Can Probit or Logit Models Be Used on Panel Data with 50 Subjects?

  • Context: Graduate 
  • Thread starter Thread starter monsmatglad
  • Start date Start date
  • Tags Tags
    Data Probability
Join the discussion
Registration is free. Ask a follow-up in this thread, or start your own.
Sign up Log in
3 replies · 1K views
monsmatglad
Messages
75
Reaction score
0
Is it possible to use probit or logit models on panel data?

Mons
 
Physics news on Phys.org
monsmatglad said:
Is it possible to use probit or logit models on panel data?

Mons
Yes, but depending on the number of people there may not be enough data to do any meaningful statistics. Also, depending on the selection criteria the panel may constitute a very biased sample
 
I have about 50 different "individuals" and (optimally) 20 observations for each. the "individuals" are chosen based on a list of the 50 largest US, public companies at the time of the first observation. Do you see any immediate reasons for concern, based on this information (if I am using this data material for a logit or probit model)?

Mons
 
50 subjects should be enough for reasonable statistics. Your sample is highly biased towards large companies, so your conclusions should not be generalized to smaller companies.
 
  • Like
Likes   Reactions: ZeGato