[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: implementation of boschloo's test: very slow execution

From   "Joseph Coveney" <>
To   "Statalist" <>
Subject   Re: implementation of boschloo's test: very slow execution
Date   Mon, 3 Mar 2008 22:09:14 +0900

Eva Poen wrote (excerpted):

I will recalculate all p-values using your program and play around
with this default, to see what difference it makes in various
situations. If I can find a reliable pattern, I will report back.

. . . I will make an
immediate version of your command as soon as I have a little bit of


I've been asked to work it up for SSC, so will try to get it ready by the
time Kit gets back, absent an objection.  I'll probably loop through a few
hundred examples of various table configurations during the certification
script preparation; there should be something coming out of that for
refining search repeats and bounds, but if you run across anything striking
meanwhile, I would appreciate hearing from you.

It dawned on me that we're talking about two-by-two tables and not r-by-c
tables with ragged null spaces, so unless I've got my wires crossed (a
not-unheard-of phenomenon) the short cut around exhaustive Fisher-Irwin
testing should should be reasonably straightforward.  That should make it
into the uploaded version, too.

Joseph Coveney

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index