Chapter 13More Topics in Regression
One of the goals for this chapter is to link regression analysis with some of the hypothesis tests we conducted in Chapter 10. In Chapter 10, we compared two parameter values. We will show that the same test we learned for comparing two population means can be implemented using ordinary least squares (OLS) regression. Moreover, we can use regression to compare more than two population means. In most statistics textbooks, there is a dedicated chapter for comparing multiple means that is titled Analysis of Variance (ANOVA). The ANOVA chapter spends time walking through a separate testing procedure to compare more than two means. However, the results of that testing procedure are fully contained in the ANOVA section of the regression output produced by any statistical software program. In this way, the chapter on ANOVA is usually a bit awkward because the regression techniques learned in the regression chapter cover ANOVA plus much more. Part of this chapter will walk through the process of using the ANOVA section in regression to conduct hypothesis tests of multiple means.
We will also take a brief look at other regression topics covered in some business statistics courses. We will explore how to use OLS regression to estimate relationships that are not predicted to be linear. The chapter also explores how to estimate and interpret the interactions between independent variables. Finally, we will comment on time-series regression and forecasting. ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access