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

st: Re: Nonparametric two way ANOVA


From   Roger Newson <roger.newson@kcl.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: Nonparametric two way ANOVA
Date   Thu, 05 Feb 2004 16:56:46 +0000

At 11:28 05/02/04 -0500, Joseph Wagner wrote:

I want to do what I know is a pretty simple calculation but I am constrained
by my dependent variable which is non-normal.

I wish to see if there are differences in viral load stratified by age
category and by race.  Viral load is not normal and in my case, I cannot
transform this variable to approximate normal.

I know I could do kruskal wallis or trend tests by race and by age category
individually but I need to do both.

If viral load were normal, I could do:

anova vload agecat race

The Friedman test is the only thing that comes to mind but I don't think
this is what I want.
In my experience, viral loads are lognormally distributed. I would therefore log-transform the viral loads and use linear regression methods on the logs to estimate geometric means and their ratios, using the -eform()- option of -regress-. For instance:

gene logvload=log(vload)
gene byte baseline=1
xi:regress vload i.agecat i.race baseline, noconst robust eform(GM/Ratio)

The parameter -baseline- will then be a baseline geometric mean viral load, representing geometric mean viral load for individuals with the reference age category and race category. The other parameters will be ratios of geometric mean viral load in other race and age categories, compared to the baseline category. The effect of race and age are assumed to be multiplicative.

We need to generate the variable -baseline- and use the -noconst- option of -regress-, because, if we use the -sform- option without the -noconst- option, then Stata does not print the intercept, which in this case is the baseline geometric mean. Using the variable -baseline- with the -noconst- option, we can fool Stata into thinking there is no intercept for it to hide.

I hope this helps.

Roger


--
Roger Newson
Lecturer in Medical Statistics
Department of Public Health Sciences
King's College London
5th Floor, Capital House
42 Weston Street
London SE1 3QD
United Kingdom

Tel: 020 7848 6648 International +44 20 7848 6648
Fax: 020 7848 6620 International +44 20 7848 6620
or 020 7848 6605 International +44 20 7848 6605
Email: roger.newson@kcl.ac.uk
Website: http://www.kcl-phs.org.uk/rogernewson

Opinions expressed are those of the author, not the institution.

*
* 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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index