A school psychologist uses stratified random sampling to study a program and uses a well-researched measure before and after the intervention. Which statement about the study's validity is true?

A school psychologist uses stratified random sampling to study a program and uses a well-researched measure before and after the intervention. Which statement about the study's validity is true?

• A. The external validity is strong, but the internal validity is not, because changes that occur over the course of the intervention cannot be attributed solely to the intervention.
• B. The internal validity is strong, but external validity is not, because the sample limits generalizability.
• C. Both external and internal validity are strong due to stratified sampling.
• D. Both external and internal validity are weak due to lack of controls

Answer: (B)

The main idea here is how sampling and measurement affect validity. Using stratified random sampling helps ensure that important subgroups within the population are represented, which reduces sampling bias and makes findings more credible for the population that was actually sampled. The fact that a well‑researched measure is used before and after the intervention reduces measurement error and increases confidence that observed changes reflect real differences rather than artifacts of the instrument. Taken together, these design features support internal validity—the study can more plausibly attribute observed change to the intervention within the study context. However, because the sample may not capture all possible populations or settings beyond those strata, generalizing the results to broader groups is limited, so external validity is weaker.

The main idea here is how sampling and measurement affect validity. Using stratified random sampling helps ensure that important subgroups within the population are represented, which reduces sampling bias and makes findings more credible for the population that was actually sampled. The fact that a well‑researched measure is used before and after the intervention reduces measurement error and increases confidence that observed changes reflect real differences rather than artifacts of the instrument. Taken together, these design features support internal validity—the study can more plausibly attribute observed change to the intervention within the study context. However, because the sample may not capture all possible populations or settings beyond those strata, generalizing the results to broader groups is limited, so external validity is weaker.