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

st: Explained variation / variance partitioning using xtmixed

From   "Patrick P. Phillips" <>
To   "" <>
Subject   st: Explained variation / variance partitioning using xtmixed
Date   Fri, 16 May 2008 11:54:36 +0100

Dear StataList,

        Referring to the paper by Xu in Statistics in Medicine 2003, "Measuring explained variation in linear mixed models" (22:3527-3541), has this measure of explained variation been implemented in Stata as a postestimation command to xtmixed or anywhere else?

        From xtmixed, Stata gives the residual variance (sigma^2), that is the variance in the response variable conditional on all the fixed and random effects. How do I calculate, or convince Stata to produce, the variance in the response conditional only on the clustering (sigma_0^2)?

        Xu's formula for Omega^2 as a measure of the explained variation is the ratio of the variance of the response conditional on all fixed and random effects (sigma^2) and the variance of the response conditional on the clustering only (sigma_0^2) subtracted from 1. It is the proportion of the variance conditional on the clustering that is explained by the covariates. That is:

                Omega^2 = 1 - (sigma^2 / sigma_0^2)

This seems to be simple partitioning of the variance that I believe SAS gives you automatically, but I'm not sure how to get this from Stata.

Can anyone help me here?

Many thanks in advance,


Patrick Phillips
MRC Clinical Trials Unit
222 Euston Road
London NW1 2DA

Tel: 0207 670 4637
Fax: 0207 670 4829


This communication is confidential and may contain privileged information intended solely for the named recipient(s). It may not be used or disclosed except for the purpose for which it has been sent. If you are not the intended recipient, you must not copy, distribute, take any action or reliance on it. If you have received this communication in error, do not open any attachments but please notify the MRC Euston Campus ICT Service Desk by e-mailing quoting the sender details, and then delete this message along with any attached files. E-mail messages are not secure and attachments could contain software viruses which may damage your computer system. Whilst every reasonable precaution has been taken to minimise this risk, The MRC cannot accept any liability for any damage sustained as a result of these factors. You are advised to carry out your own virus checks before opening any attachments. Unless expressly stated, opinions in this message are those of the!
  e-mail author and not of the Medical Research Council (MRC).


*   For searches and help try:

© Copyright 1996–2022 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index