1001Ferramentas
📈 Calculators

Point-Biserial Correlation

Computes the point-biserial correlation coefficient, which measures the association between a continuous variable and a dichotomous (two-group) variable. It is, in fact, the Pearson correlation applied to the case where one variable takes only two values — so it ranges from −1 to +1 and carries the same interpretation. It shows up often in psychometrics, to assess how well a test item (right/wrong) discriminates between high- and low-scoring students. Enter the continuous values of each of the two groups.

Resultado

Point-Biserial Correlation

Computes the point-biserial correlation coefficient, which measures the association between a continuous variable and a dichotomous (two-group) variable. It is, in fact, the Pearson correlation applied to the case where one variable takes only two values — so it ranges from −1 to +1 and carries the same interpretation. It shows up often in psychometrics, to assess how well a test item (right/wrong) discriminates between high- and low-scoring students. Enter the continuous values of each of the two groups.

Correlating a yes-or-no with a number

Pearson's correlation measures the relationship between two continuous variables, but what about when one of them is just a yes or no, pass or fail, group A or group B? The point-biserial correlation covers exactly that case. Despite the technical name, it isn't a new formula: it is Pearson's correlation itself, applied when one of the variables takes only two values.

The calculation compares the means of the continuous variable in the two groups and scales that difference by the total spread of the data and by the proportions of each group. The result lives between minus one and plus one and reads like any correlation: near zero means belonging to one group or the other relates little to the continuous value; near the extremes, the separation is sharp.

Enter the continuous values of each of the two groups, in two separate lists. The tool returns the point-biserial coefficient. It is a central measure of classical test theory: in item analysis, it tells how much getting a specific question right is associated with doing well on the test as a whole, helping to flag questions that discriminate poorly.

Related Tools

The results provided by this tool are for general informational and educational purposes only and do not constitute professional, financial, medical, legal, tax or accounting advice. Always confirm important decisions with a qualified professional and official sources.