Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Model fit with regress cluster option

From   "Collewaert V (MCFE)" <>
To   "" <>
Subject   st: Model fit with regress cluster option
Date   Wed, 12 May 2010 13:55:37 +0200

Dear all,

I ran two models, one being a control model, the second one additionally including my predictors of interest. In both cases I used the regress command with cluster option, in order to cluster for companies (I have multiple investment rounds per company so I clustered for company).

My question is: am I correct to believe that the respective degrees of freedom needed to determine the significance of the F change statistic (to compare both models) is 

- the number of additional regressors in the second model and 
- the number of clusters minus 1 (in my case 47)? (which hence is the same for both new and old model)

With kind regards,


*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index