Say that my data consists of

time success failure exog
2009 3 1002 0.2
2010 2 1200 0.3
2011 9 1091 0.1
2012 0 1099 0.4

And I want to fit a GLM with a Binomial family and Logit link to this grouped timeseries data.

E.g. The function would be "success + failure ~ exog + intercept".

When using this data to fit a model in Python using the GLM from statsmodels.api library, it seem to work. However, my last data point is 0 success, which means when computing the proportion success / (success + failure), it becomes 0.

How can the logit transformation be calculated when this ratio is 0? Maybe I am missing something regarding MLE...



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.