Paired Samples t test

The paired samples t test is a parametric test of whether the mean difference between two related measurements, such as pre- and post-scores from the same subjects, differs from zero.

대응표본 t검정은 같은 대상의 사전·사후 점수처럼 서로 관련된 두 측정값의 평균 차이가 0과 다른지를 검정하는 모수 검정입니다.

How do I test whether scores changed between two time points for the same people?

같은 사람들의 점수가 두 시점 사이에 변했는지 어떻게 검정하나요?

The paired samples t test compares the means of two related measurements by testing whether the average within-pair difference is zero. It fits pre-post designs, matched pairs, and two conditions measured on the same subjects when the differences are approximately normally distributed.

When to use Paired Samples t test

• Pre-test and post-test scores from the same participants
• Two conditions measured on each subject in a within-subjects design
• Matched pairs, such as twins or case-control pairs, measured on a continuous outcome

When to use something else

• Differences are clearly non-normal in a small sample: use the Wilcoxon signed-rank test
• Three or more time points or conditions: use repeated measures ANOVA

Assumptions and requirements

• Continuous outcome measured twice on the same or matched units
• Pairs independent of one another
• Paired differences approximately normally distributed
• No extreme outliers in the differences

What the analysis reports

• Mean difference with 95% confidence interval
• t statistic, degrees of freedom, and p-value
• Cohen's d for paired data
• Descriptive statistics for each measurement

How to report it

Scores increased from [time 1] (M = [value], SD = [value]) to [time 2] (M = [value], SD = [value]), t([df]) = [value], p = [value], d = [value].

Related methods

• Wilcoxon Signed Rank Test
• Independent Samples t test
• Repeated Measures ANOVA

Run Paired Samples t test on Quorant