Log Likelihood

[Glenda C]

Dear all,

Could somebody tell me how I can incorporate the log-likelihood in the output of my regressions since I did not find the right command for visualising the log-likelihood.

I've used "estout m*, cells(b(star fmt(%9.3f)) se(par)) stats(r2_a N chi2, fmt(%9.3f %9.0g) labels(R-squared)) legend label collabels(none) varlabels(_cons Constant)".

Thank you in advance.

[Andrew Musau]

After your estimation, type

ereturn list

and the maximized log-likelihood is stored under scalars as

 e(ll)

Therefore, you need to include it as -ll- within the stats brackets, e.g.,

stats(ll r2_a N chi2)

That said, I think there may be a misunderstanding on your part. I do not know any standard Stata estimator that outputs both a log-likelihood and an adjusted R2 (r2_a). The reason is R2 and adjusted R2 are applicable to least squares estimation whereas in cases where the equation to be estimated is non linear and does not generate well-defined residuals which can be minimized, maximum likelihood estimation is employed (and hence you obtain a log-likelihood). So running -regress- will not yield a log-likelihood whereas logit and probit will.

[Glenda C]

Thank you for your feedback and help!

[Phil Bromiley]

By the way, while Andrew answered your question in this case, you'll have a greater chance of a useful answer if you follow the FAQ on asking questions suggests you provide Stata code in code delimiters, Stata output, and sample data using dataex.

Also, we normally use our real names on this list serve.