To better visualize the association between two data sets {*x _{1}, …, x_{n}*} and {y

_{1}, …, y

*} we can employ a chart called a*

_{n}**scatter diagram**(also called a

**scatter plot**). This is done in Excel by highlighting the data in the two data sets and selecting

**Insert > Charts|Scatter**.

Figure 1 illustrates the relationship between a scatter diagram and the correlation coefficient (or covariance).

**Figure 1 – Scatter diagrams**

Notice that the *x* and y values in the example with *r* = .976 are very strongly positively correlated. This is not too surprising since *r* is almost at its maximum value of 1. In the example with *r* = -.912, the linear correlation is also quite strong, but negative (note that the slope of the line that seems to fit the data is negative).

In the example where *r* = .300 and *r* = .068, there is no apparent linear relationship between *x* and y. In fact in the latter case it seems that the points are randomly scattered, indicated by a correlation coefficient near zero, which is consistent with the fact that *x* and y are independent or nearly so.

what about q-q or p-p plot when considering single variable