Dear James, Model-implied variances and covariances of the non-error variables (observed and latent) are given by (I - A)^-1 P [(I - A)^-1]', where the A and P matrices are from the RAM formulation of the model, and are in the object returned by sem(), and I is an identity matrix. Your model presumably includes estimated error variances for the endogenous variables in the model. Subtract these from the variances to get "variance explained."
I hope this helps, John -------------------------------- John Fox Senator William McMaster Professor of Social Statistics Department of Sociology McMaster University Hamilton, Ontario, Canada web: socserv.mcmaster.ca/jfox > -----Original Message----- > From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On > Behalf Of James Stegen > Sent: November-10-10 10:33 AM > To: r-help@r-project.org > Subject: [R] sem: variance explained > > Hi, does anyone know if there is a way to extract the variance of each > variable explained in a structural equation model when using the sem() > function? > Thanks, > James Stegen > > -- > James C. Stegen > NSF Postdoctoral Fellow in Bioinformatics > University of North Carolina > Chapel Hill, NC > 919-962-8795 > ste...@email.unc.edu > http://www.unc.edu/~stegen/index.html > > ______________________________________________ > 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. ______________________________________________ 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.
