Suppose Y1,...,YN are independent random variables, each with the Pareto distribution and E(Yi) = (ß0 + ß1xi)2 Is this a generalized linear model? Give reasons for your answer.
Suppose Y1,...,YN are independent random variables, each with the Pareto distribution and
E(Yi) = (ß0 + ß1xi)2
Is this a generalized linear model? Give reasons for your answer.
This is what I know:
I know that the Pareto distribution is part of the exponential family. So, it meets the first criteria for a generalized linear model.
However, I cannot figure out if this question is canonical, natural, or neither. For example, I know some exponential families are not in the exponential dispersion family used in generalized linear models unless a scale parameter is added and interpreted as a dispersion parameter.
This is what I need help with:
Please explain if this question is canonical, natural, or neither and to recognize the difference.
Thanks!
Trending now
This is a popular solution!
Step by step
Solved in 2 steps with 2 images
