Statalist The Stata Listserver

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

Re: st: Contextual analysis

From   "Anders Alexandersson" <>
Subject   Re: st: Contextual analysis
Date   Thu, 8 Jun 2006 16:23:41 -0400

Fernando Proietti <> wrote, I summarize:

I have a dataset, from a health survey we conducted. There are about
20,000 participants. Participants are nested in what could be called in
the US as census tracts.

Right now, I am planning a Contextual analysis (the dependent variable =
Self-rated Health, 3 levels) and the explanatory variables measured at
two levels:

Individual level: for example, age, sex, personal income, formal

Aggregated level (Census tracts characteristics where participants are
nested): for example, Average Income, Average Age, % of roads that have

How could I conduct analysis of this type in Stata ?

I am worried with what some authors report as " the residual correlation
between outcomes within groups that may persist after accounting for
individual-level and group-level variables included in the analysis"
I would consider gllamm. See and the reference:

Rabe-Hesketh, S. and Skrondal, A. (2006). Multilevel modeling of
complex survey data. Journal of the Royal Statistical Society, Series
A. In press.

--Anders Alexandersson
*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index