Logistic Regression
This technical note presents the reason for using a binomial logic regression in marketing applications and a consumer-utility-based behavioral rationale is presented for the applicability of the binomial logistic regression for modeling dummy variables.
Abstract
This technical note presents the reason for using a binomial logic regression in marketing applications. It is used in Darden's "Big Data in Marketing" course elective. The issues surrounding the use of a linear regression model when the dependent variable is a dummy variable are identified. A consumer-utility-based behavioral rationale is presented for the applicability of the binomial logistic regression for modeling dummy variables. Simulated and real data examples are used to present the mechanics of the logistic regression and the interpretation of the outputs. The relationship between odds ratio and the logistic regression probabilities are presented. Application areas such as brand choice and customer retention are discussed. Excerpt UVA-M-0859 Rev. Feb. 3, 2014 LOGISTIC REGRESSION Almost all of us are familiar with odds. What are the chances one thing will happen versus another? What are the chances you will succeed at work today? What are the chances your favorite game-show contestant will win today versus the chances he or she will lose? What we might not be familiar with is how odds can be applied to marketing analytics. What are the chances a customer will buy your product versus the chances he or she won't? What are the chances you will retain a customer versus the chances you will lose him or her? When you are using odds, you are examining two opposing outcomes. Any such unknown (i.e., one that can only be one thing or another) is known as a dummy variable. But if you know how to examine dummy variables properly, the results are anything but dumb. . . .