Terms from Statistics for HCI: Making Sense of Quantitative Data

This is when the relationship between things cannot be represented by a simple linear formula such as y=3+2x; that is where there is some sort of bend or curve in the graph of the data. In statistics this tends to be harder to see because there is usually a lot of noise in the data. Note particularly that when performing linear regression, two variables might have a large Pearson correlation coefficient but the relationship can still be non-linear.

Used on pages 49, 114

Also known as non-linear, nonlinear