Zero-inflated gaussian distribution model

Question

I am trying to create a generalised linear model with random effect. I have a small dataset, with longitudinal data of 4 subjects. The data I obtain from them is a frequency data, and for one of the subjects all of the data points are 0. So when checking the normality and the residual plots the distribution is not normal.

Graph:

I tried transforming the data in different ways but the plot remains to look the same.

Is there any model or transformation I can use for this type of data, where one of the subjects shows no variability?

m=lme(Freq ~ Time, random=~ 1|Subject,  data=my_data, method='ML')

Answer 1

You have frequency data, with a small mean. You can't expect the residuals to look very normal. I am not sure why you are assuming a Gaussian model - you could try fitting using a Poisson family in a call to glmer() (package lme4).

If you really have zero inflated Poisson data, as TTNK says, you will need many more than 4 subjects.