st: Re: interrupted time series

["Ariel Linden, DrPH" <ariel.linden@gmail.com>]

Hi Giuseppina,

The models that were suggested to you by others on the list are generally
for ARIMA type models that require a significant number of preintervention
observations (generally over 50) and are not that user friendly (they
require some skill and are a bit too subjective in their estimation).

Interrupted regression using OLS or AR1 models are very easy to implement in
Stata, and they can be enhanced using ARIMA processes as well. There are
some good papers on this topic, and I have an older paper on the topic
(2003) and a current one in press (you can give me a shout off line for a
copy)

Simonton DK. Cross sectional time-series experiments: some suggested
statistical analyses. Psychological Bulletin 1977;84(3):489-502.
Wagner AK, Soumerai SB, Zhang F, Ross-Degnan D. Segmented regression
analysis of interrupted time series studies in medication use research. J
Clinical Pharmacy and Therapeutics 2002;27:299-309. 
Linden A, Adams J, Roberts N. Evaluating disease management program
effectiveness: An introduction to time series analysis. Disease Management.
2003;6(4):243-255.
Linden A, Adams JL. Applying a propensity-score based weighting model to
interrupted time series data: improving causal inference in program
evaluation. Journal of Evaluation in Clinical Practice. In Press   

I hope this helps

Ariel


Date: Tue, 31 Aug 2010 17:16:34 -0400
From: "Giuseppina Chiri" <gchiri@brandeis.edu>
Subject: st: interrupted time series

Dear list members,
I am looking for guidance on how to do interrupted time series analysis
using Stata. I have looked on the web and in the list archives using
keywords like 'interrupted time series, stata' and 'segmented regression,
stata' to no avail. 
I would greatly appreciate any suggestions you can provide.
Giusi
 

__________________________________________
Giuseppina Chiri, Doctoral Student
Lurie Fellow in Disability Policy
The Heller School for Social Policy and Management
Brandeis University

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/