1
$\begingroup$

Casella& Berger Theorem 6.2.28: If a minimal sufficient statistics exists, any complete statistics is minimal sufficient.

So let's suppose $X_1...X_n$ are iid $Bernoulli(p)$ $p\in (0,1)$, then $\bar{X}$ is minimal sufficient statistics. But it seems that $X_1+X_2$ is complete since its distribution is Binomial(2,p), but it is not sufficient, let alone minimal sufficient...

$\endgroup$
0
$\begingroup$

You are completely right, and there is a lot of evident counterexamples. The word sufficient is missed in the theorem. The right statement is:

If a minimal sufficient statistics exists, any complete sufficient statistics is minimal sufficient.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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