Case Control, Cross Sectional, Ecologic - Week 7 IPHY

Case-Control Design Description

compares persons who have a disease (cases) with those who are free from the disease (controls); design explores whether differences between cases and controls result from exposures to risk factors

Case-Control Study Description

Single point of observation; unit of observation and unit of analysis are the individual; exposure is determined retrospectively; does not directly provide incidence data; data collection typically involves combination of primary and secondary sources

Selection of Cases

defining a case conceptually - standard diagnostic criteria & severity of disease; identifying a case operationally

Sources of Cases

(ideally) identify and enroll all incident cases in defined population in specific time period (like a registry)

Selection of Controls

ideal controls should have same characteristics as cases, except for exposure of interest; if controls were equal, easily tell the difference in disease status to exposure of interest

Sources of Controls

population based controls; obtain list of names and addresses of most residents in same geographic area as cases

Interpretation of Odds Ratio

exposed are # times more/less likely as non exposed to have disease
the odds of disease are _% higher/lower among exposed compared to non exposed

Strengths of Case-Control Study

tend to use smaller sample sizes than surveys or prospective studies; quick and easy to complete; cost effective; useful for studies of rare disease

Limitations of Case-Control Study

unclear temporal relationship between exposures and diseases; use of indirect estimate of risk; not useful for rare exposures; recall bias

Cross-Sectional Study Description

surveys of population to estimate prevalence of disease; exposures and disease measures obtained at individual level and simultaneously; single point in time; can describe magnitude and distribution of health problem; repeated surveys can be used to examine trends in disease or risk factors that vary over time

Strengths of a Cross-Sectional Study

generalizability; conducted in relatively short period of time; low cost

Limitations of a Cross-Sectional Study

limited usefulness for inferring disease etiology; does not provide incidence data; cannot study low prevalence of diseases; cannot determine temporality of exposures and disease as E & D information is collected at same time & after they have occurred

Ecologic Study Definition

unit of analysis is group, not individual; generally makes use of secondary data collected by government, some other agency, or investigators; unknown level of exposure for each individual in unit being studied

Ecologic Fallacy

observations made at group level may not represent exposure/disease relationship at individual level; fallacy occurs when incorrect inferences about individual are made from group level data

Simpson’s Paradox

an association in observed subgroups of population may be reversed in entire population

Difference between Case-Control and Cross-Sectional Studies

Case control studies retrospective - comparing cases and controls to identify past exposures
Cross sectional studies collect data from single point in time to assess prevalence and relationships between variables