Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Hardy-Weinberg with genhw


From   Tom Trikalinos <[email protected]>
To   [email protected]
Subject   Re: st: Hardy-Weinberg with genhw
Date   Thu, 2 Dec 2004 10:17:02 +0200

At least for the asymptotic test, and the "Understand Why" part of your e-mail:
For a biallelic marker (AA;Aa;aa), when -say- the A allele frequency is 0
the expected numbers of the AA and Aa genotypes are 0.
The asymptotic test for HWE uses a \chi^2 distributed statistic that is derived using quantities like:
(observed_AA - expected_AA)^2 / expected_AA
which cannot be defined when expectedd_AA is 0.

I wouldn't use continuity corrections. I don't suppose you can do much.
Perhaps someone else can propose some literature on the subject or a workaround.

tom

On Dec 1, 2004, at 11:05 AM, Paolo Grillo, MD wrote:


I have to perform Hardy-Weinberg equlibrium test with your stata program "genhw" a lot of gene polimorphism.
So, I wrote a Stata do.file with the loop "foreach". Unfortunately the program stopped when an allele frequencies is equal to = 0.
I have decided to write both to understand why and how to try to work out this problem.
Best regards
Paolo Grillo

--



* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
Paolo Grillo MD
Nephrologist Statisticians
EPOCA Research Center for Occupational, Clinical & Environmental Epidemiology
Department of Occupational and Environmental Health "Clinica L. Devoto"
University of Milan
Via San Barnaba 8
20122 Milano - ITALY
Tel: +39 02 503-20148
Fax: +39 02 503-20126
E-Mail [email protected]



*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index