Hello,
I'm running meglm models because it involves two levels (team and individual) and the dependent variable follows a gamma distribution.
However, STATA says it "cannot compute an improvement -- discontinuous region encountered."
I tried to remove one variable at a time to see what causes the problem and found that the team size variable, which is theoretically and empirically important, may be the source.
It shows results when I run the exactly the same models with Bayesian inference, but not with frequentist stats.
How can I fix this to see the result? Please advise.
Related Posts with Mixed effects generalized linear modeling (meglm) cannot compute an improvement -- discontinuous region encountered
using graph hbar with Panel DataHey! I have Panel Data on Commodity (Variable) prices across 36 Cities (Variable) from Jan to April …
Keeping variables with different cases in each groupDear Statalist users, I would like to ask this data management questions. For example I have indivi…
Stata output InterpretationKindly assist with the discussion and interpretation of Tables 2-4 and Figure 1 in the attached docu…
how to incorporate both fixed effects and robust std errors into panel analysisI am doing an event study where i use a panel analysis (different observations on a same day) with d…
Difference -in-difference research designHi all, I have a panel data (firm and year). I create Post indicator for states that adopt certain …
Subscribe to:
Post Comments (Atom)
0 Response to Mixed effects generalized linear modeling (meglm) cannot compute an improvement -- discontinuous region encountered
Post a Comment