Re: [R] Code to construct table with paired data

Thank you Peter! Great solutions! That's exactly what I was looking for. Maurício Cardeal Em 08/04/2017 09:11, peter dalgaard escreveu: > Here's one way: > >> ddw <- reshape(dd, direction="wide", idvar="pair", timevar="treatfac") >> names(ddw) > [1] "pair" "imprfac.A" "imprfac.B" >>

Re: [R] change the R home directory

Change to the desired directory before starting R. -- Sent from my phone. Please excuse my brevity. On April 8, 2017 10:40:13 AM PDT, Da Zheng wrote: >Hello, > >By default, the home directory of R is "/usr/lib/R" in Ubuntu. >Everything works fine. > >However, when I

[R] change the R home directory

Hello, By default, the home directory of R is "/usr/lib/R" in Ubuntu. Everything works fine. However, when I installed Jupyter notebook and the R kernel with anaconda2, it seems the R home directory is changed to some directory in anaconda2. This messes up compilation and linking. I wonder how I

Re: [R] difference metric info of same font on different device

On 2017/4/7 23:13, Jeff Newmiller wrote: I think it is a fundamental characteristic of graphics drivers that output will look different in the details... you are on a wild goose chase. Postscript in particular has a huge advantage in font presentation over other graphics output mechanisms.

Re: [R] difference metric info of same font on different device

On 2017/4/7 23:13, Jeff Newmiller wrote: I think it is a fundamental characteristic of graphics drivers that output will look different in the details... you are on a wild goose chase. Postscript in particular has a huge advantage in font presentation over other graphics output mechanisms.

Re: [R] Paired sample t-test with mi.t.test

Dear Dr. Eichner and Dr. Kohl, First, thank you for your response. I tried your code and R it worked perfectly I just had to add: mi.t.test(implist*$imputation,* "pre_test", "post_test", alternative = "greater", paired = TRUE, var.equal = TRUE, conf.level = 0.95) for the code to run. Thank you

[R] mgcv gam/bam model selection with random effects and AR terms

Would be grateful for advice on gam/bam model selection incorporating random effects and autoregressive terms. I have a multivariate time series recorded on ~500 subjects at ~100 time points. One of the variables (A) is the dependent and four others (B to E) are predictors. My basic formula

Re: [R] Code to construct table with paired data

Here's one way: > ddw <- reshape(dd, direction="wide", idvar="pair", timevar="treatfac") > names(ddw) [1] "pair" "imprfac.A" "imprfac.B" > xtabs(~ imprfac.A + imprfac.B, ddw) imprfac.B imprfac.A + - + 1 3 - 2 1 (reshape() is a bit of a pain to wrap one's mind

[R] Code to construct table with paired data

Hi! Is it possible to automatically construct a table like this: #treat B # improvement # + - #treat A improvement + 1 3 # - 2 1 From these data: pair <-

Re: [R] Archive format

Hi Joe, I have read your question with great interest. I am a little bit astonished to read about your project. There is a big national institute in Germany called GESIS (https://de.wikipedia.org/wiki/GESIS_%E2%80%93_Leibniz-Institut_f%C3%BCr_Sozialwissenschaften) which does the same job you