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, is already up and running.

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

st: Re: re: st baseline adjustment in linear mixed models

From   Clyde B Schechter <>
To   "" <>
Subject   st: Re: re: st baseline adjustment in linear mixed models
Date   Wed, 13 Feb 2013 04:46:28 +0000

In response to my response to his original inquiry about including as a covariate the baseline value of a series of repeated measures Giulio Formoso asks:

"...If I compare intervention and control areas, their baseline values look much closer than their post-intervention values (curves clearly divaricate when the intervention starts). I don't know if, under these circumstances, baseline (pre-intervention) values  could be considered as distinctively influential as you say (if you have time, I'd like your opinion on this point). ..."

To me this does not sound like evidence of distinctive influence of the baseline value.  In the absence of any such influence, I would expect to see precisely what you describe: the baseline values in the two groups should be close together, and they should diverge clearly in the post-intervention period (assuming the intervention has an effect).

My original remark about distinctive extra influence of the baseline value was really meant on the level of the science, rather than the data.  But, you could look for evidence of this in the data by doing a matrix of scatter plots of all pairs of the series of values--do this separately for intervention and control groups.  If the scatter plots involving the baseline value on either axis systematically appear to exhibit a stronger correlation than the scatter plots involving only values from post-intervention time periods, that would suggest a distinctive, lasting influence of the baseline value.  It's a relatively coarse way of looking at it, but I think it will capture the essence of the matter.

Clyde Schechter
Department of Family & Social Medicine
Albert Einstein College of Medicine
Bronx, NY, USA

*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index