Tobit Regression: Pseudo R2

[Mohd Fahad]

Dear Members,

Greetings!

I ran a tobit regression but got the Pseudo R2 = 7.2702 for 10644 observations. F( 67, 10577) = 325.95 and Log pseudolikelihood = 5726.2154.

I read that Pseudo R2 values can be greater than 1 or less than 1. https://www.stata.com/support/faqs/s...ics/pseudo-r2/

However since my values are greater than 7 , hence wanted to just check if the regression is ok? The output is below:


Tobit regression Number of obs = 10,644
F( 67, 10577) = 325.95
Prob > F = 0.0000
Log pseudolikelihood = 5726.2154 Pseudo R2 = 7.2702

(Std. Err. adjusted for 5,705 clusters in acqnamecluster)



Kindly share your thoughts.

Warm Regards
Fahad

[Phil Bromiley]

You'll increase your changes of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex.

This seems like an extreme value, but I don't really know what values are normal. In addition to a Tobit, I'd double check the results with regression and Poisson regression just to make sure something weird is not going on.