I would like to learn what they represent and where this is documented. A pointer is appreciated. Rich dalles-dam-disch

[R] R mail list archive Google search function not work

Dear Robert and R project team, I notice that the Google search function on the R mail list archives page has stopped working for quite a while, http://tolstoy.newcastle.edu.au/R/. Is there any solution on this or this has been move to another webpage? I know Google advance search can be used but

Re: [R] Customise a symbol in a scatterplot with for loop

The mk_pent function returns a matrix with 2 columns that is stored into a variable I called tmp. The x-values are in the first column and tmp[,1] is the first column of tmp, tmp[,2] is the second column, the y-values. This is covered in "An Introduction to R" and you can also find discussion in

Re: [R] Extraction of few columns with desired values

HI, May be this helps: dat <- read.table(text="GENEID    Chrom 2211 x 2200    y 2412 xy 2456 x 2476 het",sep="",header=TRUE,stringsAsFactors=FALSE) subset(dat,Chrom=="x",select="GENEID") #  GENEID #1   2211 #4   2456 A.K. Hello I have generated this script an

Re: [R] Digits in R

On 25/03/2014 7:17 AM, Pavneet Arora wrote: Hello All, I am new in R, so please excuse the basic questions. But how do you change the number of digits to be displayed? I have done the following, hoping I will get 4 decimal places in my answer: vars <- var(cbind(Sepal.l,Sepal.w,Petal.l,Petal.w)

Re: [R] Digits in R

The digits option gives you the number of significant digits (ignoring leading zeros after the decimal) and it operates on a column by column basis. The first and second columns have values with a leading zero after the decimal (-0.04074 in both columns) so R prints five decimal places to get four

Re: [R] install gam in LINUX R

On 25/03/2014 13:57, qingqing.x...@rriny.com wrote: This was the error: /usr/include/gnu/stubs.h:7:27: error: gnu/stubs-32.h: No such file or directory As I guessed, completely inappropriate for R-help, and not about R at all. Your Linux installation is broken: my guess is that you are tryin

Re: [R] Digits in R

On 25/03/2014 7:17 AM, Pavneet Arora wrote: Hello All, I am new in R, so please excuse the basic questions. But how do you change the number of digits to be displayed? I have done the following, hoping I will get 4 decimal places in my answer: vars <- var(cbind(Sepal.l,Sepal.w,Petal.l,Petal.w)

Re: [R] How to select multiple cells in a matrix and perform an operation on corresponding cells in another matrix of the same size?

Couple of comments, but as I have not followed this closely, take them with salt. 1. I would have thought that no flow or pollutants should be recorded as zeros, not NA's. So don't you want to first change these to zeros? If some of the NA's are actually missings, then I think you have potentially

Re: [R] Digits in R

Have you tried "round(vars, digits = 4)" ? KK On Tue, Mar 25, 2014 at 7:17 AM, Pavneet Arora < pavneet.ar...@uk.rsagroup.com> wrote: > Hello All, > > I am new in R, so please excuse the basic questions. > But how do you change the number of digits to be displayed? > > I have done the following,

Re: [R] How to select multiple cells in a matrix and perform an operation on corresponding cells in another matrix of the same size?

Hi Jim, Thanks for your help! I tried it on my own data, but there seems to be a problem with NA values. For regions where there is no flow or pollutant, my cells are NA. Using your script below changed to include NA's in flowmat, I get the error message "Error in if (selected_cells[row, col])

[R] Digits in R

Hello All, I am new in R, so please excuse the basic questions. But how do you change the number of digits to be displayed? I have done the following, hoping I will get 4 decimal places in my answer: vars <- var(cbind(Sepal.l,Sepal.w,Petal.l,Petal.w)) print(vars,digits=4) But as seen below fro

Re: [R] Calculations with aggregate data: confidence intervals

Hi Luigi, You could also use: library(Rmisc)  group.CI(copy~stimulation,my.data)[,-3] A.K. On Tuesday, March 25, 2014 6:19 AM, Jorge I Velez wrote: Hi Luigi, Thanks for sending the data in reproducible format.  Perhaps something like this? aggregate(my.data[,3], list(my.data[,2]), FUN = f

Re: [R] Bayesian Regression with half-normal distributions

I can't work out exactly what you are trying to do, but it sounds like the sort of problem that should be fairly easy to set up in BUGS or JAGS, which can both be run through R. Bob On 25 March 2014 11:35, Jochen Mattes wrote: > Hi, > > thanks, I've seen that page, but I cannot find module tha

Re: [R] Bayesian Regression with half-normal distributions

Hi, thanks, I've seen that page, but I cannot find module that supports folded Gaussians. Has anyone got experiences with that kind of problem? Best, Jochen On 25.03.2014 07:44, Frede Aakmann Tøgersen wrote: Hi Perhaps you can find something at http://cran.r-project.org/web/views/Bayesian

Re: [R] Calculations with aggregate data: confidence intervals

Hi Luigi, Thanks for sending the data in reproducible format. Perhaps something like this? aggregate(my.data[,3], list(my.data[,2]), FUN = function(x) t.test(x)$ conf.int[1:2]) #Group.1 x.1 x.2 #1 Unstimulated 5.296492e+02 2.410510e+03 #2ESAT6 9.105338e+00 4.078

[R] Calculations with aggregate data: confidence intervals

Dear all, I would like to calculate the confidence intervals on aggregate data. I know how to do this using the t test, but it did not work together with the aggregate function. Is there a function that can be applied to the aggregate function to obtain the (95%) confidence intervals, rather than a

Re: [R] randomForest warning: The response has five or fewer unique values. Are you sure you want to do regression?

Dear Andy, Thank you for your help! Below are the full details of what I am doing in R along with the data structure, so hopefully this will help. Okay so the warning is just a warning and nothing to worry about when doing regression. But why is randomForest only producing regression trees for eac