What is the importance of sample size in building normative tables?

• A. Larger, well-represented samples provide more precise estimates and narrower confidence intervals.
• B. Smaller samples are more precise.
• C. Sample size has no effect.
• D. Larger samples always worsen generalizability.

Answer: (A)

The main idea is that sample size directly affects how precisely we can estimate the norms. When you have a larger, well-represented sample, the sampling error shrinks, so the estimated norms (means, percentiles, etc.) are closer to the true population values. This also produces narrower confidence intervals around those estimates, meaning you can judge where an individual score fits with greater accuracy. With a small sample, estimates can swing a lot due to just a few unusual cases, making the norms less stable and the interpretation less reliable. Representativeness matters too: a very large sample that is biased or unrepresentative won’t generalize well. But when the sample is both large and representative, the norms are more precise and more generalizable, which is why the best answer emphasizes larger, well-represented samples providing more precise estimates and narrower confidence intervals.