POPM 3240 Lecture Notes - Lecture 9: Observational Error, Confounding, Cervical Cancer
Document Summary
Any systematic error in the design, conduct, or analysis of a study that results in a mistaken estimate of an exposure"s effect on the risk of disease . Increase sample size (always a chance of a freak sample) Due to design flaws: selection of participants, data collection, confounding, analysis, etc. Affects validity (ability to get the right answer) Solution: as researcher: careful study design, analytic techniques, as a reader: making decisions about study after critically appraising it. Three types: selection, information, confounding, selection bias. Arises from the way subjects are selected, agree to participate, or agree to remain in the study (samples doesn"t represent source population) The relationship between e and o among those in the study differs from that among those who were potentially eligible for the study but did not participate. Many types (we will look at 3: nonresponse/volunteer, detection/surveillance, loss of follow up.