On Tue, 12 Feb 2002, Jeff D. Hamann wrote:
> I've trying to check for model bias. It was recommended to me that I
should
> break the residuals into n groups and test to see if the mean is different
> from zero. What is the best way to generate the groups. I've generated
a
> matrix that contains the residuals and groups, but the values all have
> quotes around them.
>
> 1) how do I get rid of the quotes?
> 2) is this an acceptable method for testing for model bias?
>
> # this is the test code...
> signif <- symnum(fit3sls[[2]]$residuals,
> corr = FALSE,
> na = FALSE,
> cutpoints = c(-5,.1,.2,.3,.4, 5),
> symbols =
c("A","B","C","D","E"))
>
> table <- cbind( fit3sls[[2]]$residuals, signif )
> colnames(table) <- c("resid","group")
>
> # prints fine
> print.matrix(table, quote = FALSE, right = TRUE )
>
> # resid_table <- matrix(table,quote=FALSE )
> # just to look at the data
> #boxplot( resid ~ group, data = resid_table )
1) standard names in R don't have `_' in
2) signif is, I presume, character or factor. You want a data frame, not a
matrix, and that's what boxplot.formula expects. cbind creates a character
matrix. So use, say,
table <- data.frame( resid = fit3sls[[2]]$residuals, signif )
3) Avoid the names of R objects like resid and signif will help not to
confuse your readers, yourself and perhaps R.
--
Brian D. Ripley, ripley at stats.ox.ac.uk
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272860 (secr)
Oxford OX1 3TG, UK Fax: +44 1865 272595
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at
stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._