***** To join INSNA, visit http://www.sfu.ca/~insna/ *****
"Carolyn.Birmingham-1" <[log in to unmask]> writes:
> I got asked a question today that I had no clue how to answer... When
> doing network stuff how does one figure out statistical power (meaning
> a formula to put in how many nodes, variables, kinds of ties, etc.)?
> Is it dependent upon the software used? I just sort of figured with
> 200 plus nodes and 100% response rate that this wouldn't be an
> issue...but a regular stats jock wants a more concrete answer...
What you describe (sample size) has nothing to do with power.
If you are doing a test, the basic idea would be to run the statistic
that you are using on a random (simulated) sample drawn from the test
statistics null hypothesis (no effect? whatever that means for your
Figure out the 95% or 97.5% percentile of the test statistics'
distribution -- you've just established the cut off point for a 5%
significance level (one or two sided).
Next, you've got to simulate data from situations which are what you
are looking for, and see how many times they exceed that cut-off point
above. That's the power.
The catch is that you've got to figure out the distributions to sample
from in both cases. Unless you can do it explicitly
(i.e. mathematical calculations), which is usually harder.
Anthony Rossini Research Associate Professor
[log in to unmask] http://www.analytics.washington.edu/
Biomedical and Health Informatics University of Washington
Biostatistics, SCHARP/HVTN Fred Hutchinson Cancer Research Center
UW (Tu/Th/F): 206-616-7630 FAX=206-543-3461 | Voicemail is unreliable
FHCRC (M/W): 206-667-7025 FAX=206-667-4812 | use Email
CONFIDENTIALITY NOTICE: This e-mail message and any attachments may be
confidential and privileged. If you received this message in error,
please destroy it and notify the sender. Thank you.
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.sfu.ca/~insna/). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.