Statalist The Stata Listserver

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

st: Re: Testing for difference between two medians

From   "Michael Blasnik" <>
To   <>
Subject   st: Re: Testing for difference between two medians
Date   Sat, 15 Jul 2006 11:46:49 -0400

Please try the built-in help system before posting basic questions:

search median test, all

yields many hits. -somersd- and -cendif- may be of particular interest

Michael Blasnik

----- Original Message ----- "Ashwin Ananthakrishnan" <> wrote


I have the outcome variable in a research project as
the waiting time, which is a continuos variable.
However it is a skewed distribution and therefore I
would like to use the medians instead of means. If I
want to compare the median waiting time between
different subgroups, for example male vs. female, or
low income vs. medium income vs. high income, how do I
go about doing that?
To my understanding the t-test or anova looks only for
differences in the means. In case of a skewed
distribution, is it appropriate to use them for this

*   For searches and help try:

© Copyright 1996–2021 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index