Compare Fit of two linear models

6 次查看（过去 30 天）
Femke R
Femke R 2020-11-2
评论： Jeff Miller 2020-11-3
Hi guys,
I have a model that looks like this (DV ~ IV1 + IV2)
I also have a nested model where I constrained the coefficients of IV1 and IV2 to be equal. Is there a function I can use to compare the model fit of these two models?
(so I can see if the fit get significantly worse or not in the nested model).
In R I would use CompareFit from the lavaan package, is there something similar for Matlab?
Thanks in advance.

请先登录，再回答此问题。

采纳的回答

Jeff Miller
Jeff Miller 2020-11-2
A quick and dirty solution is to form a new variable
S=IV1+IV2;
and then compare the fit of the model 'DV~S' to the model 'DV~S+IV2'. If the second model fits significantly better, then you know the constrained model with equal slopes is significantly worse.
  2 个评论
Femke R
Femke R 2020-11-3
I've found how to constrain them, I just need to know if there's a way to compare model fit (with significance). To see if the drop in fit is actually significant.
Jeff Miller
Jeff Miller 2020-11-3
X = [S,IV2];
mdl = fitlm(X,DV)
Under the mdl.Coefficients output, you will see a pValue for X2. If this is less than .05 (or whatever your alpha is), then the drop is statistically significant.

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Gaussian Process Regression 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by