|
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 - #304340 |
|
Title:
|
Nonresponse Bias: Telephone Point-of-Purchase Survey
|
|
Author(s):
|
Madeleine Saxton*+ and Patrick Falwell
|
|
Companies:
|
Bureau of Labor Statistics and Bureau of Labor Statistics
|
|
Address:
|
2 Massachusetts Ave., NE, Washington, DC, 20212,
|
|
Keywords:
|
non-response bias ; random digit dialed ; telephone surveys ; weighting
|
|
Abstract:
|
The Telephone Point-of-Purchase Survey (TPOPS) is a random-digit-dialed, computer-assisted-telephone-interview survey that provides the Consumer Price Index with a sampling frame of retail establishments for the most of items priced in the index. TPOPS is a rotating panel survey administered across the country, in only households with residential landline telephone numbers. TPOPS response rates have fallen precipitously from an average of 70% in the late 1990s to about 45% more recently. While the primary concern with non-response is the missing cell-phone only population, other demographic cohorts may be underrepresented, also. This paper discusses the results of a TPOPS non-response bias analysis. Spending patterns of underrepresented populations are compared to the sampled landline population, and methods which can be used to mitigate non-response in the short-term are recommended.
|
