Epidemiologic STUDY DESIGNS

Types of Epidemiologic Research


Experimental (implies randomization)

                Clinical trials

                Community intervention trials






Randomization - groups under study will be similar on measured and unmeasured variables



·       Strength of the association

·       Dose-response effect

·       Lack of Temporal Ambiguity

·       Consistency of Findings

·       Biological Plausibility

·       Coherence of Evidence

·       Specificity of the Association

·       Experimentation

·       Analogy


Different ways to describe study designs (other than experimental vs. observational):

·       Directionality

·       Timing




Deals with timing of investigation of exposure and outcome

·       Exposure known prior to disease – Forward directionality    

·         Exposure determined AFTER disease – Backward directionality     

·         Exposure and Disease determined simultaneously – Nondirectional




Relates to whether the study is initiated before or after the outcome.

Retrospective – the disease/outcome has already occurred when the study begins



Prospective – the disease/outcome occurs sometime after the initiation of the study



Could be a mixture or retrospective and prospective (Mixed timing)
We now go into the specific of the major study design:

          Clinical trial






Clinical Trials


Experimental design

Assess therapeutic effects/health benefits


Key features:



        Ethical concerns

        Intention to treat analysis (analyze-as-randomized, effectiveness) vs. Treatment-received analysis (efficacy)



Cohort Studies


Observational; Can be prospective or retrospective





Which do you think usually provides more accurate information, prospective or retrospective?


Ways in which a cohort study might be designed:

1.      Sample population, divide into exposed and nonexposed

2.      Identify an exposed population – find an external, nonexposed group for comparison




Advantages of cohort studies:

        Of observational studies, tends to be least prone to bias

        Can address several diseases in same study

        With retrospective, can be relatively low cost, quick

        Can be used with rare exposures


Disadvantages of cohort studies

        Loss to follow-up a potential problem

        Usually larger sample size than case-control

        Prospective – can be expensive & time-consuming

        Prospective – inefficient with rare diseases, diseases of

long latency


Case-Control Studies


Identify cases, then sample those without disease (controls)



Ideally should be from a clearly defined source population

Controls should also be from the same source population


Can be retrospective, prospective, or mixed


Case-Control Studies - continued


        Relative to cohort, quicker

        Usually smaller sample size

        Better with rare diseases than cohort

        Better with diseases of long latency periods

        Can evaluate multiple exposures



        Only one outcome can be studied (in contrast to cohort)

        Does not allow direct assessment of risk

        More susceptible to certain biases

        Not efficient for studying rare exposures


Use of incident vs. prevalent cases in case-control studies

Incident cases preferred

With prevalent cases, exposure-disease relationship may be affected by prognostic indicators of duration of disease.


Choosing controls in a Case-Control Study


Controls should be from same source population as cases.


        Population-based vs. hospital/clinic-based


Hospital vs. Population-based Case-control studies


Hospital Advantages (relative to population-based)

·       Controls easily accessible

·       Less expensive, less time consuming


Hospital Disadvantages (relative to population-based)

·       Controls less representative of source population

·       Controls are ill; possibly ill due to exposure of interest



·       Reye syndrome – relation with aspirin

·       Creutzfeldt-Jakob Disease – relation with animal products


Cross-Sectional Studies


Most frequently used study design.

Provides a snapshot of a population

Observational design

Variables measured at a single point in time



·       NHANES – National Health and Nutrition Examination Surveys

·       BRFSS – Behavioral Risk Factor Surveillance Survey

·       EPI – Expanded Program on Immunization Surveys

·       MICS – UNICEF Multiple Indicator Cluster Survey


The target population could be the general population, individuals belonging to an organization (Medical Society), patients at a hospital (patient satisfaction survey), etc., etc., etc.



·       Tends to be an inexpensive study design

·       Can assess several exposures and diseases simultaneously

·       Can generate hypotheses



·       Cannot establish whether exposure preceded disease

·       In general, deals with prevalent disease (potential for survivor bias)

·       Need large sample sizes for rare conditions


Example of a Cross-Sectional Study – Peripheral Vascular Disease in Scotland



Hybrid Designs


2 types described – both are variants of  population-based case-control study: Case-Cohort and Nested Case-Control


Case-Cohort Study


Start with a cohort study; identify those with disease (“cases”) at a latter point in time, select subsample from nondiseased as controls using exposure information collected at the start of the study.


Example: gastric cancer and H. pylori infection


·       Cohort of 9,775 men in Taiwan with blood samples at baseline.

·       During study, 29 developed gastric cancer

·       Selected 220 controls from those with no gastric cancer

·       Compared frequency of H. pylori infections at baseline.



Nested Case-Control Study


Variation of Case-Cohort.   Identify cases as they occur, select control(s) for each case.  Also called density-type case control study. 


Example of nested case-control: Cohort study of 5000 telephone employees



Incomplete Designs


Ecologic Studies


Also called ecologic correlations/studies; comparison based on summary or aggregate data from groups (not individuals).  Subject to ecologic fallacy.




Proportional Studies


Deals only with the proportion of deaths due to a cause.


3,520 deaths among nuclear power plant workers

Do not know size of population at risk