Take the 2-minute tour ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.

I need to show that $\hat\lambda = \bar X$ is a sufficient estimator for a Poisson distribution iid $X_1...X_n$, show that $\hat\lambda$ is the UMVUE for $\lambda$ and that $\hat\lambda$ is a consistent estimator.

I don't even know how to tackle the sufficiency part. I've looked over the definition and I don't understand at all.

For the UMVUE I already have that var($\hat\lambda$)=CRLB, but I can figure out how to evaluate E($\hat\lambda$) at all.

I have a terrible head cold, so these may be stupid questions but any help is appreciated!!

share|improve this question
1  
Probably you meant, sufficient statistics? To show it, you can use factorization theorem. That is, try to write the PMF as $g_{\lambda}(\bar{X}) h(X)$ where $h$ does not depend on $\lambda$. –  passerby51 Feb 15 '13 at 18:34

1 Answer 1

up vote 2 down vote accepted

I don't even know how to tackle the sufficiency part.

http://en.wikipedia.org/wiki/Sufficient_statistic#Fisher.E2.80.93Neyman_factorization_theorem

recognize that

$$\prod \lambda^{x_i} = \lambda^{\sum x_i}$$

After which it's trivial

I can figure out how to evaluate $\operatorname{E}(\hat{\lambda})$ at all

Write $\bar{X}$ as a constant times a sum. What's the distribution of that sum?

Can you find the expectation of that?

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.