### 4.1 Correlation

The simplest way to investigate the relationship between two variables is to use the appropriate test for correlation. The relationship is illustrated graphically using a scatter plot (typically called an 'X-Y plot' in spreadsheets). A high degree of correlation will be shown where data points tend to fall along a straight line, where high and low values of the two variables tend to coincide (positive correlation) or where high values of one variable correspond to low values of the other, and vice versa (negative correlation). A 'shotgun' scatter, or an alignment of points that is close to horizontal or vertical, indicates very low correlation (Fig. 9 below).

**Figure 9.** Illustration of scatter plots with various properties: (a) 'shotgun' scatter, with low correlation, (b) strong positive correlation, (c) strong negative correlation, (d) and (e) low correlation, with very little change in one variable compared with the other, (f) this scatter would generate a spurious high correlation because of the effect of the five points enclosed by the shaded area