ctest wishlist

[Kurt Hornik]

In the past months (maybe even years), I have received a variety of
suggestions on improving/extending/... my ctest package.  Some of the
wishes have already been fulfilled.  In the future, I will at least:

* provide a formula-based interface

* provide an option for controlling the behavior of 2-sided p-values
(sum of more extreme, tail balancing a la S-PLUS, double one-sided, mid
p-value, more?)

* add something for analyzing odds ratios

* add something like an `info' slot to `htest' objects for displaying
useful additional information.  E.g., info on possible heterogeneity of
strata when analyzing 2 by 2 by k tables, etc.

The question is, which other features would you like to see in ctest?
Any additional tests?  What about exact inference methods?

Feedback will be appreciated.

-k
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel 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-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._