Activity Number:
|
417
- Redesigning Federal Surveys
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, July 31, 2018 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Government Statistics Section
|
Abstract #328728
|
Presentation
|
Title:
|
A Statistical Comparison of Call Volume Uniformity Due to Mailing Strategy
|
Author(s):
|
Andrew Raim* and Elizabeth Nichols and Thomas Mathew
|
Companies:
|
U.S. Census Bureau and U.S. Census Bureau and University of Maryland, Baltimore County
|
Keywords:
|
Multinomial Logistic Regression;
K-L Divergence;
Entropy;
Decennial Census
|
Abstract:
|
The U.S. Census Bureau conducts a variety of experiments to prepare for a full-scale decennial census and investigate possible improvements to operations. An innovation for the 2020 Census will be that the public can self-respond through the internet. The Census Bureau is investigating several mailing strategies to prompt recipients to self-respond. It is suspected that the choice of mailing strategy affects the distribution of call volumes to the Census Bureau's telephone helplines. For staffing purposes, more uniform call volumes throughout the week are desirable. In this work, we consider formal statistical methods to compare call volumes resulting from several recent experiments, and determine whether one mailing strategy yields a more uniform call distribution than the others.
|
Authors who are presenting talks have a * after their name.