Re: statistics versus biostatistics

On Jan 3, 6:34 pm, hru...@xxxxxxxxxxxxxxxxxxxx (Herman Rubin) wrote:
In article <1167795729.340183.67...@xxxxxxxxxxxxxxxxxxxxxxxxxxx>,

in many case, statistical procedures have to be largely
judged by their asymptotic properties.

These "mathematical statistics exercises" are the means
by which statistical procedures are evaluated.

Only a mathematician could write this. Statistical procedures have to
be evaluated by their empirical performance in particular problems. No
mathematical proof can guarantee their efficacity empirically, which
is all that matters (unless you are a mathematician).

illywhacker.

.