Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Re: error in -vanelteren- (1 group found, 2 required)
From
"Joseph Coveney" <[email protected]>
To
<[email protected]>
Subject
Re: st: Re: error in -vanelteren- (1 group found, 2 required)
Date
Tue, 21 Jan 2014 10:34:36 +0900
Ariel Linden wrote:
Thanks to both Red Owl and Joseph Coveney for the response!
That error message is easy to misunderstand. I assumed (wrongly) that the
error was referencing the binary variable used in by(), not in missing
levels of the strata...
Joseph, FYI, I emailed you at [email protected] on 12/29/13 and then
again at [email protected] on 1/1/14. I did not receive a notification of a
bounce either time...
--------------------------------------------------------------------------------
Sorry about the misunderstood error message. I suppose that it's like the
"no observations" error message that you can get from some official Stata
commands that seems curious at first.
Regardless, I recommend using the -emh- command in lieu of -vanelteren- for
performing van Elteren's test. I've posted at least a couple of times on this
list how to do it, but if you need a handy permanent reference as to how, you
can take a look at the FAQ on the same topic by SAS for its PROC FREQ at
http://support.sas.com/kb/25/022.html . You'd use the analogous options with
-emh-, that is,
PROC FREQ;
TABLES STRATA * TREATMENT * RESPONSE / CMH2 SCORES=MODRIDIT NOPRINT;
RUN;
becomes
emh response treatment, strata(strata) anova transformation(modridit)
You can download and install -emh- from the same source as you got -vanelteren-.
-emh- can do everything that the older -vanelteren- can, and much more besides.
Checked again, and no hits. I can see how the bigplanet account might not have
had anything--it has a "Postini" spam filter on the mail server that can get
pretty aggressive. But I can't explain why the gmail account doesn't have
anything from you on the fourteenth except your Statalist post on subscripting.
Joseph Coveney
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/