GraphPad Statistics Guide

Key concepts: Correlation

Key concepts: Correlation

Previous topic Next topic No expanding text in this topic  

Key concepts: Correlation

Previous topic Next topic JavaScript is required for expanding text JavaScript is required for the print function Mail us feedback on this topic!  

When two variables vary together, statisticians say that there is a lot of covariation or correlation.

The correlation coefficient, r, quantifies the direction and magnitude of correlation.

Correlation is used when you measured both X and Y variables, and is not appropriate if X is a variable you manipulate.

X and Y are almost always real numbers (not integers, not categories, not counts).

The correlation analysis reports the value of the correlation coefficient. It does not create a regression line. If you want a best-fit line, choose linear regression.

Note that correlation and linear regression are not the same. Review the differences. In particular, note that the correlation analysis does not fit or plot a line.

Correlation computes a correlation coefficient and its confidence interval. Its value ranges from -1 (perfect inverse relationship; ax X goes up, Y goes down) to 1 (perfect positive relationship; as X goes up so does Y). A value of zero means no correlation at all.

Correlation also reports a P value testing the null hypothesis that the data were sampled from a population where there is no correlation between the two variables.

The difference between Pearson and Spearman correlation, is that the confidence interval and P value from Pearson's can only be interpreted if you assume that both X and Y are sampled from populations with a Gaussian distribution. Spearman correction does not make this assumption.

If either X or Y has only two possible values, the results of Pearson correlation are identical to point-biserial correlation.