What Is a Scatter Plot Matrix?

Cartesian Coordinates

• A Cartesian coordinate system specifies each point on a plane using pairs of numerical coordinates that indicate the point's distance from each of two fixed directional perpendicular lines, the x-axis (horizontal) and y-axis (vertical). Each coordinate can be positive or negative, with the sign telling you the coordinate's direction.

Graphs Using Cartesian Coordinates

• You can plot the relationship between two variables on a graph using Cartesian co-ordinates. Each variable uses one axis of the graph. For example, you might want to plot the relationship between the growth of a plant seeding against the time since planting. For the purposes of data sets that include only positive numbers, the negative part of the axes is usually omitted, giving a square-shaped graph.

Scatter Plot Graphs

• A scatter plot graph, also known as a scatter graph, scatter chart, scatter diagram or scattergram, represents a data set as points on a two-axis Cartesian graph. One variable is assigned to the x-axis; the other to the y-axis. The resulting graph is a scatter of dots across a square plane. Scatter plot graphs are useful for visualizing the relationship between the two variables. They can help reveal any problems or issues with the data, such as large numbers of outliers; data points that have markedly different values than are typical for your data set.

A Scatter Plot Matrix

• A scatter plot shows the relationship between two variables; for more than two variables, use a scatter plot matrix. To examine the relationship among three variables -- for example, a seedling's height, the time since planting, and the hours of direct sunlight it receives, you create a matrix of nine squares. The upper left square could display the plant height, the central square the time since planting and the lower left square the sunlight hours. The upper middle square could contain a scatter plot of the height and time; the upper right could contain a scatter plot of the height and sunshine; and so on for the rest of the matrix.