How to Report a Pearson Correlation in APA 7 (With Example)

A Pearson correlation measures the strength and direction of the linear relationship between two continuous variables. The write-up is short, but the APA 7 formatting rules around the r value, degrees of freedom, and leading zeros trip people up. This guide gives you the exact format, a worked example you can copy, and the mistakes reviewers catch.

What you need before you write a single word

An APA 7 write-up of a Pearson correlation needs these values from your output:

1. The correlation coefficient (r).
2. The degrees of freedom (df), which is N minus 2 (report N somewhere either way).
3. The exact p value.
4. Optionally a 95% confidence interval for r, which APA 7 encourages.

The correlation coefficient r is itself the effect size, so you do not need a separate one. As a rough guide, .10 is small, .30 is medium, and .50 is large.

The APA 7 format template

Report the result in running text using this pattern:

There was a [strong/moderate/weak] positive/negative correlation between [variable 1] and [variable 2], r(df) = .XX, p = .XXX, 95% CI [.XX, .XX].

boltAll 53 templates, ready to paste with the italics set: the Rescue Vault, $27 →

Formatting rules reviewers actually check:

• Italicize the symbols: r, p, N.
• Put the degrees of freedom (N minus 2) in parentheses after r.
• No leading zero on r or p, because neither can exceed 1, so write r = .45, not 0.45.
• Round r to two decimals. Report p to two or three decimals, and if it is below .001, write p < .001.
• State the direction (positive or negative) and describe the strength in words.

A worked example

Suppose you measured hours of study and exam score for 62 students.

• N = 62, so df = 60
• Result: r(60) = .48, p < .001, 95% CI [.27, .64]

Written up in APA 7, that becomes:

There was a moderate positive correlation between hours of study and exam score, r(60) = .48, p < .001, 95% CI [.27, .64]. Students who studied more tended to score higher.

The sentence carries the direction, the strength in words and as a coefficient, the significance, and the confidence interval.

The APA 7 correlation matrix (for several variables)

If you correlated several variables, report a correlation matrix rather than many sentences (the full layout, with means, SDs and the table note, is in how to make an APA correlation table). APA tables use horizontal rules only:

Note. N = 62. Asterisk indicates p < .05.

Reporting a non-significant result

Use the same statistics; change the wording, and do not call it a trend:

There was no significant correlation between hours of sleep and exam score, r(60) = .18, p = .162, 95% CI [−.07, .41].

Where to find these numbers in SPSS

• Correlations: for each pair, the Pearson Correlation, Sig. (2-tailed) and N. The degrees of freedom are N − 2.
• SPSS 27 and later can add confidence intervals (Confidence interval button in the Bivariate Correlations dialog).

Mistakes reviewers catch

• A leading zero on r or p. APA drops it for anything bounded by 1, so r = .48, not 0.48.
• Writing p = .000. Report p < .001.
• Omitting degrees of freedom or N. The reader needs the sample size; report r(60) or state N = 62.
• Claiming causation. A correlation is not evidence that one variable causes the other. Describe the association, not an effect.
• Using Pearson on the wrong data. Pearson assumes a linear relationship between two continuous variables. For ranked or ordinal data, or a monotonic but non-linear relationship, report Spearman's rho instead.
• Ignoring outliers. A single extreme point can inflate or hide a correlation. Inspect a scatterplot before trusting r.

Before you report: did the test's assumptions hold?

A Pearson correlation assumes:

• Two continuous variables.
• A linear relationship (check with a scatterplot).
• Approximate bivariate normality and no extreme outliers.

If the relationship is monotonic but not linear, or the data are ordinal, report Spearman's rho, which has its own APA format and uses r_s instead of r.

Let KyroStat do the write-up for you

Formatting correlations by hand, with the leading-zero rules and the matrix layout, is where errors creep in. KyroStat runs the correlation on your data, produces the scatterplot, checks linearity and outliers, and hands you the finished APA 7 sentence, a publication-ready correlation table, and the underlying Python or R code. Upload your spreadsheet, and the report is done in seconds.

Run a Pearson correlation yourself, in the browser

mtcars ships with R: 32 cars from a 1974 road test. This asks whether heavier cars use more fuel. Runnable in your browser, nothing to install.

# Pearson correlation: car weight against fuel economy
cor.test(mtcars$wt, mtcars$mpg)

Running that gives:

Pearson's product-moment correlation

data:  mtcars$wt and mtcars$mpg
t = -9.559, df = 30, p-value = 1.294e-10
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 -0.9338264 -0.7440872
sample estimates:
       cor 
-0.8676594

Every number in the write-up above comes from output like this. If you want the mechanics rather than the reporting, the free R lesson on this walks through it step by step, and the playground is there whenever you want to try something.

Frequently asked questions

What degrees of freedom does a correlation use? N minus 2. With 62 participants, df = 60, reported as r(60).

Do I need a separate effect size for a correlation? No. The coefficient r is the effect size. As a guide, .10 is small, .30 is medium, and .50 is large.

When should I use Spearman instead of Pearson? When the data are ordinal, the relationship is monotonic but not linear, or the assumptions of Pearson are violated. Report it as r_s.

My p value shows as .000. What do I write? Report p < .001. A p value is never exactly zero.

What if I want to predict, not just correlate? A correlation describes how two variables move together; to predict one from the other, run a simple linear regression, or a multiple regression with several predictors. For two categorical variables, use a chi-square test, and for agreement between two raters, Cohen's kappa. Not sure which applies? The test decision guide walks through it.

Which related guides might I need? Often these: partial correlation, point-biserial correlation and Kendall's tau.