• Understanding Research: Case Control Studies

    by Cian O'Brien. Last modified: 09/05/14


    • Study group is defined by the outcome (presence of a disease) not by exposure to a risk factor
    • The study starts with the identification of a group of cases (individuals with a particular health outcome) in a given population and a group of controls (individual without the health outcome)
    • Prevalence of exposure to a potential risk factor is compared between cases and control
    • If the prevalence of exposure is more common among cases than controls, the exposure may be a risk factor for the outcome
    • Useful for studying disease that are rare
    • Major characteristic is that data on potential risk factors are collected retrospectively – bias
    • A particular problem associated with case-controls – should be addressed in design and conduct of study

    Cases: People in a population with the disease

    Controls: People in a population without the disease


    Issues in the design of case-control studies

    • Formulation of a clear hypothesis
    • Case definition
    • Sources of cases
    • Incident cases – cases newly diagnosed
    • Prevalent cases – individuals who have had the outcome under investigation for some time
    • Selection of controls  – should be selected to be a representative sample – to minimize bias

    Sources of Bias

    • Retrospective nature they are susceptible to the effects of bias which may be introduced as a result of a poor study design or during the collection of exposure and outcome data
    • Because the disease and exposure have already occurred at the outset of a case-control there may be differential reporting of exposure information between cases and controls based on their disease status
    • Cases and control may recall past exposures differently because knowledge of being a case may affect whether the individual remembers a certain exposure (recall bias)
    • The recording of exposure information may vary depending on the investigator’s knowledge of an individual’s disease status (observer bias)
    • Temporal bias may also occur when trying to establish a link between exposure and outcome. It must be clear that the exposure occurred well before the diagnosis of the disease
    • The design and conduct of the study must be carefully considered as there are limited options for the control of bias during analysis


    • A factor associated independently with both the exposure and outcome and can be a problem where cases and control differ with respect to a potential confounder.
    • It can be dealt with:
      • Design stage – when selecting controls (matching or restriction)
      • Analysis stage – statistical techniques (adjustment) and multivariate techniques

     Analysis of case-control studies

    • OR to estimate the strength of association between exposure and outcome
    • It is not possible to estimate the incidence of disease from a case-control study – unless the study is population based and all cases in a defined population are obtained


    The odds ratio is a measure of the odds of exposure in the cases, compared to the odds of exposure in the control group.



    Calculation of the OR from a hypothetical case-control study of smoking and cancer of the pancreas among 100 cases and 400 controls (Table 1)



    The OR calculated from the hypothetical data in table 1 estimates that individuals with cancer of the pancreas (cases) are 4.5 times more likely to have smoked than those without the disease

    • The odds ratio of smoking and cancer of the pancreas has been performed without adjusting for potential confounders.
    • Further analysis of the data would involve stratifying by levels of potential confounders such as age.


    • Cost-effective relative
    • Case-control studies are retrospective, cases are identified at the beginning of the study –  no long follow up period (compared to cohort)
    • Efficient for the study of diseases with long latency periods
    • Efficient for the study of rare disease
    • Good for examining multiple exposures


    • Prone to bias – selection, recall & observer
    • Limited to examining one outcome
    • Unable to estimate incidence rates of disease
    • Poor choice for the study of rare exposures
    • The temporal sequence between exposure and disease may be difficult to determine

    Examples of case-control studies

    • Investigations of cases of childhood leukaemia near Sellafield

    Controlling for Confounding

    Design Stage:

    • Randomization – Reduces potential for confounding by generating groups that are fairly comparable with respect to known and unknown confounding variables (attempts to simulate a counterfactual contrast)
    • Restriction – Eliminates variation in the confounder (e.g. only recruiting males into the study will eliminate confounding by sex)
    • Matching – Involves selection of a comparison group that is forced to resemble the index group with respect to the distribution of one or more potential confounders


    • Unlike selection and information bias, confounding is one type of bias that can be, to some extent, adjusted in the analysis
    • Stratification
    • Multivariate methods
    • To control for confounding in the analyses – must measure the confounders in the study!
    • Investigators usually do this by collecting data on all known, previously identified confounders
    The following two tabs change content below.
    Cian O'Brien

    Cian O'Brien

    Cian is an Irish trained Emergency Medical Technician, Registered General Nurse and holds a Masters degree in Public Health from University College Cork, Ireland. His research interests include prehospital care and marathon medicine.

    Tags: , ,

    Leave a Reply