Stephen J Fromm wrote:

> [snip]
> > This is from a stats prof! We'll see if he is successful in getting
> > the concepts through my thick skull!
>
> My main problem with stats is that the concepts are not economically
> presented.

Now I _like_ that.  Economically presented.  Wouldn't that mean, fewer
equations, fewer words?  :)

I think the key issue is how people learn math-type stuff.  most of us tend to
work from the specific to the general, which is why we like a specific case to
start off.  But recognition of the generalities involved comes more easily or
less easily.  I think we need more focus on explaining these generalities - the
'rules' - to people who do not see them easily.

Jay

>
>
> In math (my training), there's more emphasis on central points, which leads
> to (*relatively*) less confusion.
>
> There are also problems, like discredited methods not clearly disavowed (I'm
> thinking of "model fishing" involved with some multi-step regression
> models).
>
> Your point about omission of calculations is well-founded.  Many books seem
> to have the attitude "Here's was SAS says..."
>
> ..
> ..
> =================================================================
> Instructions for joining and leaving this list, remarks about the
> problem of INAPPROPRIATE MESSAGES, and archives are available at:
> ..                 http://jse.stat.ncsu.edu/                    .
> =================================================================

--
Jay Warner
Principal Scientist
Warner Consulting, Inc.
4444 North Green Bay Road
Racine, WI 53404-1216
USA

Ph: (262) 634-9100
FAX: (262) 681-1133
email: [EMAIL PROTECTED]
web: http://www.a2q.com

The A2Q Method (tm) -- What do you want to improve today?




.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to