How do I interpret the p-value from this t-test?

The p-value is the probability of seeing a difference this large (or larger) between the two sample means if there were actually no difference in the underlying populations. A common threshold is p < 0.05 to call the difference statistically significant; p=0.085 in the example does not clear that bar.

Why does this use pooled variance instead of Welch's t-test?

This calculator assumes both groups have equal population variances and pools them into a single estimate, which is the classic Student's t-test. If your two groups' standard deviations are very different, Welch's t-test (which doesn't assume equal variances) would be more accurate.

T-Test Calculator

Q: Why does this use pooled variance instead of Welch's t-test?

This calculator assumes both groups have equal population variances and pools them into a single estimate, which is the classic Student's t-test. If your two groups' standard deviations are very different, Welch's t-test (which doesn't assume equal variances) would be more accurate.

Run a two-sample t-test to compare the means of two groups.

How this is calculated

t = (mean1 − mean2) ÷ √(pooledVariance × (1/n1 + 1/n2))

Assumptions used in this calculation

Equal variance assumed: Uses pooled-variance Student's t-test; results may differ from Welch's t-test for groups with very different variances.

About this calculator

The t-test calculator runs a two-sample (independent, equal-variance) Student's t-test to compare the means of two groups, returning the t-statistic, degrees of freedom and p-value.

Worked example

mean1=50 vs mean2=45

Result: t=1.75, p=0.085 (not significant)

Was this helpful?

Frequently asked questions

Chi-Square Calculator

Run a chi-square goodness-of-fit test on observed vs. expected frequencies.

Confidence Interval Calculator

Calculate a confidence interval for a sample mean.

T-Test Calculator

About this calculator

Frequently asked questions

How do I interpret the p-value from this t-test?

Why does this use pooled variance instead of Welch's t-test?

Related calculators