In article <[EMAIL PROTECTED]>, David C.
Howell <[EMAIL PROTECTED]> writes
>    This morning I sent out the message below. I still have basically 
>    the same question, but when I went back and looked at my resampling 
>    program, I discovered an error. When I corrected that, the 
>    distribution is normal. But I still don't know what is wrong with 
>    my argument that it shouldn't be normal.
>
(trimmed)
>
>    That would seem to settle the question--b is normally distributed.
>
>    BUT, suppose that we standardized our variables. This is a linear 
>    transformation for both X and Y, so would not change the 
>    correlation nor the shape of distributions. With standardized 
>    variables the slope is equal to the standardized slope (beta). And 
>    it is easy to show that beta, with only one predictor, is equal to 
>    the correlation coefficient. So when we take standardized 
>    variables, which are just linear transformations of unstandardized 
>    variables, r, b, and beta will all be numerically equal.
>
>    Now, we all know that the sampling distribution for r is skewed 
>    when r* (the parameter) is not 0. If we let r* = .60, the skew is 
>    quite noticeable. But if r and beta are equal, then the sampling 
>    distribution of beta will be equal to the sampling distribution of 
>    r, and therefore it will also be skewed. And if the sampling 
>    distribution of beta is skewed, so should be the sampling 
>    distribution of b, because it is simply a linear transformation on 
>    beta.
>
>    So now I have shown that the sampling distribution is skewed, 
>    though I began by quoting experts I respect saying that it is 
>    normal.
>
>    Finally, I used Resampling Stats to empirically generate the 
>    sampling distribution. It is very definitely skewed.
>
>    So where did I go wrong? The sampling distribution of b cannot be 
>    both normal and skewed, at the same time.
>
In order to standardise the variables, you need to look at the data to
work out the constant and scaling factor, which depend on the data.
Y'i=cYi+d is linear but
Y'i=Yi/stddev(Y)-mean(Y) is not.
Linear functions don't give you grief if you present them with Yi=0 for
all i.

After you have standardised the data points, they are no longer even
independent of each other - since you fix both the mean and variance, if
you show me all but two of the data points, I believe that I should be
able to work out what the other two are - well almost. I think this
boils down to 

Y1^2+Y2^2=G
Y1+Y2=H

which is the intersection of a straight line and a circle, so you have
0, 1, or 2 possible solutions.
-- 
A. G. McDowell
.
.
=================================================================
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