Re: [R] Comparison of correlation coefficients
Anupam Tyagi yahoo.com> writes: > It seem the more complicated case is often of more substantive interest in > many > settings: is children's income more strongly correlated with parent's > education > than parent's income? An even better example (same measurement scale)---Questions like this get asked quite often in practice: Is a child's income/wealth more strongly correlated with a parent's income than parent's wealth? And some variants. I think there is some literature on inference on marginals and conditional distributions, and bounds that may be useful: Search: James Heckman, Charles Manski. Anupam. __ R-help@stat.math.ethz.ch 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, minimal, self-contained, reproducible code.
Re: [R] Comparison of correlation coefficients
Peter Dalgaard biostat.ku.dk> writes: > No, he wants to compare two correlation coefficients, not test that > one is zero. That's usually a misguided question, but if need be, the > Fisher z transform atanh(r) can be used to convert r to an > approximately normal variate with a known variance 1/(N-3) and > comparing r1 and r2 from two independent samples is straightforward. > The correlated case (like cor(x,y) vs cor(x,z)) is more complicated. It seem the more complicated case is often of more substantive interest in many settings: is children's income more strongly correlated with parent's education than parent's income? __ R-help@stat.math.ethz.ch 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, minimal, self-contained, reproducible code.
Re: [R] Comparison of correlation coefficients
Dear Donglei Hu, If you have two correlation coefficients, you may try cordif {multilevel} and cordif.dep {multilevel} for the independent correlations and for the dependent correlations, respectively. However, they are both based on the sampling distribution of correlation coeficient. A better approach may be the one based on the Fisher z transformation as suggested. The papers by Olkin and Finn (1995) and Steiger (1980) may be relevant for you. If you have more than two independent correlation coefficients, meta-analysis may be a better choice. You may also choose between the approaches based on correlations (Hunter and Schmidt) or Fisher z transformation (Hedges and Olkin). If the correlations are dependent, structural equation modeling (SEM) is a more convenient approach (e.g., Cheung & Chan, 2004). Cheung, M.W.L., & Chan, W. (2004). Testing dependent correlation coefficients via structural equation modeling. Organizational Research Methods, 7, 206-223. Olkin, I., & Finn, J. D. (1995). Correlation redux. Psychological Bulletin, 118, 155-164. Steiger, J. H. (1980). Tests for comparing elements of a correlation matrix. Psychological Bulletin, 87, 245-251. Regards, Mike -- --- Mike W.L. Cheung Department of Psychology National University of Singapore Homepage: http://courses.nus.edu.sg/course/psycwlm/internet/ --- On 19 Sep 2006 01:22:47 +0200, Peter Dalgaard <[EMAIL PROTECTED]> wrote: > > "David Barron" <[EMAIL PROTECTED]> writes: > > > Is cor.test() in the stats packages what you mean? > > No, he wants to compare two correlation coefficients, not test that > one is zero. That's usually a misguided question, but if need be, the > Fisher z transform atanh(r) can be used to convert r to an > approximately normal variate with a known variance 1/(N-3) and > comparing r1 and r2 from two independent samples is straightforward. > The correlated case (like cor(x,y) vs cor(x,z)) is more complicated. > > > > > On 18/09/06, Hu, Donglei <[EMAIL PROTECTED]> wrote: > > > Hi, > > > > > > > > > > > > I calculated a few correlation coefficients. Now I want to know > whether > > > they are different from each other. Is there an R package that can do > > > such a comparison? Thanks for any suggestion. > > > > > > > > > > > > Best, > > > > > > Donglei Hu > > > > > > Department of Medicine > > > > > > UCSF > > > > > > > > > [[alternative HTML version deleted]] > > > > > > __ > > > R-help@stat.math.ethz.ch 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, minimal, self-contained, reproducible code. > > > > > > > > > -- > > = > > David Barron > > Said Business School > > University of Oxford > > Park End Street > > Oxford OX1 1HP > > > > __ > > R-help@stat.math.ethz.ch 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, minimal, self-contained, reproducible code. > > > > -- >O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B > c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K > (*) \(*) -- University of Copenhagen Denmark Ph: (+45) > 35327918 > ~~ - ([EMAIL PROTECTED]) FAX: (+45) > 35327907 > > __ > R-help@stat.math.ethz.ch 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, minimal, self-contained, reproducible code. > [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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, minimal, self-contained, reproducible code.
