Dear Thomas,
I'm not sure that you wanted something that outputs LaTeX code, but if so,
here's a bit of code that I use. It doesn't take multiple models, so
it's
not exactly what you want, but with some trivial cutting and pasting, it
should be ok. As you can see, it only tests significance at the 0.05 level,
but that could be easily changed as well.
HTH,
Dave
outreg <- function(object, fit=TRUE){
coef <- coef(object)
t.obj <- coef/sqrt(diag(vcov(object)[1:length(coef), 1:length(coef)]))
s.e <- sqrt(diag(vcov(object)[1:length(coef), 1:length(coef)]))
p.val <- 1-pnorm(abs(t.obj))
out.mat <- matrix(NA, ncol=2, nrow=2*length(coef))
l <- 1
for(i in seq(from=1, to=2*length(coef), by=2)){
out.mat[i, 1] <- if(p.val[l]<0.05) paste(round(coef[l], 3),
"*",
sep="") else round(coef[l], 3)
out.mat[i+1, 1] <- paste("(",
paste(if(as.character(round(s.e[l],
3)) == "0") "0.000"
else round(s.e[l], 3), ")", sep=""),
sep="")
out.mat[i, 2] <- names(coef)[l]
out.mat[i+1, 2] <- c("")
l <- l+1
}
row.names(out.mat) <- out.mat[,2]
out.mat <- cbind(rep("&", length(out.mat[,1])), out.mat[,1],
rep(c("\\", "
\\[.1in <file://%5B.1in/>]"), length(out.mat[,1])/2))
colnames(out.mat) <- c("", "", "")
cat("\\begin{table}\n <file://begin%7Btable%7D/n>")
cat("\\caption{}\n <file://caption%7B%7D/n>")
cat("\\begin{center}\n <file://begin%7Bcenter%7D/n>")
cat("\\begin{tabular}{ld{3}}\n
<file://begin%7Btabular%7D%7Bld%7B3%7D%7D/n>
")
cat("\\hline\n <file://hline/n>")
cat(" &
\\multicolumn{1}{r}{Estimate<file://multicolumn%7B1%7D%7Br%7D%7BEstimate/>}
\\\\\n")
cat(" &
\\multicolumn{1}{r}{(S.E<file://multicolumn%7B1%7D%7Br%7D%7B(S.E/>.)}
\\\\\n")
cat("\\hline\\hline\n <file://hline//hline/n>")
print.table(out.mat)
cat("\\hline\n <file://hline/n>")
cat("\\multicolumn{2}{l}{N
<file://multicolumn%7B2%7D%7Bl%7D%7BN/>=")
cat(paste(object$df.residual + object$rank, "}\\\\\n",
sep=""))
cat("\\multicolumn{2}{l}{*p$<$0.05<file://multicolumn%7B2%7D%7Bl%7D%7B*p$%3C$0.05/>,
2-sided}\\\\\n")
if(fit == TRUE){
if(class(object)[1] == "lm"){
cat("\\multicolumn{2}{l}{R$^{2}$<file://multicolumn%7B2%7D%7Bl%7D%7BR$%5E%7B2%7D$/>
=")
cat(paste(round(summary(object)$r.squared, 3), "}\\\\\n",
sep=""))
}
else if(class(object)[1] == "glm"){
cat("\\multicolumn{2}{l}{deviance<file://multicolumn%7B2%7D%7Bl%7D%7Bdeviance/>
=")
cat(paste(round(summary(object)$deviance, 3), "}\\\\\n",
sep=""))
}
}
cat("\\hline\\hline\n <file://hline//hline/n>")
cat("\\end{tabular}\n <file://end%7Btabular%7D/n>")
cat("\\end{center}\n <file://end%7Bcenter%7D/n>")
cat("\\end{table}\n <file://end%7Btable%7D/n>")
}
On 5/3/06, Thomas Davidoff <davidoff@haas.berkeley.edu>
wrote:>
> It would be nice to have something like stata's outreg that lets
> regression
> output go into a form like
> Specification (1) Specification (2)
> Var 1 coef(1,1) coef(1,2)
> se(1,1) se(1,2)
> Var 2 coef(2,1) coef(2,2)
> se(2,1) se(2,2)
>
> I don't think this can be done in xtable?
>
> Thomas Davidoff
> Assistant Professor
> Haas School of Business
> UC Berkeley
> Berkeley, CA 94618
> Phone: (510) 643-1425
> Fax: (510) 643-7357
> email: davidoff@haas.berkeley.edu
> web: http://faculty.haas.berkeley.edu/davidoff/
>
> ______________________________________________
> 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
>
--
Dave Armstrong
University of Maryland
Dept of Government and Politics
3140 Tydings Hall
College Park, MD 20742
Office: 2103L Cole Field House
Phone: 301-405-9735
e-mail: darmstrong@gvpt.umd.edu
web: www.davearmstrong-ps.com
[[alternative HTML version deleted]]