1. Customer Relationship Management: A Database Approach MARK 7397 Spring 2007 James D. Hess C.T. Bauer Professor of Marketing Science 375H Melcher Hall jhess@uh.edu 713 743-4175 Class 5

2. 1.0 Year 0 0.5 XXX XXX XXXXXXX X X ABB Purchases time Regular ABB Service, S GE Purchases Brand Choice Models What Might Have Happened

3. 1.0 Year Regular ABB Service, S Heavyup Service, S+  0 0.5 XXX XXXXXXX XXXXX ABB Purchases GE Purchases Brand Choice Models What You See

4. Brand Choice Models What You Infer 1.0 Year Regular ABB Service, S Heavyup Service, S+  0 0.5 XXX XXXXXXX XXX XX X X X X ABB Purchases GE Purchases brand switches

5. Brand Choice ABB 1 GE 0 Service Regression Model of Brand Choice ? ? ?

6. Brand Choice e a+bA 1+e a+bA Logit Model Of Brand Choice ABB 1 GE 0 Service

7. ABB GE The part a i + b i S is the “deterministic” part of utility. The terms  i are aspects of the situation which we are unable to observe, and hence give a feeling of randomness to the choice. The customers are not really random, but simply know their situation better than us. Explanation: Random Utility Model Daniel McFadden 2000 Nobel Laureate

8. If  A -  G has a logistical distribution, then this probability is where a=a G -a A and b=b G -b A. Random Utility Model (continued) ab

9. Calibrating the Logit Model Suppose there were n brand choices and m times ABB was chosen and n-m times GE was chosen, each with a different service S. The likelihood of this is the probability: The values of a and b are chosen to “maximize likelihood” of observing the sample we did. ABBGE

10. Interpretation of Logit Coefficients Logit is not linear like regression, so its coefficients have a slightly different interpretation. Odds that ABB is chosen over GE: Odds= Pr(ABB)/Pr(GE) = e a+bS. How much do odds of ABB go up if S increases by 1? New Odds = e a+b(S+1) = e a+bS e b = Odds x exp(b) Exp(b) tells the factor by which the odds of ABB rise when S is one unit higher. Examples: b =2, exp(b)= 2.71 2 = 7.3, so when b=2, increasing S by +1 increases the odds of ABB being chosen by a factor of roughly seven. If they had been 3:1, they are now 22:1. b = - 1, exp(b)= 2.712 -1 = 0.37, so when b= -1, increasing S by +1 decreases the odds of ABB being chosen by a factor of roughly one-third. If they had been 3:1, they are now 1:1.

11. Let’s look at a very simple Excel version of a logit model. Please download the file “ABB Logit illustration.xls” from WebCT. It should look like the following.