Re: Statistics in Psychology?

In article <Mgcmg.2340$No6.48821@xxxxxxxxxxxxxx>,
Jerry Dallal <gdallal@xxxxxxxxxxxxxxxx> wrote:
Herman Rubin wrote:
As for being a good researcher in ANYTHING, a Ph.D. is
neither necessary nor sufficient. I never had a single
course in statistics, nor did I find one to audit.
Likewise for me in matrix algebra (a few weeks in an
abstract algebra course, definitely inadequate), or in
numerical analysis, or in set theory, in all of which
I have contributed.

If Karl Pearson or Neyman or Wald or Karlin had any
courses in statistics worth a darn, I would be highly
surprised.

One would hope that in the years since Karl Pearson flourished that the
profession would have learned to design a course worth a darn.

The profession has advanced in many directions.

Unfortunately, it seems that the tendency is to avoid
teaching a basic course in anything. By a basic course,
I mean one teaching the underlying concepts, not how to
treat trivial problems. Concepts have to be taught and
then practiced, and education has to be for the future.
The Ph.D. in mathematics and in statistics has greatly
declined in the past 30 years from this.

The fundamental concepts in statistics are probability,
and the problem of decision making under uncertainty.
There are a few books which start with probability,
which is represented by measure theory with the whole
space having measure 1. Now there are intuitive ideas
which can be used to exemplify this, but start with it
and continue. I can present measure theory and integration,
including countable additivity and why it is important,
at the high school algebra level; the ideas are much
simpler than usually made.

After the basics, they can understand how to formulate
their problems and understand the answers. It matters
not that they do not know how to carry out the procedures;
it takes someone with a strong background to use these
in even slightly complex problems.

Back to psychology. I have a SHORT derivation of the
asymptotics for factor analysis, which just carries
out my 1955 abstract, and which also points out that
everything gets worse if the usual normalizations are
used; variation which is irrelevant adds to the
deviations in the results. Where to publish this?
I do not expect someone with a first course to follow
the arguments, but to understand the problem and the
results.
--
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, Department of Statistics, Purdue University
hrubin@xxxxxxxxxxxxxxx Phone: (765)494-6054 FAX: (765)494-0558
.

Relevant Pages

  • Classical Text in Mathematics and Statistics
    ... Hardy G.H. A Course of Pure Mathematics ... Shilov G.E. Linear Algebra ... Feller W. An Introduction to Probability Theory and Its Applications ... Statistics, Volume 1: Distribution Theory ...
    (sci.math)
  • Maximum Likelihood Degree and PI
    ... "Algebraic statistics: ... like sheaves, degrees of algebraic functions, generating functions, ...
    (sci.stat.math)
  • Re: What Math Is Needed for Programming?
    ... Algebra for simple standard programming. ... Geometry for graphics work. ... Calculus for games and simulations. ... > school, Calculus, Algebra, Geometry, Statistics. ...
    (comp.lang.java)
  • Re: philippines population will reach 100 million in five years
    ... Send in your monetary contributions now. ... and the 'plagiarists' go to hell right? ... pass algebra so you can move on to plane trigonometry and statistics. ...
    (soc.culture.filipino)
  • Re: Put your babies on statins
    ... About half of the 25 male rats fed the ... >> are those of the Statistics Department or of Purdue University. ... I do not claim that these views are those of the Statistics Department or of Purdue University. ...
    (sci.med.cardiology)