Re: Who "invented" the null hypthesis?


Matt Dz. wrote:
"Luis A. Afonso" wrote:
DZ. (not Bob) wrote

Matt Dz. wrote:

*** The term "acceptance interval" is of course correct in case of parameter space being a REAL LINE. However, the "acceptance region" is more general.
Regards,
Matt Dz. ***


My response:

WRONG
Do you ignore that the term *interval* could be n-dimensional?

Do you ignore the fact, that the only correct term for n-dimensional
case is "... region"?

That was actually my response late at night, except Google
said I had made too many posts already. :-)


For example - in case of the p-dimensional multivariate normal
distribution, when we want to find the counterpart to CI (which would be
the univariate case) for the mean vector, the confidence region will
be a p-?dimensional ellipsoid. This is one of the kinds of elliptic
confidence regions.

This is the redeeming value of picking out Afonso's errors because
it prompted my forthcoming post about "elliptic" <?> and
"rectangular" questions about bivariate (and multivariate)
normal random variables!

Regards,
Matt Dz.

-- Bob.

.

Relevant Pages

  • Re: parsing Nero .nri file -- possible character set issues (perl newbie)
    ... >> Hello Matt, ... > Thanks for the response. ... reading the file using the sysread function, ... they are organized into fixed-length records of some ...
    (comp.lang.perl.misc)
  • Re: car radio/cd in bathroom 12 volt supply
    ... That way I won't waste my time constructing a response. ... You know Matt, I hate to say it, but you're starting to make me realize ... you're acting like a real jerk. ... Nyah nyah nah-nyah-nyah. ...
    (rec.audio.car)
  • RE: /dev/random on Linux
    ... I did not get any answer from Matt and was sure that it was of no interest. ... Zvi did contact Matt Mackall, the current /dev/random maintainer, ... So he's demanding that one person spend time responding to his ... received no response. ...
    (Linux-Kernel)
  • Re: Slow mouse reactions on SW 2006
    ... caught Matt on a bad day, then that is to bad but even after an informitive, ... non-confrontational response he continued with how I was full of BS when I ... talking about Matt the consultant who you paid bucks to or Matt the guy ... who posts here because, like the rest of us, it is gratifying to help ...
    (comp.cad.solidworks)
  • Re: Call subroutine based on character variables? Guru Required!
    ... > Matt wrote: ... Typical bv response. ... What relevance does the choice of compiler have to ... Rich ...
    (comp.lang.fortran)