You are not logged in. You can browse but not post. Login or Register by clicking 'Login or Register' at the top-right of this page. For more information on Statalist, see the FAQ.
The term joinpoint regression can mean two different things, and it isn't clear which you mean.
1. A pre-specified joinpoint exists and you want to fit a model that takes that into account. Any Stata regression command applied to variables constructed with the -mkspline- command accomplishes this.
2. You wish to fit a model that is piecewise linear with a joinpoint, but the location of the joinpoint is not known a priori and is to be estimated from the data. There is a user written command -nlhockey- that does this. (And the same author has a command -loghockey- that estimates logistic models with an unknown joinpoint.) -search nlhockey- will get you a link to download these programs.
The term joinpoint regression can mean two different things, and it isn't clear which you mean.
1. A pre-specified joinpoint exists and you want to fit a model that takes that into account. Any Stata regression command applied to variables constructed with the -mkspline- command accomplishes this.
2. You wish to fit a model that is piecewise linear with a joinpoint, but the location of the joinpoint is not known a priori and is to be estimated from the data. There is a user written command -nlhockey- that does this. (And the same author has a command -loghockey- that estimates logistic models with an unknown joinpoint.) -search nlhockey- will get you a link to download these programs.
Thank you so much, Clyde. You are always helpful.
The second description is what I am looking for: to fit a model with unknown "joinpoints". I will look into the -nlhockey- and will followup with you if I have additional questions.
Comment