Re: [R] Comparison of correlation coefficients
"David Barron" <[EMAIL PROTECTED]> writes: > Is cor.test() in the stats packages what you mean? No, he wants to compare two correlation coefficients, not test that one is zero. That's usually a misguided question, but if need be, the Fisher z transform atanh(r) can be used to convert r to an approximately normal variate with a known variance 1/(N-3) and comparing r1 and r2 from two independent samples is straightforward. The correlated case (like cor(x,y) vs cor(x,z)) is more complicated. > On 18/09/06, Hu, Donglei <[EMAIL PROTECTED]> wrote: > > Hi, > > > > > > > > I calculated a few correlation coefficients. Now I want to know whether > > they are different from each other. Is there an R package that can do > > such a comparison? Thanks for any suggestion. > > > > > > > > Best, > > > > Donglei Hu > > > > Department of Medicine > > > > UCSF > > > > > > [[alternative HTML version deleted]] > > > > __ > > R-help@stat.math.ethz.ch 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, minimal, self-contained, reproducible code. > > > > > -- > = > David Barron > Said Business School > University of Oxford > Park End Street > Oxford OX1 1HP > > __ > R-help@stat.math.ethz.ch 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, minimal, self-contained, reproducible code. > -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@stat.math.ethz.ch 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, minimal, self-contained, reproducible code.
Re: [R] Comparison of correlation coefficients
Is cor.test() in the stats packages what you mean? On 18/09/06, Hu, Donglei <[EMAIL PROTECTED]> wrote: > Hi, > > > > I calculated a few correlation coefficients. Now I want to know whether > they are different from each other. Is there an R package that can do > such a comparison? Thanks for any suggestion. > > > > Best, > > Donglei Hu > > Department of Medicine > > UCSF > > > [[alternative HTML version deleted]] > > __ > R-help@stat.math.ethz.ch 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, minimal, self-contained, reproducible code. > -- = David Barron Said Business School University of Oxford Park End Street Oxford OX1 1HP __ R-help@stat.math.ethz.ch 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, minimal, self-contained, reproducible code.
[R] Comparison of correlation coefficients
Hi, I calculated a few correlation coefficients. Now I want to know whether they are different from each other. Is there an R package that can do such a comparison? Thanks for any suggestion. Best, Donglei Hu Department of Medicine UCSF [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch 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, minimal, self-contained, reproducible code.
[R] Comparison of correlation coefficients
Dear expeRts Is it possible to compare correlation coefficients or to normalize different correlation coefficients? Concretely, we have the following situation: We have gene expression profiles for different tissues, where the number of samples per tissue are different, ranging from 10 to 250. We are able to determine the correlation between two genes A and B for each tissue separately, using "cor.test". However, the question arises if the correlation coefficients between different tissues can be compared or if they must somehow be "normalized", since the number of samples per tissue varyies. Searching the web I found the function "compcorr", see: http://www.fon.hum.uva.nl/Service/Statistics/Two_Correlations.html http://ftp.sas.com/techsup/download/stat/compcorr.html and implemented it in R: compcorr <- function(n1, r1, n2, r2){ # compare two correlation coefficients # return difference and p-value as list(diff, pval) # Fisher Z-transform zf1 <- 0.5*log((1 + r1)/(1 - r1)) zf2 <- 0.5*log((1 + r2)/(1 - r2)) # difference dz <- (zf1 - zf2)/sqrt(1/(n1 - 3) + (1/(n2 - 3))) # p-value pv <- 2*(1 - pnorm(abs(dz))) return(list(diff=dz, pval=pv)) } Would it make sense to use the resultant p-value to "normalize" the correlation coefficients, using: corr <- corr * compcorr()$pval Is there a better way or an alternative to "normalize" the correlation coefficients obtained for different tissues? Thank you in advance for your help. Since in the company I am not subscribed to r-help, could you please reply to me (in addition to r-help) Best regards Christian Stratowa == Christian Stratowa, PhD Boehringer Ingelheim Austria Dept NCE Lead Discovery - Bioinformatics Dr. Boehringergasse 5-11 A-1121 Vienna, Austria Tel.: ++43-1-80105-2470 Fax: ++43-1-80105-2782 email: [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html