SAR HS 300 Study Guide - Midterm Guide: Blind Experiment, Sampling Error, Observational Error
3 Jan 2017
School
Department
Course
Professor
Document Summary
Identify spurious, non-causal and causal association in epidemiology. Spurious associations: false association that could be caused by recall bias, specifically prevalent in ecological studies. Non causal associations: confounders (there is a secondary association) Causal associations: changes in exposure produce changes in outcome (best shown with experimental studies) A statistically significant association between an exposure and an outcome is a starting point for evaluating cause-effect relationships. Six criteria for judging potential causal associations (hill"s postulates) Strength of association: stronger the association the more likely it is to be causal. Consistency of association: when same study is done in different populations at different times in different places, same findings are found. Dose-response relationship (biologic gradient): increased exposure leads to greater frequency of outcome. Study validity: the degree to which inferences are drawn from a study are warranted. Takes into account (1) study methods, (2) representativeness of study sample.
