In an attempt to learn to use the rv package, I have been working through the examples in Jouni Kerman and Andrew Gelman's "Using Random Variables to Manipulate and Summarize Simulations in R" (July 4, 2007).
I am using a Dell Precision 380n computer running Gentoo Linux and R 2.2.1 (the latest available through Gentoo's portage/emerge system). Everything worked well until I tried the following command (found on p. 2 of the document): beta <- rvnorm(mean=beta.hat, var=V.beta*sigma^2) That command produced the following error message: Error in .rvmvnorm(n = n, mean = mean, Sigma = var) : Invalid (non-numeric) covariance matrix Sigma Any suggestions for interpreting the error message or correcting the problem would be much appreciated. Pasted below, in case it is useful, is my R file: ****R file begins here ************************** # This is a file of R commands to test Kerman and Gelman's package rv. # It is based on their "Using Random Variables to Manipulate and # Summarize Simulations in R,", July 4, 2007. testscores <- read.table("rv_data.txt",header=TRUE) # Extract data. attach(testscores) # Put testscores in R search path testscores[1:2,] # Print first 2 observations testscores[14:15,] # Print last 2 observations x <- testscores[,1] # midterm scores y <- testscores[,2] # final exam scores testlm <- lm(y ~ x) # fit linear model by OLS sigma.hat <- sqrt(deviance(testlm)/df.residual(testlm)) # deviance(testlm) is equivalent to sum(residuals(testlm)^2) beta.hat <- coefficients(testlm) V.beta <- vcov(testlm)/(sigma.hat^2) # unscaled covariance matrix n <- 10 library(rv) sigma <- sigma.hat*sqrt((n-2)/rvchisq(df=n-2)) # default number of simulations # is 1000 beta <- rvnorm(mean=beta.hat, var=V.beta*sigma^2) ****R file ends here ********************* Best regards, John -- John P. Burkett Department of Environmental and Natural Resource Economics and Department of Economics University of Rhode Island Kingston, RI 02881-0808 USA phone (401) 874-9195 ______________________________________________ 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.