In short
A t-test is reported with the mean and SD of each group, the t with its degrees of freedom, the exact p and Cohen's d: t(58) = 3.42, p = .001, d = 0.89. A chi-square test of independence carries the degrees of freedom and the sample size inside the same parentheses, plus an effect size: χ²(2, N = 200) = 12.40, p = .002, Cramér's V = .25 (use φ for 2 × 2 tables). t, p, M, SD, d, N and V are italicised; χ² and φ are Greek letters and stay upright.
These are two of the most basic tests and, at the same time, two that accumulate the most APA formatting errors. Here's how to report the t-test and the chi-square in APA 7, with examples. The general guide is in how to report results in APA 7.
If what you have is a loose t or χ² and all you need is the formatting, the APA 7 results formatter gives you the full string with correct italics and decimals. And if it's the other way round, you have the result written out in a paragraph and need Cohen's d or Cramér's V, effect size from text extracts it without sending you back to SPSS.
How to report a t-test
You report each group's means and standard deviations, the t statistic with its degrees of freedom, the p-value and the effect size (Cohen's d). For example:
"The experimental group (M = 23.45, SD = 4.12) scored significantly higher than the control group (M = 19.87, SD = 3.98), t(58) = 3.42, p = .001, d = 0.89."
Always state whether the t-test is independent-samples or paired. If variances are unequal (a significant Levene's test), use Welch's t and report the decimal degrees of freedom it returns. If that is your case and the two SPSS tables leave you unsure which row applies, paste the output and it points to the right row, with the sentence already drafted.
How to report a chi-square
For the chi-square test of independence you report the χ² statistic with its degrees of freedom and the sample size in parentheses, the p-value and the effect size (Cramér's V for tables larger than 2×2; phi, φ, for 2×2 tables):
"There was a significant association between group and response, χ²(2, N = 200) = 12.40, p = .002, Cramér's V = .25."
Remember the formatting: χ² and φ are Greek, so they stay upright; t, p, M, SD, d, N and V are italicised.
If what you need is not a single sentence but the table (several comparisons, several outcomes, or both tests side by side), the universal APA table generator builds the t-test, ANOVA or χ² table from your numbers, with the three horizontal rules, the italics where they belong, APA decimals and the note already in place.
Common mistakes
In the t-test: omitting Cohen's d, not stating whether it's independent or paired, and ignoring the homogeneity-of-variance assumption. In the chi-square: forgetting the N in parentheses, not giving the effect size, and applying it with expected frequencies below 5 without the continuity correction or Fisher's exact test.
Frequently asked questions
How do you report an independent-samples t-test in APA 7?
Means and standard deviations of both groups first, then the statistic: "The experimental group (M = 23.45, SD = 4.12) scored significantly higher than the control group (M = 19.87, SD = 3.98), t(58) = 3.42, p = .001, d = 0.89." Say in the text whether the test is independent or paired, and add the 95% CI of the mean difference if your journal asks for it.
What do I do if Levene's test comes out significant?
Use Welch's t and report the decimal degrees of freedom it returns: t(52.31) = 3.05, p = .004. Do not silently take the "equal variances assumed" row. In fact several methodologists argue for using Welch by default, whatever Levene says, because it costs almost nothing when the variances are equal and protects you when they are not.
How do you report a paired-samples t-test?
State that it is paired, give the descriptives at each time point or the mean difference with its confidence interval, and remember the degrees of freedom are n − 1, with n the number of pairs, not the number of observations. For the effect size, say which standardiser you used: Cohen's dz divides the mean difference by the standard deviation of the differences, while the version that divides by the average standard deviation of the two moments gives a different, usually smaller, value. They are not interchangeable.
How do you report a chi-square in APA 7?
The degrees of freedom and the sample size go inside the same parentheses, separated by a comma, followed by the exact p and the effect size: "There was a significant association between group and response, χ²(2, N = 200) = 12.40, p = .002, Cramér's V = .25." Forgetting the N is the most repeated formatting error in the whole test.
Which effect size goes with a chi-square?
φ (phi) for 2 × 2 tables and Cramér's V for anything larger; both run from 0 to 1, so they take two decimals and no leading zero. In a 2 × 2 table with a clinical or epidemiological reading, the odds ratio or the relative risk with its 95% CI usually says more than V. For a goodness-of-fit chi-square, Cohen's w.
What if the expected frequencies are below 5?
The chi-square approximation stops being trustworthy. In a 2 × 2 table, use Fisher's exact test and report the exact p. In larger tables, either collapse categories that make substantive sense or compute an exact or simulated p. Yates's continuity correction is the classic patch for 2 × 2 tables, but it tends to be over-conservative, so Fisher is usually the cleaner answer.
Want your tests done right and reported right?
I'm a PhD in psychology. I choose the correct test, check the assumptions, compute the effect size and hand you the APA 7 report ready for your thesis or paper.
Get a free consultation →That's the t-test and chi-square reported without issues. If your design needs something more. ANOVA, regression, non-parametrics, we look at it in my statistical consulting for theses and papers.