

Height and age were recorded for a group of children 4 to 15 years old, and a regression analysis indicated the following relationship: per year.Ī slope of 0 means that changes in the independent variable on the X-axis are not associated with changes in the dependent variable on the Y-axis, that is, there is no association.Ĭonsider the following example. weight gain on average, then the slope for this relationship is 2. If each 1 year increase in age is associated with a 2 lb.

In the image below each step has a width of 1 and a rise of 2, so for each horizontal (X) increment of 1 step, there is a 2 unit increase in the vertical measurement (Y). In the illustration above the slope is 307.5, so the average savings per week is $307.50.Ī useful analogy for slope is to think about steps. The slope (b 1) is the steepness of the regression line, indicating the average or expected change in Y for each unit change in X. The correlation coefficient indicates how closely these observations conform to a linear equation. In an earlier example we considered accumulated savings over time.
