Negative binomail distribution and its variance

AI Thread Summary
The discussion focuses on estimating the variance of the negative binomial distribution using maximum likelihood estimation and Fisher's information. The original poster seeks feedback on their solution but expresses difficulty in deriving the variance despite understanding its theoretical basis. A suggestion is made to reformulate the problem in the context of the exponential family to facilitate the estimation process. Additionally, there is a critique of the maximum likelihood estimator (MLE) provided, specifically questioning the calculation of the log-likelihood function. The conversation emphasizes the need for clarity in the derivation process and the importance of accurate calculations in statistical estimation.
_joey
Messages
44
Reaction score
0
Hi,

I am trying to estimate variance for negative Binomial distribution using
maximum likelihood estimation and Expected (Fisher's) information to determine its variance. I know what variance is for this distrubution but I cannot derive it.


Here is my solution. Any comments and suggestions are much appreciated

Thanks!

Solution: http://img825.imageshack.us/img825/7545/ndist.png
 
Last edited by a moderator:
Physics news on Phys.org
I think I know what the problem is. I've been solving problems for many hours and I need a break. :)
 
Have you tried putting it into the form of the exponential family first?

Your MLE = x bar is incorrect. What did you get for your log-likelihood function?
 
I was reading documentation about the soundness and completeness of logic formal systems. Consider the following $$\vdash_S \phi$$ where ##S## is the proof-system making part the formal system and ##\phi## is a wff (well formed formula) of the formal language. Note the blank on left of the turnstile symbol ##\vdash_S##, as far as I can tell it actually represents the empty set. So what does it mean ? I guess it actually means ##\phi## is a theorem of the formal system, i.e. there is a...
Back
Top