Low Pseudo R Square in Panel Data

[Atik Fazalina]

Dear statalister
I ran regress panel data with logistic regression, and i got low pseudo R square,it just 19,15%. I think my model is not good because of the low value of R square.
and then I added the independent variables, the results of pseudo R square increased to 24%.
I want to ask, does logistic regression panel data with a lower pseudo R square is normal? and can I still use my model with the lower pseudo R square like that (24%) ?

Thank you in advance

[Carlo Lazzaro]

Atik:
there's no hard and fast rule.
What can be considered "low" in one research field is widely accepted in another one.
The usual recommedation is to skim the litetrature of your research field and see the average R-sq and the set of predictors that others used when presented with the same research topic.
As a closing-out remark, as reminded by FAQ please post what you typed and what Stata gave you back. Thanks.

[Phil Bromiley]

You might also look at the 2x2 predicted versus actual matrix. That is often more informative - telling you for example whether your difficulties are in false positive or false negatives.
Phil