Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Chao-Yu Sung" <chaoyusung@gmail.com> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | st: subgroup analysis in the DCE model |
Date | Mon, 27 Aug 2012 16:17:52 +0800 |
Dear all, I am currently implementing discrete choice experiment (DCE) to elicit participants¡¦ preference. I coded dependent variable 1 represent participants¡¦ decision, the others coded 0. There are columns for choice (30 alternatives per respondent), choiceID (10 sets per respondent), alternative (1 & 2 for the product alternatives, and 3 for the no-choice option). I used the conditional l logistic model (clogit)to analyze the relative importance of DCE attributes and also want to investigate heterogeneity in preferences between subgroups of participants. In other words, I¡¦d be like to investigate the preference between groups A and B. Previous study advised ¡§included interaction terms in the model¡¨ can analyze the preference of subgroups. Unfortunately, I have created effect coding (1 represent groups A) ,but I didn¡¦t succeed. I am confused to conduct the ¡§interaction terms¡¨ in the DCE model. Any help or advice would be greatly appreciated! Kind regards, Rebecca * * 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/