Without more detail, it is hard to know what to suggest. What data do you have? (e.g. Are they from doctors or patients? From what group of people? Are the data a random sample, and if so, of what? Do they include covariates that may be of interet? (e.g. data on patient and on physician?)
How many different drugs are there for this disease? Do they all have the same purpose? Do many patients have prescriptions for two drugs? For more than two drugs? Might some patients be getting different prescriptions from different doctors? Might some patients be self-medicating, and, if so, how would that affect what you want to do? HTH Peter Peter L. Flom, PhD Assistant Director, Statistics and Data Analysis Core Center for Drug Use and HIV Research National Development and Research Institutes 71 W. 23rd St www.peterflom.com New York, NY 10010 (212) 845-4485 (voice) (917) 438-0894 (fax) >>> [EMAIL PROTECTED] 3/2/2004 6:51:37 PM >>> Hello. I have a statistics question that I was wondering if you could answer. I'm doing research on a particular disease and am interested in examining which drugs are commonly prescribed together. Which statistical tests do you suggest I use? Thanks. . . ================================================================= 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/ . =================================================================
