Sample entropy analysis
I am analysing sample entropy of my mouse-tracking data using lmer. As seen by the residuals of my model, the distribution does not seem to be normal. I tried to log-transform sample entropy but given that I have a lot of zero values, the log-transformation produces 'infinite' values and as a result I get an error when I try to make a model with a log-transformed sample entropy.
Do you know how sample entropy is usually analysed, e.g. is it advisable to transform it or not, or should I use a different function/family?
Any advice would be much appreciated.
Thank you in advance,