Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: pkequiv and p-values from one-sided t-tests


From   Nigel Perkins <nigel@ausvet.com.au>
To   statalist@hsphsun2.harvard.edu
Subject   st: pkequiv and p-values from one-sided t-tests
Date   Mon, 25 Feb 2013 16:28:11 +1000

I am using pkequiv in Stata 12.1 to analyse data for bioequivalence

. pkequiv value treat period sequence id, tost

      Classic confidence interval for bioequivalence
      ----------------------------------------------------------------------
                         [equivalence limits]        [    test limits   ]
      ----------------------------------------------------------------------
           difference:   -86.775       86.775       -150.067      185.817
                ratio:       80%         120%         65.412%     142.827%
      ----------------------------------------------------------------------
      probability test limits are within equivalence limits =    0.0160
      Schuirmann's two one-sided tests
      ----------------------------------------------------------------------
      upper test statistic =    -0.797                   p-value =     0.456
      lower test statistic =     1.211                   p-value =     0.271
Everything makes sense to me except the reported p-values for the
Schuirmann's tests.

The DF for this dataset is equal to 6 based on a 2-period cross-over study
with n=4 in each sequence.

The reported p-values appear to be two-sided p-values and not one-sided
p-values. I can estimate one-sided p-values using Excel or a web-calculator
and they are numerically equal to half the p-values reported by pkequiv. I
expected the Schuirmann tests to each report a one-sided p-value.

I have repeated this analysis using a couple of different datasets and the
results appear to be consistent.

I am wondering if I am doing something wrong here. Any comment would be much
appreciated.

Nigel Perkins
AusVet, Australia
nigel@ausvet.com.au
*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index