Re: Parameter Estimamtion of a Exponential Dist.
From: Timothy Little (tim-via-n.i.net_at_little-possums.net)
Date: 12/18/04
- Next message: William F Hummel: "Re: Question about President's Social Security plan"
- Previous message: John O'Flaherty: "Re: do you have any smart way of finding which number is bigger ?"
- In reply to: carkaci: "Parameter Estimamtion of a Exponential Dist."
- Messages sorted by: [ date ] [ thread ]
Date: 18 Dec 2004 02:34:57 GMT
carkaci wrote:
> However, I plan to use A'=sqrt(Sample Variance). Does any one have
> an idea about the robustness of the estimation ?
Sample variance is a biased estimator of population variance:
<sample variance> = A^2 (n-1) / n. I can prove that A' is a biased
estimator of A, but haven't been able to derive a closed expression
for <A'>/A in terms of n.
Unfortunately, setting A' = sqrt(Sample Variance * n / (n-1)) does not
remove the bias.
- Tim
- Next message: William F Hummel: "Re: Question about President's Social Security plan"
- Previous message: John O'Flaherty: "Re: do you have any smart way of finding which number is bigger ?"
- In reply to: carkaci: "Parameter Estimamtion of a Exponential Dist."
- Messages sorted by: [ date ] [ thread ]
Relevant Pages
|
