[EMAIL PROTECTED] (Stan Brown) wrote in message 
news:<[EMAIL PROTECTED]>...
> Gordon Kenyon <[EMAIL PROTECTED]> wrote in sci.stat.edu:
> >In quantitative methods text-books for the social and behavioral
> >sciences one constantly sees the equation which describes the pdf for
> >both normal distributions in general and the standard normal
> >distribution.  I have never seen any basic warning that this
> >"description" of the standard normal distribution is only the density
> >function and not a computing formula of any kind. 
> 
> It's not? I'm pretty sure that in the past I have computed the 
> population between two z scores by computing the definite integral 
> with those z scores as limits. Granted, it's a lot more efficient to 
> use a table or a calculator (and in fact I used my TI89 to calculate 
> the definite integral). 
> 
> Perhaps I am failing to understand what you mean by "a computing 
> formula"?

  I think I make it clear later in my post.  What I am describing is
the density function presented to look really scary (with the number
"e" and pi and all), then hustled away never to spoken of again, its
role fulfilled by "table C". As a stand-alone density function it
isn't much use- taking the integral converts it into the distribution
function.  Not that any of this is even hinted at in introductory
social/behavioral science stats texts.  One is told rather (in the
several example texts I have on hand) that further explanation
"requires calculus".  I contend it is a long way from "calculus in
general" to the information that will allow a student to initiate a
sound base for her or his work.  I use (and am used to) "computing
formula" meaning a directly applicable function providing a meaningful
outcome.  Like one is generally provided for variances, sums of
squares and one-and-two-variable regressions.
.
.
=================================================================
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