Re: large negative parameter correlations in regression


Anon. wrote:
Reef Fish wrote:
Anon. wrote:
Reef Fish wrote:
Stephen Clark wrote:
<snip>
I would suggest you pay little attention to what Bob O'Hara says in
Regression matters. He is full of thumbs and a frequent Quack on
that subject.

Well, kindly show why what I suggested was wrong. If I've made a
mistake, I'd be happy to know what it was.
--
Bob O'Hara
Department of Mathematics and Statistics

Perhaps someone ELSE can do that honor. I think even m00es
may be able to tell you a thing or three you don't know even thought
he is rather deficient in the Hypothesis Testing subject itself.

I see. So,you're not going to help the OP by showing what bits of my
advice were wrong: you merely malign me without feeling the need to
justify your insults.

I had already given the OP all the help I could, interpreting
everything
he mentioned, and suggested that he was missing the information
on partial correlations if he wants to know more about the exact
severity of his multicollinearity problem.

So, no change there.
--
Bob O'Hara
Department of Mathematics and Statistics

Your reply was so non-specific, so speculative, so name-dropping
without knowing what you were talking about that it would require
FREE tuition to explain it to YOU, without benefiting the OP.

You had already PROVEN yourself to be DEFICIENT in regression
methods, in Linear Models, and in every statistical topic your stuck
your nose into that no further proof is necessary.

I had mentioned over and over again that you're a disgrace to
the Department of Mathematics and Statistics in Helsinki, and
to the entire country of Finland by associateing your name with
theirs, in your anti-Netiquette 11-line sig.

I FINALLY noticed line 10 of your sig
WWW: http://www.RNI.Helsinki.FI/~boh/

that you actually had an honest self-confession:

*> I am forever unclear about whether I am a biologist or a
*> statistician (I think it depends on who I'm talking to).

I take that to mean you tell a biologist you are a statistician
and to a statistician that you're a biologist. :-) Not a bad
strategy given your absence of knowledge about STATISTICS.

*> I am presently employed by the Academy of Finland as a
*> research fellow, which means that I can avoid doing too
*> much teaching.

A research fellow in biology is about as low an academic
appointment anyone can get and claim to know anything
about statistics. It's a credit to the Department of Math
and Statistics that they would NOT ALLOW you to teach
anything!

Your background is about the same as that of Richard
Ulrich for being the top-two Quacks in sci.stat.math.
He used to have some research associate appointment
(but with an Asst. Prof. title) in the Department of
Psychiatry. His statistical knowledge is apparently all
self-taught, from SPSS manuals and other computer
manuals.

Now we have m00es, who is infinitely more knowledgeable
than you two put together, with blissfully IGNORANT about
some fundamental and basic concepts in APPLIED
statistics.

Perhaps he'll join you two if he revealed that he is some
kind of self-taught graduate student at the unimaaas.nl
in the Netherlands.

Then we would ALL know why such Quackery come out
of the mouths of the posters like you, Richard Ulrich, and
m00es.

If it's any consolation to all three of you, I believe you
are, each of you, statistically significantly different from
Luis A. Afonso, in the sense of "better". But that's
only STATISTICAL SIGNIFICANCE. When it comes
to PRACTICAL significance (or USEFULNESS) , now
being discussed in a thread in sci.stat.consult and
sci.stat.edu, I think all of you ranked about the same,
compared to Afonso, in the amount of NOISE you make,
relative to the small amount of statistical SUBSTANCE
you produce.

Hope the above helps all of you.

Did anyone ever tell any of you that "Silence is Golden"
when you are bankrupt in the statistical subject matter
under discussion?

-- Reef Fish Bob.

.

Relevant Pages

  • Re: APPEAL: Sci. Stat. Math. MODERATED
    ... Tkink into count the nonsense and ignorance on fundamental points in Statistics Jack Tomsky a very learned BIOLOGIST that his immoderate ... I never took a class in biology in high school or college. ... But it is clear to any sentient being that Jack ... It would quiet the group down and let us poor statistically ignorant ...
    (sci.stat.math)
  • JOBS: 3 postdocs in statistical bioinformatics and e-science, Newcastle, UK
    ... School of Mathematics and Statistics, ... statistical bioinformatics and computing science. ... Computational Biology or a related discipline. ...
    (sci.stat.math)
  • Hope for Pitmans Statistics
    ... lifespan or of weaning weight to maternal weight. ... good for biology, ... All the ratios are constraned to the range 0-1, ... relatively simple issue in statistics. ...
    (talk.origins)
  • Re: Hope for Pitmans Statistics
    ... Sean was keen to show that a guy with a simple ... >lifespan or of weaning weight to maternal weight. ... >good for biology, ... But the problem with Sean wasn't so much his statistics ...
    (talk.origins)
  • Re: HELP: Non-linear regression problem
    ... over the standard regression methods and outputs. ... Jacobian to calculate the next estimate (assuming that's what you're ... In the Nonlinear Regression context, ... That was one of my "consulting projects" at Yale Statistics Department ...
    (sci.stat.math)