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

st: Nomenclature when using random (mixed) effects modeling


From   "James W. Shaw" <shaw@pharmacy.arizona.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: Nomenclature when using random (mixed) effects modeling
Date   Sat, 26 Oct 2002 09:03:56 -0700

I have a question regarding nomenclature. In most of my reading, random effects models are used with cross-sectional time series. In such cases, "i" is used to refer to a grouping variable (e.g., subject, firm), while "t" is used to designate time. However, I have seen a few papers in which "t" clearly does not refer to time. For example, a number of studies have used random effects modeling to estimate the health state value system for the EQ-5D (a self-reported quality of life index). In these studies, each respondent was asked to rate (on a scale ranging from -1 to 1) a random selection of 12 of the 243 health states described by the EQ-5D. Thus, "i" referred to respondent (the random effect), while "t" referred to health state. My question is as follows: what would one call this type of analysis? Hierarchical analysis? Multi-level modeling? I presume that the terms "panel data" and "cross-sectional time series" would be inappropriate.

As always, any help is greatly appreciated.

Best Regards,

James Shaw
*
* 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