HI, library(MBESS) Cor.mat <- matrix(c(1,0.5,0.5,1),nrow=2)
Sd<- c(0.07,0.05) Covmat<-cor2cov(Cor.mat,Sd) Covmat # [,1] [,2] #[1,] 0.00490 0.00175 #[2,] 0.00175 0.00250 cov2cor(Covmat) # [,1] [,2] #[1,] 1.0 0.5 #[2,] 0.5 1.0 Cor.mat2<-matrix(c(1,0.2,0.8,0.2,1,0.6,0.8,0.6,1),nrow=3) Sd2<- c(0.7,0.5,0.3) Covmat2<- cor2cov(Cor.mat2,Sd2) Covmat2 # [,1] [,2] [,3] #[1,] 0.490 0.07 0.168 #[2,] 0.070 0.25 0.090 #[3,] 0.168 0.09 0.090 cov2cor(Covmat2) # [,1] [,2] [,3] #[1,] 1.0 0.2 0.8 #[2,] 0.2 1.0 0.6 #[3,] 0.8 0.6 1.0 identical(Cor.mat2,cov2cor(Covmat2)) #[1] TRUE A.K. >Hello, >I am totally new to R. >I am trying to convert a corr. matrix to a covar. one but keep getting the >same error. >> Cor.mat <- matrix(c(1,0.5,0.5,1),nrow=2) >> Sd <- matrix(c(0.07,0.05),nrow=1,ncol=2) >> cor2cov(Cor.mat,Sd) >Error in diag(sd) %*% cor.mat : non-conformable arguments > >I´ve tried all possible combinations for st.dev vector Sd >(nrow=1,ncol=2;nrow=2,ncol=1) but to no avail. >Your help will be very appreciated. > >Regards, >Artur ______________________________________________ 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, minimal, self-contained, reproducible code.
