Unbiased estimator

  1. Hi, I'm working on the following problem and I need some clarification:
    Suppose that a sample is drawn from a [tex]N(\mu,\sigma^2)[/tex] distribution. Recall that [tex]\frac{(n-1)S^2}{\sigma^2}[/tex] has a [tex]\chi^2[/tex] distribution. Use theorem 3.3.1 to determine an unbiased estimator of [tex]\sigma[/tex]
    Thoerem 3.3.1 states:
    Let X have a [tex]\chi^2(r)[/tex] distribution. If [tex] k>-\frac{r}{2}[/tex] then [tex]E(X^k)[/tex] exists and is given by:
    [tex] E(X^k)=\frac{2^k(\Gamma(\frac{r}{2}+k))}{\Gamma(\frac{r}{2})}[/tex]
    My understanding is this:
    The unbiased estimator equals exactly what it's estimating, so [tex]E(\frac{(n-1)S^2}{\sigma^2})[/tex]is supposed to be[tex]\sigma^2[/tex] which is 2(n-1).
    Am I going the right way here?
    Last edited: Jan 30, 2006
  2. jcsd
  3. Ok, So after hours of staring at this thing, here's what I did:
    I let k=1/2 and r=n-1, so the thing looks like this:
    so I use the property of the gamma function that says:
    which leads to:
    So now do i just flip over everything on the RHS,leaving [tex]\sigma[/tex] by itself and that's the unbiased estimator, i.e.
    Any input will be appreciated.
    Last edited: Jan 31, 2006
  4. OK
    Anyone who looked and ran away, here at last is the solution: (finally)
    [tex]E=\sigma\sqrt{\frac{2}{n-1}} \frac{\Gamma\frac({n}{2})}{\Gamma\frac({n-1}{2})}[/tex]
    is indeed correct, however my attempt to reduce the RHS with the properties of the Gamma function is wrong.
    The unbiased estimator is obtained by isolating the [tex]\sigma[/tex] on the RHS and then using properties of the Expectation to get:
    So at last it has been resolved. WWWWEEEEEEEEEEEeeeeeeee
    Last edited: Jan 31, 2006
Know someone interested in this topic? Share this thead via email, Google+, Twitter, or Facebook

Have something to add?