In meta-analysis, increasing external validity (generalizability) is accompanied by an increase in statistical power, which is the probability that a test correctly rejects a false null hypothesis.

• A. statistical power; reject a false null hypothesis
• B. p-value; accept a false null hypothesis
• C. confidence interval width; narrower is better
• D. sample bias; increases error

Answer: (A)

Statistical power is the probability that a test correctly rejects a false null hypothesis. In meta-analysis, pooling data from multiple studies increases the overall information about the effect, which reduces uncertainty and makes it easier to detect a real effect if one exists. When more true effects are detectable, the chance that the test will reject a false null hypothesis rises, so power goes up. That’s why the best description here is the idea that statistical power reflects the ability to reject a false null.

The other terms don’t capture that concept. A p-value measures the probability, under the null, of obtaining data as or more extreme than what was observed, and does not itself state the power to detect a true effect. Confidence interval width concerns precision of the estimated effect, with narrower intervals indicating more precision, not directly power. Sample bias refers to systematic error that can mislead results and typically reduces validity, not increases power.