1) Suggest that you log/record _all_ your data, not just the ones that 'do well.' If you have ever looked closely at photographs (analogue, chemical kind) you know that

"You won't understand fuzzy until you've seen sharp."

In your case, you won't understand 'good' communication, until you have seen 'poor.' It takes both to understand what correlates with what.

2) Suggest that you consciously work out (based on correlations perhaps) those factors & levels that indeed are likely to influence 'communication.' Set up a proper orthogonal array of these factors (i.e., a designed experiment - it ain't hard), and then select from your data stream those conditions that fit your design. Make sure you collect data for all the selected conditions, and do a proper DoE analysis for the factor effects.

3) Oh, and I forgot to put this first - I _assume_ that your measure of 'communication' is treated as a continuous variable, on a ratio scale. If it is not, then what you measure would be a first item to resolve.

Cheers,
Jay

meredith wrote:

Summary of research project: The basic idea is that on a computer
network you have machines called servers and machines called clients
that talk to each other.  The data flow is of interest to the research
team I'm working with.  We're measuring the data flow and calculating
a correlation value as a standard measure of "how well" a server and
client talk to each other.  Naturally we only want to see servers and
clients that talk to each other well, so we use a correlation
threshold to determine which servers and clients talk to each other
well and which don't.

Currently our calculations are done after the fact, it's more a
history report than a real time diagnostic tool.  I'm looking for a
way to guess the correlation value (within 90% - 99%) based on the
number of machines that passed the correlation threshold.  I have four
possible variables to work with and I'm currently testing for
interactions between the variables.

Any tips or guidance is appreciated.
.
.
=================================================================
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/                    .
=================================================================

Reply via email to