Re: Statistical Analyses of Non-Static Group Question

Hi,

You've done a great job describing what's distinctive and "unusual" with
your design. To really help, though, I (or anyone really) will also need to
know more about what's "typical" about your design.

So, if you can say bit more about:

(a) who your participants are, how you are selecting them (or how they are
self-selecting), and how they are being assigned to various treatment
conditions (if there are any),
(b) what the participants are doing (i.e.,what's the task or tasks),
(c) what materials or stimuli are being used and, in particular, how the
materials differ due to any treatment conditions or manipulations, and
(d) how you are assessing and testing the participants and how often (i.e.,
what's the measure and its frequency)

that would be great. These four things -- participants, tasks, materials,
and measures -- are essential to understand in order to provide sound
advice.

No need to go overboard, though. I can ask follow-up questions for
clarification or elaboration, if needed. For now, if you can just provide
the basics of what's going on along these four dimensions, that's a great
start.

Cheers,
Doug


On Thu, 09 Aug 2007 15:52:21 -0700, gwcallahan1@xxxxxxxxxxxx
<gwcallahan1@xxxxxxxxxxxx> wrote:
I don't have a background in statistics so perhaps someone can lend
some guidance with respect to the issue that I present here or tell me
where I can go to find guidance.

The goal is to determine how well a group of participants for a given
program is performing over a given period of time. The number of
participants is not static. The program has a lifecycle where the
number of participants starts out small, builds to a maximum then
declines through attrition until the program is retired. Participants
tend to participate with greater frequency when first added to the
program then taper off with time. A very small percentage of
participants are extremely active from the time they are added until
they leave the program and to a point where they artificially raise
the norm.

The question then is how does one compare group performance from one
sample to the next if the group dynamic is changing?

How does one account for the influx of new participants and the effect
they have on the group?

How does one correct for the overly active participants?

Is it valid to look at only those participants who appear in
subsequent sample periods (i.e. exclude additions and removals)?

Statistics is a broad subject. What form of analysis does this problem
represent? What texts (books) should I study to gain a better
understanding of the problem?


doug morse | psychology vanderbilt | 615.322.5565 | http://edoug.org/dm

.

Relevant Pages