On this page
What this lesson covers
A parametric correlation t-test assesses whether the population Pearson correlation is zero using matched observations from normally distributed variables.
Calculate the statistic from the sample correlation and number of matched pairs. Separate evidence of a nonzero relationship from the strength of that relationship.
How do you calculate the correlation t-statistic?
Multiply the sample correlation by √(n − 2), divide by √(1 − r²), and compare with a t-distribution with n − 2 degrees of freedom.
Correlation t = sample correlation × √(n − 2) / √(1 − sample correlation²)
- Sample Pearson correlation of the matched variables
- Number of matched pairs
For example, Strategy Q and a commodity strategy have sample correlation 0.25 over 144 matched monthly returns. Under the lesson’s normality assumptions and H₀: ρ = 0, t = 0.25 × √142 / √(1 − 0.25²) ≈ 3.08, with 142 degrees of freedom. It exceeds the two-sided 5% critical value 1.977, supporting a nonzero correlation.
Common mistakes
- Reading statistical significance as evidence of a large correlation confuses significance with correlation size.
Try a practice question
Choose an answer, then check it to read the explanation for every option.
Continue studying in Quizara
In Quizara the lesson comes with more practice questions on the topic, explanations for every option and an AI tutor for your follow-up questions.
Written by the Quizara Editorial Team under our editorial standards.