Research Methods and Statistics
What to know
Understand design logic: experimental vs. correlational, internal vs. external validity, random assignment vs. random selection, and threats to validity (maturation, history, regression to the mean, attrition). Know sampling and measurement concepts (operational definitions, levels of measurement). Statistics: descriptive (mean, median, mode, variance, standard deviation) and inferential (null hypothesis testing, Type I and Type II error, statistical power, effect size, confidence intervals). Recognize when to use common tests (t-test, ANOVA, chi-square, correlation, regression) at a conceptual level, and the difference between statistical and clinical significance. Understand research ethics: IRB review, informed consent, deception and debriefing, and data integrity.
Traps
Questions often swap Type I (false positive) and Type II (false negative) errors, or confuse power (1 − β) with alpha. Watch for items that describe a significant result and ask about generalizability-significance does not equal importance or applicability. Random assignment controls confounding; random selection supports generalizability.
Rule of thumb
Type I = rejecting a true null (false alarm); Type II = failing to reject a false null (miss). Power increases with larger samples and larger effects. A p-value is not the probability the null is true.