Observational Study

In an observational study, the researcher observes the behavior of the individuals without trying to influence the outcome of the study.

\(\ominus\) Key terms:

response/dependent variable vs. explanatory/independent variable

confounding variable: usually known and measured, but not properly controlled.

lurking variable: not included in the study at all.

Types of observational studies:

  • Cross-sectional studies. Collect information about individuals at a specific point in time, or over a very short period of time. A snapshot.

  • Case-control studies. Individuals who have certain characteristics (cases) are matched with those that do not (controls). Retrospective.

  • Cohort studies. A cohort is observed over a long period of time. Prospective.

Example

  1. Smoking and hypertension.

  2. Daily screen time and reported sleep quality.

  3. Financial aids and retention rate in colleges.

Experiments

In a designed experiment, a researcher randomly assigns the individuals in a study to groups, intentionally manipulates the explanatory variables, and records the value of the response variable for each individual.

\(\ominus\) Key terms:

experimental unit, factors, treatment

control group and placebo

single-blind vs. double-blind

Types of experiments:

  • Completely randomized design: each experimental unit is randomly assigned to a treatment.

  • Matched-pairs design: only two levels of treatment and the experimental units are paired up.

  • Randomized block design: the experimental units are (1) divided into homogeneous groups (i.e., blocks), and (2) randomly assigned to treatments.

Examples

  1. Testing a new medicine for pain relief.

  2. Piloting a new training method.

  3. Measuring plant growth with different fertilizers