"Explaining Unbiased Expression with Probability

  • Thread starter Thread starter TSN79
  • Start date Start date
  • Tags Tags
    Expression
Join the discussion
Registration is free. Ask a follow-up in this thread, or start your own.
1 reply · 2K views
TSN79
Messages
422
Reaction score
0

Homework Statement



In an example my book says that the expression bellow is unbiased.
I can't see why this is exactly...

Homework Equations



[tex] \begin{array}{l}<br /> \hat p = \frac{X}{n} \\\\<br /> E(\hat p) = E\left( {\frac{X}{n}} \right) = \frac{1}{n} \cdot E(X) = \frac{1}{n} \cdot (n \cdot p) = p \\ <br /> \end{array}[/tex]

The Attempt at a Solution



Could the reason be that the expression comes down to just p, which is simply a probability and we have no better suggestion than to believe that it "hits the target"? (If that didn't make any sense, just ignore it)
 
Physics news on Phys.org
A statistic [itex]\tau(x_1,x_2,...,x_n)[/itex] is said to be unbiased for a parameter [itex]\theta[/itex] if [itex]E[\tau(x_1,x_2,...,x_n)]=\theta[/itex].

It is just a definition.

It is important to know that to say that [itex]\hat{p}=\frac{x}{n}[/itex] is unbiased is WRONG. It is unbiased for a particular PARAMETER.

The expectation of [itex]\hat{p}[/itex] is precisely p. If it so happened that [itex]E[\hat{p}]=p-2[/itex] then [itex]\hat{p}[/itex] would not be an unbiased estimator for p, it would be an unbiased estimator for p-2.
 
Last edited: