Dear all,
I am working with a highly skewed dependent variable. I would like to estimate the effects of a series of independent variables on both the mean and the dispersion of my DV. That is, I would like to know to what extent my independent variables can predict not only the mean value of my DV, but also its degree of dispersion.
My problem is that I don't know how to specify that in the glm model that I am employing. By default, I obtain results over the mean value of my DV, but not on its dispersion. My code basically follows this form:
The nbreg command does not seem to have this option neither.
Any help or idea would be highly appreciated. Thanks in advance.
I am working with a highly skewed dependent variable. I would like to estimate the effects of a series of independent variables on both the mean and the dispersion of my DV. That is, I would like to know to what extent my independent variables can predict not only the mean value of my DV, but also its degree of dispersion.
My problem is that I don't know how to specify that in the glm model that I am employing. By default, I obtain results over the mean value of my DV, but not on its dispersion. My code basically follows this form:
Code:
glm dv cov1 cov2 cov3, fam(nb ml)
Any help or idea would be highly appreciated. Thanks in advance.