O'Reilly logo

Statistical Inference: A Short Course by Michael J. Panik

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

12.2 Linear Relationships

One of the most common types of relationships detected between the X and Y variables is a linear relationship (e.g., the type of relationship exhibited in Figs. 12.2a and 12.2b).

12.2.1 Exact Linear Relationships

Suppose we have the equation Y = 2 + 3 X, where Y is the dependent variable and X is the independent variable (Fig. 12.3). Here “2” is the vertical intercept—the value of Y obtained when X = 0. The coefficient “3” attached to X is the slope (= rise/run) of the line—when X increases by one unit, Y increases by three units. More generally, the slope of this linear equation is the rate of change in Y per unit change in X. The expression Y = 2 + 3 X is “not a statistical equation”—it is an exact mathematical equation. There is very little (if anything) that a course in statistics can contribute to the understanding of this equation.

Figure 12.3 A linear equation.

img

Let us examine Fig. 12.2a again. We noted previously that this scatter diagram involving, say, n sample points exhibits a direct linear relationship between X and Y. In fact, because not all of the points (Xi, Yi), i = 1, . . ., n, lie on a linear equation passing through them, these points could “not” have been generated by an “exact” linear equation. This observation opens the door for the specification of a statistical model (called a regression model) that can describe the “goings-on” ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required