Hi I am running a test whereby I sequentially add a group of fixed effects indicators (eg client fixed effects indicators) sequentially to the baseline model (consisting of only time variant characteristics) and calculate the incremental adjusted r-square that can be attributed to the addition of the set of fixed effect indicators. I am looking perform Vuong’s (1989) likelihood ratio test to assess whether the incremental r-square is significant
Example
Baseline model/Model 1
y = a + bx where x is time variant client characteristics
Model 2
y= a + bx + i.client
I then measure the incremental r-square between both models. Further I am looking to perform the vuong (1989) LR test to assess whether the incremental R2 is significant.
Please note these are non linear models.
Many thanks
Example
Baseline model/Model 1
y = a + bx where x is time variant client characteristics
Model 2
y= a + bx + i.client
I then measure the incremental r-square between both models. Further I am looking to perform the vuong (1989) LR test to assess whether the incremental R2 is significant.
Please note these are non linear models.
Many thanks
