Comparison of study designs

Descriptive and analytic study designs are observational in nature, in that children cannot be randomly assigned to receive the environmental exposure (e.g. chemical). Analytic study designs are 

Descriptive9 Ecologic Assessment of group exposures and health outcomes, thereby gauging impact of a particular exposure in a defined population Hypothesis generating Cannot link exposure to diseases or study outcomes among individuals Residual confounding may threaten validity 

Cross- sectional Design that simultaneously ascertains exposures and outcomes Appropriate for exploring research questions as a first attempt or to generate hypotheses for analytic study designs Can be completed in a relatively short period of time, often at reduced cost Useful initial approach for evaluating human health risks Disease prevalence only Cannot assess causality or the temporal relation between exposure and health outcome Residual confounding may threaten internal validity 

Cohort Longitudinal design that begins with ascertainment of exposure(s) for cohort members with follow-up for occurrence of Less subject to selection bias Can establish a temporal order between exposure and outcome Loss to follow-up may bias results Depending upon length of follow-up needed, can be costly 

---