What does it mean if the maximum log likelihood (REML) is negative
Hello,
Doing the metaregression, and the Log Likelihood is negative score. Is that because the sample density is small or any other causes? Need advice to interprete the negative log likelihood.
Cheers
Comments
In discrete data models, the log likelihood will always be negative (b/c the data is associated with probabilities). In continuous data models, the log likelihood is about the density, and that may be lower than 1 as well. Likelihood is defined up to a multiplicative constant anyway, so I would not worry about it.
Cheers,
E.J.
Thank you.
Guan