Which of the following is an inferential statistic?

• A. T-tests
• B. Regression
• C. P-values and Confidence Intervals
• D. Percentages

Answer: (C)

Inferring something about a population from a sample relies on statements that quantify uncertainty and specify plausible values for a population parameter. P-values and Confidence Intervals are exactly those inferential statements. A p-value tells you how likely the observed data would be if the null hypothesis were true, guiding decisions about whether to conclude there’s an effect. A confidence interval gives a range of values that likely contains the true population parameter, reflecting sampling variability. Together, they provide the probabilistic conclusions that let you go beyond the sample data.

Percentages describe what was observed in the sample and don’t by themselves generalize to the population. T-tests and regression are methods used to perform inference and to obtain results (including p-values and estimates), but the direct inferential quantities you’d report to make population-level claims are the p-values and confidence intervals.