In article <[EMAIL PROTECTED]>,
Castagliola Philippe 51858309 <[EMAIL PROTECTED]> wrote:
>I agree with Dennis Roberts.
>Te mean, the variance, the median, the mode are quantities which are computed
>theoretically for a distribution.
>Then , we have the sample mean, sample variance, sample median which are random
>variables computed from samples. Like any random variables the sample mean sample
>variance and sample median have a variance...
>But as I know, there is no sample mode ! May be it is possible to derive one, but
>it seems not obvious for me.
There are ways to come up with a "nonparametric" procedure for
the sample mode; for example, see Chernoff's paper. However,
because of the difficulties in estimating it, the variance of
the estimator will not be on the order of 1/n; Chernoff got
1/n^{2/3}, and much more will be difficult to get.
--
This address is for information only. I do not claim that these views
are those of the Statistics Department or of Purdue University.
Herman Rubin, Dept. of Statistics, Purdue Univ., West Lafayette IN47907-1399
[EMAIL PROTECTED] Phone: (765)494-6054 FAX: (765)494-0558
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
