Hi
Sorry for this going out with the "mailing list" subject
header. An oversight on my part.
On Tue, 7 Nov 2000, Nathalie Cote wrote:
> Suppose you were in a Methods or Statistics class in which you had to design
> a study, create the materials, collect some of the data, and then use the
> data from this partial sample to simulate or fill in fictitious data for the
> rest of the sample.
>
> Let's say, for example, that you've collected scores on self-esteem and body
> image instruments from 10 college men and 10 college women, and you want to
> use those data as the basis for generating fake data for 40 more women and
> 40 more men. The data will then be analyzed for correlations between the
> measures and differences between men and women on each measure and on the
> correlations.
I do two variations of this for my honours methods and stats
class.
(1) They work on individualized assignments that are computer
generated. I use SPSS algorithms for generating samples from
known populations (e.g., specified mu, sigma, rho, ...) and they
include their students numbers as part of the SET SEED= value.
SEED determines the actual data. So you could use the 10
observations to "estimate" mu, sigma, and rho, and then plug
those values into the SPSS routines. When I get into more
complex situations (e.g., multiple regression, factorial
anovas) there is some "trial and error" work in getting realistic
data.
(2) We also do a class project each term, where we design a
study, develop measures, etc. Ideally we then run a study with
100 or more real subjects. I give them algorithms to sample a
specified number of observations out of the entire data set for
their personal analyses and writeups. Occasionally there has not
been enough time to collect full data so we end up with just data
for the class (30-40 students). In those cases, I have
"replicated" data set. That is, simply add the set of
observations to itself a specified number of times, and then
sample from this expanded set. Ten might be a little low to do
this approach on, depending on what you want the final n to be.
Best wishes
Jim
============================================================================
James M. Clark (204) 786-9757
Department of Psychology (204) 774-4134 Fax
University of Winnipeg 4L05D
Winnipeg, Manitoba R3B 2E9 [EMAIL PROTECTED]
CANADA http://www.uwinnipeg.ca/~clark
============================================================================
