Point-Biserial Correlation Calculator

Measure the relationship between a two-group variable and a continuous one. Paste the 0/1 values and the matching continuous values in the same order.

Learn how to calculate it yourself

Enter your values

Results update as you type.

Point-biserial r

Check your inputs

Enter valid values to see your result. Use the field hints or open the data guide for help.

Calculated in your browser. No data is sent to us.

Calculate it yourself

Use binary group codes 0,0,1,1 with matching continuous values 1,3,5,7.

Follow this worked example, then repeat the steps with your own numbers.

  1. Find the mean of each variable

    Mean binary code = 0.5. Mean continuous value = 4.
  2. Center values and add products

    Binary deviations = −0.5, −0.5, 0.5, 0.5. Continuous deviations = −3, −1, 1, 3. Sum of cross-products = 4.
  3. Divide by the combined spread

    Sum of squared binary deviations = 1; continuous = 20. r = 4 ÷ √(1 × 20) ≈ 0.894. r² = 0.8.
  4. If needed, look up the significance test

    t = r × √[(n − 2)/(1 − r²)] = √8 ≈ 2.828, with n − 2 = 2 degrees of freedom.

    Use a t table or spreadsheet to find twice the upper-tail probability beyond |t|. Point-biserial correlation is Pearson correlation with a 0/1 variable.

Check your answer in the calculator

Use your PaperSurvey.io results

Export matched binary and numeric responses to calculate their point-biserial correlation here.

PaperSurvey Correlation widget showing a relationship between two numeric rating questions.
View full-size screenshot
Example from PaperSurvey.ioThis example compares two rating scales; point-biserial correlation instead pairs a binary code with a numeric value.

What point-biserial measures

The point-biserial correlation measures how strongly a two-group variable relates to a continuous one, for example whether answering a test item correctly relates to the total score. It is mathematically a Pearson correlation with one variable coded as 0 and 1, so it runs from minus 1 to plus 1 and is read the same way.

Formatting your data

Enter the binary variable as 0s and 1s, then the continuous values in the same respondent order. The two lists must be the same length. A positive result means the group coded 1 tends to have higher continuous scores.

Frequently asked questions

Where is this used in testing?

Item analysis uses point-biserial correlation as a discrimination index: it shows whether students who got an item right also scored higher on the test overall.

Embed this calculator on your site

Free to use. Paste this snippet wherever you want the calculator to appear.


Get Started with PaperSurvey.io Software

Get Started

Start your 14-day free trial now, no credit card required.