|
Activity Number:
|
162
- SPEED: Government Statistics, Health Policy, and Marketing
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 31, 2017 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistics in Marketing
|
|
Abstract #323755
|
View Presentation
|
|
Title:
|
AARP 2016 Master Model Building and Validation
|
|
Author(s):
|
Renting Xu* and Jared Weiss and Paul Maiste and Jerrod Begora and Roger Marcus
|
|
Companies:
|
AARP and AARP, Inc and Lityx,LLC and Lityx,LLC and Lityx,LLC
|
|
Keywords:
|
AARP Member Opinion Survey ;
50 Master Models ;
Factor Analysis ;
Scores ;
Logistic Regression ;
Campaign Selection
|
|
Abstract:
|
AARP's Member Opinion Survey (MOS) obtains information on members' experience,attitudes,and situation in life. The most recent version was sent out to a random sample in May 2016 and yielded 20,000 responses. These responses are used to build the Masters models, a suite of fifty models predicting members' preferences, aligning with specific groupings of questions from the MOS. The first step to build a Masters model is factor analysis which turns a group of questions into multiple factors. Each MOS respondent then receives a score loaded from factors. Based on the distribution of the scores, a cutoff point is defined for each model. Individuals whose scores above the cutoff point are considered to be positive responders. The second step is modeling. A logistic regression model is applied to predict the likelihood of a positive response, with variables including demographic, census data, contact history, and past activities. Validation showed all 50 models brought a significant lift comparing to random performance. Campaign managers therefore can select the most responsive prospects with the model applied to the entire 30 million members to save a significant budget.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2017 program
|
