Given the Poisson BKMR has not been added, can I use gaussian in the family option of kmbayes when the outcome is count data, like episodes of getting a fever?
If the mean is large, then the Poisson distribution can be approximated by a normal distribution. So if you're counts aren't small, then the normal approximation is probably OK.
Given the Poisson BKMR has not been added, can I use gaussian in the family option of kmbayes when the outcome is count data, like episodes of getting a fever?