203 / 762
Chapter 5: Bivariate Data
203
association. It is the weather conditions which are impacting the values of
the variables and in turn impacting the association.
Hence, one can conclude that correlation is not the same as causation.
This situation is illustrated in
Figure 5-15
.
Figure 5-15:
Correlation and Causation
Next we will discuss how one can model any observed linear pattern.
Regression analysis
will allow us to propose a mathematical model for the
association. We can use such models to make predictions for one variable
given a value of the other variable. We will, however, restrict the
discussions to linear models.