|
Activity Number:
|
299
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, August 14, 2002 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
SSC
|
| Abstract - #300170 |
|
Title:
|
Additive Models in Survey Sampling
|
|
Author(s):
|
Jamie Stafford*+ and Hugh Chipman and David Bellhouse
|
|
Affiliation(s):
|
University of Toronto and University of Waterloo and University of Western Ontario
|
|
Address:
|
McMurrich Building, Room 309, Faculty of Medicine, Toronto , Ontario, M5S 1A8, Canada
|
|
Keywords:
|
|
|
Abstract:
|
Survey sampling is a statistical domain which has been slow to take advantage of flexible regression methods such as scatterplot smoothing and additive models. To make these methods more accessible, this paper introduces techniques that account for the complex survey structure of the data. We focus on smooth regression with a normal error model. This model is complicated by the survey design, which could include stratification, cluster sampling, and other complex survey designs. The presence of tied covariate values results in the smoothing of binned means. The estimation of smoothes is seen to depend on the sampling design only via the sampling weights, meaning that standard software can be used for estimation. Inference for these curves is more challenging, due to correlations induced by the sampling design. We propose tests which account for the sampling design. Illustrative examples are given using the Ontario health survey.
|
- 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 2002 program |
