lecture 11 - Case-Control Studies Lecture 12 o Identify...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Lecture 12 Case-Control Studies Case-Control Studies o Identify causes of disease by studying how risk factors affect diseased and non- diseased people differently o Subjects selected based on disease status o Disease of interest = cases o No disease of interest = controls o At baseline: o Disease status is known o Exposure status is unknown Case-Control Study Design o Collect data on past exposures o Compare frequency of exposure among cases and controls o Calculate the odds ratio for exposure(s) of interest o Retrospective study design Æ no temporality! Case-Control Study Design Target Population No Disease (Controls) Disease (Cases) Unexposed Exposed Unexposed Exposed Selection of Cases o Clearly define the cases o Definition of disease o List diagnostic criteria o Identify the cases o Capture cases accurately o Should be representative of all cases in the population Case Definition o Standard diagnostic criteria o Severity of disease o Subjective vs. objective criteria o Subjective o Subject reports symptoms o Clinician assesses symptoms o Objective o Medical instruments used to assess disease o Lab tests/values used to assess disease
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Misclassification o Putting people into the wrong category o Classify a case as a control o Classify a control as a case o Can be the result of: o Broad selection criteria o Overly restrictive selection criteria Bottom line: Misclassification introduces error to the study Odds Ratio o Measure of association for case control studies o OR = (a * d) / (b * c) o OR Interpretation: OR = 1.84 o Cases are 1.84 times as likely to be exposed relative to controls. o Cases are 84% more likely to be exposed relative to controls. OR Approximates Risk o OR is not a direct measure of risk Why? o OR approximates risk when: o Controls are representative of target group o Cases are representative of all cases o Frequency of disease in the population is low Question: How does misclassification affect the study’s results? o What is the OR? o What does the OR mean? o What happens if we accidentally said 50 people with diabetes didn’t have it? 1,000 500 500 550 350 200 Non-smoker 450 150 300 Smoker No diabetes Diabetes 1,000 550 450 550 375 175 Non-smoker 450 175 275 Smoker No diabetes Diabetes o What is the OR? o
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 04/06/2008 for the course PUBLIC HEA 832:335 taught by Professor Schneider during the Spring '08 term at Rutgers.

Page1 / 7

lecture 11 - Case-Control Studies Lecture 12 o Identify...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online