|
Activity Number:
|
284
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #305793 |
|
Title:
|
Effectiveness of Nesting Age, Race, and Gender for Weighting Estimates of Radio Listening
|
|
Author(s):
|
Kelly Dixon*+
|
|
Companies:
|
Arbitron, Inc.
|
|
Address:
|
9705 Patuxent Woods Drive, Columbia, MD, 21046,
|
|
Keywords:
|
nesting ; weighting ; radio listening estimates
|
|
Abstract:
|
Three key variables that explain radio listening variation among panelists in Arbitron's radio surveys are age, race and gender. Users of Arbitron data, primarily radio broadcasters and advertising agencies, require Arbitron to produce a variety of estimates for certain breakouts of these three variables, an example being estimates of radio listening for Black Males 18--34. Because these three characteristics are so critical to producing, understanding, and using the survey data we conducted a study to determine if it was better to weight the survey data separately by these variables, or if some form of nesting during weighting would be best. We used a regression analysis and a mean square error analysis to assess the effectives of age, race and gender nesting for both broad and narrow demographic estimates of radio listening.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2009 program |
