Dear List: I have been asked to calculate power for a logistic
regression analysis and I need some guidance. The situation we have
is the following.
We are looking at Nurses' willingness to report to work during a Bird
Flu outbreak. Primary data indicates about 30% would report to work. We
would like to get a sample so that we can examine the relation among a
number of variables. The Outcome variable is whether or not they are
considered to be prepared to handle their responsibilities (YES or No).
If the effect size is 1.5, alpha = .05 (two-tailed), and power eq .80,
then what sample size would I need. I would also like to see what
sample size I would need for a moderate OR of 2.50. I have looked at
NCSS PASS program and it requires the input for two things that I am not
sure I understand. They are P0(Baseline Prob Y =1) and P1(Alt. Prob =1).
I have tried the Help directory but I am not sure I fully grasp PO and
P1. Does any one have any first hand knowledge about them. I would
appreciate input. thanks, martin sherman
Martin F. Sherman, Ph.D.
Professor of Psychology
Loyola College
Director of Masters Education: Thesis Track
Psychology Department
222 B Beatty Hall
4501 North Charles Street
Baltimore, MD 21210
Martin F. Sherman, Ph.D.
Professor of Psychology
Director of Masters Education: Thesis Track
Loyola College
Psychology Department
222 B Beatty Hall
4501 North Charles Street
Baltimore, MD 21210
410 617-2417 (office)
410 617-5341 (fax)
[hidden email]
Locked
