Skip to main content

You are not logged in. Your edit will be placed in a queue until it is peer reviewed.

We welcome edits that make the post easier to understand and more valuable for readers. Because community members review edits, please try to make the post substantially better than how you found it, for example, by fixing grammar or adding additional resources and hyperlinks.

Required fields*

4
  • $\begingroup$ thanks so far! This is good help... But: How can I interpret high or (low) values of theta? In McCaullaughs book generalized linear models there is a link to this paper from anscombe to make an interpretation of k. But unfortunately I don't really get it. The paper is claremontmckenna.edu/facultysites/math/FacMember/MOneill/… $\endgroup$ Commented May 6, 2011 at 21:20
  • $\begingroup$ You just have to read the first page. So theta (or k in anscombe) is the shape parameter of the negbin distribution and it manages, if the distribution is closer to gamma (k -> 0) or poisson (k -> infinity). But what does it mean to the fit? How can I interpret theta for example for the cars estimation? $\endgroup$ Commented May 6, 2011 at 21:28
  • $\begingroup$ What is the range of theta? Does theta have to be a value greater than one? $\endgroup$ Commented Dec 20, 2021 at 7:37
  • $\begingroup$ The only restriction is Theta > 0, and the value of 1 does not correspond to any case of special interest. The negative binomial distribution is always overdispersed compared to the Poisson, with smaller values of theta corresponding to more overdispersion [in this specific parametrization] $\endgroup$ Commented Jan 31, 2022 at 19:51