Regstats model equation
6 views (last 30 days)
Show older comments
The function regstats returns beta coefficients for a model of responses y from predictors x. For a quadratic model with one predictor, the model is simple:
b(1)*constant + b(2)*x + b(3)*x^2
(in that order, where b = stats.beta). However, as the number of predictors increases, it's not clear what order the beta coefficients are applied to the model. The model I'm interested in, for example, is quadratic with 3 predictor vectors, generating 10 beta coefficients. I can guess at what the model expansion would be, but is there any documentation on this (I couldn't find any)? Many thanks in advance!
0 Comments
Accepted Answer
Wayne King
on 12 Oct 2011
Hi Dave, you can use x2fx() to figure out what order your terms appear in.
More Answers (0)
See Also
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!