Re: Most accurate method of fundamental frequency determination ?

Randy Yates wrote:

> Hey Peter,
>
> Thanks for the new link.

No wuckers.

> What does "statistically efficient" mean?

When I use the term, I mean that the variance of a given unbiased
estimator meets the Cramer-Rao lower bound on the variance of such
estimators (as the sample size [number of data points] increases to
infinity).

The reason for the caveat is that many good estimators break down
(exhibit threshold behaviour) at "high" noise levels.

Some people use "as the SNR increases to infinity", to get around the
same issue... but is not the same thing.

Ciao,

Peter K.

.