Determining treatment effectiveness in a clinical trial (generalized linear mixed models)

Medical researchers want to test whether a new anticonvulsant drug can reduce a patient's rate of epileptic seizures. There are 565 patients, each randomly assigned to the new drug or the control (placebo) group and then tracked over a number of weeks to see how many epileptic seizures they experience each week. There is a measurement before the trial as a baseline and 1 measurement for each of the 5 weeks after treatment (the drug or placebo) begins, so each patient corresponds to 6 records in the dataset.

This information is collected in anticonvulsants.sav. See the topic Sample Files for more information. Repeated measurements from the same patient are typically positively correlated so a mixed model with some random effects should be appropriate. The target field, the number of seizures, takes positive integer values, so a generalized linear mixed model with a Poisson distribution and log link may be appropriate.

Next