Max LL and Average LL - Githubissues

Labo-Lacourse / stepmix

A Python package following the scikit-learn API for model-based clustering and generalized mixture modeling (latent class/profile analysis) of continuous and categorical data. StepMix handles missing values through Full Information Maximum Likelihood (FIML) and provides multiple stepwise Expectation-Maximization (EM) estimation methods.

https://stepmix.readthedocs.io/en/latest/index.html

MIT License

54 stars 4 forks source link

Max LL and Average LL #55

Closed mohrezazali closed 6 months ago

mohrezazali commented 6 months ago

Hello. Something just grabbed my attention. My model's log_likeligood in each and every iteration was around 70,000 but at the end the average LL was only 3.9676. Can anybody explain how the Average was calculated?

sachaMorin commented 6 months ago

Average LL = LL/(number of observations)

3.96 is your average LL and around 70,000 is your LL. Are you getting different numbers in the progress bar?

sachaMorin commented 6 months ago

@mohrezazali did this answer your question?

sachaMorin commented 6 months ago

Closing. Feel free to reopen if needed!