CHAPTER 15 Introducing Correlation and Regression 201

Chapter 15

Introducing Correlation

and Regression

C

orrelation, regression, curve-fitting, model-building  — these terms all

describe a set of general statistical techniques that deal with the relation-

ships among variables. Introductory statistics courses usually present only

the simplest form of correlation and regression, equivalent to fitting a straight

line to a set of data. But in the real world, correlations and regressions are seldom

that simple — statistical problems may involve more than two variables, and the

relationship among them can be quite complicated.

The words correlation and regression are often used interchangeably, but they refer

to two different concepts:»

» Correlation refers to the strength and direction of the relationship between

two variables, or among a group of variables.»

» Regression refers to a set of techniques for describing how the values of a

variable or a group of variables may cause, predict, or be associated with the

values of another variable.

IN THIS CHAPTER»

» Getting a handle on correlation

analysis»

» Understanding the many kinds of

regression analysis