Practical Regression: Log vs. Linear Specification

This is the seventh in a series of scripts that, when bound in a textbook could be entitled “Practical Regression.” The purpose of the notes is the theoretical content of most statistics texts with practical advice on nearly three decades of experience of the author, with over one hundred years experience of colleagues who have offered leadership combined supplement based. As the title “Practical regression” implies, these notes are a guide to performing regression in virtually … Read more »

This is the seventh in a series of scripts that, when bound in a textbook could be entitled “Practical Regression.” The purpose of the notes is the theoretical content of most statistics texts with practical advice on nearly three decades of experience of the author, with over one hundred years experience of colleagues who have offered leadership combined supplement based. As the title “Practical regression” implies, these notes are a guide to performing regression in practice. This note explains how to choose between log and linear specifications. The note emphasizes the economic interpretation of a logical model and as coefficients in a log-regression suggest. The note concludes that states, how to choose between log and linear specifications on econometric reasons, including an explanation of the Box-Cox test.
«Hide

from
David Dranove
Source: Kellogg School of Management
13 pages.
Release Date: 11 June 2012. Prod #: KEL641-PDF-ENG
Practical Regression: Log vs. Linear specification HBR case solution