this is interesting ... alan mclean says NO ... and, previously radford neal said YES...

the opinions of both i highly respect

so, what is the original inquirer to do?

the fact is in this case ... there is either a difference in salaries (for which they have the data) or not

let's say for argument ... that there is a difference in favor of males ... of $1000 a year ... but, because there is wide variation within the male and female categories (because of years of experience) ... a t test fails to reject the null

what is the data analyst going to say ... that there is no difference ... ??? how can you use the t test RETENTION of the null to persuade the females that the $1000 dollars is just a figment of their imagination?

we know there is a difference ... this issue then is ... is the difference important ENOUGH that the company/organization ... should do something about it? a t test is NOT going to help resolve that problem

therefore ... i claim in this kind of a situation ... the FACTS are known and ... an inferential test like a t test is completely inappropriate



At 09:49 AM 4/4/03 +1000, Alan McLean wrote:
If the population means are known and being compared, then any difference must be significant! No need for any test.....

Alan

On Friday, April 4, 2003, at 05:31 AM, Rich Ulrich wrote:

On 3 Apr 2003 19:13:43 GMT, trw7atixdotnetcomdotcom (Tim Witort)
wrote:

I'm developing a report in an analysis program.
This report examines employee salaries - comparing
the salaries of men to those of women in a particular
job title in a particular company.  The goal is to
determine if the difference in their mean salaries
is statistically significant.

I have been directed to the t-test to gather this
information.  When I look at the t-test, however,
it appears to be geared toward *estimating* the
difference in the means of a population based on
a *sample* of the population.  Since I am using
the entire population, can I still use the t-test
to determine if the difference in the means is
statistically significant?  Is there another test
that should be used instead?

Use the regular t-test.


There is such a thing as correction for
"finite population"  but it is hardly ever appropriate.

It certainly is not, in the instance *you*  describe:
With 100% sampled, there is no "correction";
*you*  would simply conclude A is greater than B  whenever
A is measured as greater than B.

Taking votes and ordering supplies...  you might use a
finite-sample correction   to further those purposes,
if you have a survey that is (a) incomplete;
and (b)  randomly chosen, for what is complete.

You can use  groups.google.com , advanced, to look
in the sci.stat.*   groups  for the topic.

--
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
..
..
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
..                  http://jse.stat.ncsu.edu/                    .
=================================================================

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

Dennis Roberts, EdPsy, Penn State 208 Cedar Bldg. AC 8148632401 Email: <mailto:[EMAIL PROTECTED]> Web: http://roberts.ed.psu.edu/users/droberts/drober~1.htm

.
.
=================================================================
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