- This topic has 3 replies, 3 voices, and was last updated 6 years, 4 months ago by
.
-
Posts
-
I am working on a paper that has three outcome variables: BMI, risky sexual behaviour, and access to healthcare. BMI is categorised into thin, normal and obese. Risky sexual behaviour is categorised into no risk, low risk, and high risk. Access to health care has three categories, low, moderate and high. The categories are ordered, so, I deceided to use ordered logistic regression instead of multinomial regression. With ologit, I need to test if proprotionality assumption holds. I need help on how to download and use brant test.
Thanks.
I am using Demographic and Health Survey (DHS) dataset. The sample for the survey was selected using a stratified two-stage cluster design.
In Stata you can install the Brant Test by giving this command
net install spost9_ado, from(http://www.indiana.edu/~jslsoc/stata)
The command for running Brant Test in stata is “brant, detail”. A significant test statistic provides evidence that the parallel regression assumption has been violated. For more details look at http://www.ats.ucla.edu/stat/stata/dae/ologit.htm
You find details about the Brant Test in R in these links: http://stats.stackexchange.com/questions/25988/proportional-odds-assumption-in-ordinal-logistic-regression-in-r-with-the-packag?rq=1 , http://www.ats.ucla.edu/stat/r/dae/ologit.htm
- You must be logged in to reply to this topic.
