All free tools
Free · no signup

Independent samples t-test calculator

Compares the means of two independent groups using Welch’s t-test (robust to unequal variances), with Cohen’s d and a Levene variance check.

Let the AI do this — sign up freeUpload your data, get the write-up back.

Or skip the manual work

In the app, you chat with your data — the AI runs the analysis and writes it up.

Kahubi AILive in the app
Typing numbers in by hand works — but inside Kahubi you just upload your dataset and ask. I check the assumptions, run the right test, and hand you an APA-ready results section. Try me.

Free accounts include AI chat, data analysis, and every tool on this site.

Your data

Paste one column of numbers per group. Groups may have different sizes. Rename the groups to match your study (e.g. "Treatment", "Control").

n = 0
n = 0
Runs in your browser — data never leaves this page.

When to use this

Use an independent-samples t-test when two different groups of cases — treatment vs. control, novices vs. experts, condition A vs. condition B — are measured on the same continuous outcome, and you want to know whether the group means differ. This calculator runs Welch’s version, which does not assume equal variances; it behaves almost identically to the classic Student t-test when variances are equal and is markedly more reliable when they are not, which is why methodologists recommend it as the default.

Key assumptions

  • The two groups are independent — no participant appears in both (otherwise use the paired t-test).
  • The outcome is interval or ratio scaled.
  • Scores within each group are approximately normal, or each group has roughly n ≥ 30.
  • Equal variances are NOT required — Welch’s correction handles unequal variances and unequal group sizes.

Common mistakes

  • Using it for before/after measurements on the same people — that needs a paired-samples t-test.
  • Running several t-tests across 3+ groups instead of a one-way ANOVA, inflating the false-positive rate.
  • Interpreting p > .05 as proof the groups are equal — non-significance is absence of evidence, not evidence of absence.
  • Omitting the effect size; a tiny, unimportant difference becomes “significant” in large samples.

Frequently asked questions

Why does the calculator use Welch’s t-test instead of Student’s?
Welch’s t-test does not assume the two groups have equal variances. When variances are equal it gives essentially the same answer as Student’s test, and when they are not it keeps the false-positive rate where it should be. The output includes Levene’s test so you can see how different the variances are — but Welch is safe either way.
Can the two groups have different sample sizes?
Yes. Unequal group sizes are fine; the Welch degrees of freedom (which may be a decimal number, e.g. t(18.4)) account for both the unequal sizes and unequal variances.
What if my data are skewed or ordinal?
Use the Mann–Whitney U test, the rank-based alternative — it compares the two groups without assuming normality. We have a free Mann–Whitney calculator as well.

Related free tools

Sample size calculatorSample size for two groupsEffect size (Cohen's d)Descriptive statisticsOne-sample t-testPaired t-testOne-way ANOVAz-table (standard normal)t-table (critical values)Chi-square table

Stop copying numbers between tools

Inside Kahubi, the AI agent runs this analysis directly on your uploaded dataset — then writes the results section in your own writing style, with the statistics reported correctly.

Try Kahubi freeMore free tools