HSS 3101 Lecture Notes - Lecture 35: Relative Risk, Prospective Cohort Study, Statistical Power
24 Nov 2018
School
Department
Course
Professor
Document Summary
Is affected by systematic and random errors. Can be reduced by increasing sample size. Types of error random and systematic. Selection bias there are 3 types listed below: If you perform a cross-sectional analysis at t1: two people have the moderate disease and one has the severe (two with the severe already died!, the risk ratio is 0. 5. At time t1 if we only use the prevalence of the disease: (how many people at time t1 have the disease) We are missing something: this is a bias. We should be using the incidence, counting all cases that occur in a time interval. Occurs in prospective cohort studies when individuals lost to follow-up do not have the same probability of having the clinical outcome of interest in comparison with individuals who remain under observation. Worst case scenario for loss to follow up: asd rate in adr treatment group = 100/400 = 25: asd rate in fusion treatment group =
