Re: Rich Ulrich continues his statistical Muddle, Quackery, and MALPRACTICE

On Fri, 6 Jan 2006 19:43:31 GMT, "Kevin E. Thorpe"
<kevin.thorpe@xxxxxxxxxxx> wrote:

> Reef Fish wrote:
>
> [much snipped]
>
> > The main, and the only needrf, reason for NOT checking any of the
> > independent variables X for normality or outliers is the FACT that
> > in the standard (conditioned on X) regression setup, NOTHING is
> > assumed about the distribution of X -- that is, ANY distribution is
> > perfectly valid except for those Xs with known errors in data
> > recording.
> >
> > -- Bob.
>
> I would not normally post to this thread, but I wanted to recognize
> that Reef Fish's statement above is correct and very succinctly put.

Just for clarity's sake -- The reason for "NOT checking" is
not what separates Bob and me. I have agreed several times
that there is not a statistical requirement. (If you want
another name, call mine a requirement for efficient practice.)
And if someone tells you that there is an error in your data,
you should deal with it. Does Bob look, himself, to find
bad values? That seems to be a sneak-peek across his barrier.

I see further wisdom and time-saving utility in various
reasons for *checking*, which I have described elsewhere
(read the last two paragraphs of "Bob Ling vs Normality",
http://groups.google.com/group/sci.stat.math/msg/12dfe550e4c3287e )
and Kevin mentions one more.

> To follow-up on "Xs with known errors in data recording, plotting of
> independent variables can be valuable for identifying Xs with
> systematic error (eg. a set of lab values from one site that
> are all out by an order of magnitude).

As I read him, Bob would insist that you discover that sort
of error from your regression and regression diagnostics.

--
Rich Ulrich, wpilib@xxxxxxxx
http://www.pitt.edu/~wpilib/index.html
.

Relevant Pages

  • Re: Sandra Day OConner resigns
    ... > bob wrote: ... >> Alan Lichtenstein wrote: ... I am convinced that such rhetoric is the main reason Democrats are ... Modify your erroneous beliefs. ...
    (soc.senior.issues)
  • Re: Jack are you a MAN or a RAT?
    ... I can't resist playing the role of Jack in response ... Why didn't you ask Bob Ling how he found ... Reef Fish did make a careless slip in omitting ... I will return the favor and play Reef Fish Bob by calling Afonso a "quack". ...
    (sci.stat.math)
  • Re: Proposed Robert J. Kolker info pack
    ... All I am proposing is that we withdraw ALL social reinforcement ... no ill-will for his baseless and senseless views of Moslems. ... Bob is a model of good behaviour except ... and reason he defends so staunchly elsewhere. ...
    (talk.origins)
  • Re: Power Analysis for Multiple Regression and Indifference
    ... Got it Bob. ... your response in sci.stat.math. ... identical post in all three groups instead of separate post the same ... -- Reef Fish Bob. ...
    (sci.stat.edu)
  • Re: The Dylan Effect
    ... silly enough to admit being taken beyond reason by Bob Dylan's art. ... Now I like rationalists. ... If Bob Dylan did not make us lose our perspectives sometimes he would ...
    (rec.music.dylan)