Estimation of an indicator of the representativeness of survey response
Estimation of an indicator of the representativeness of survey response
Nonresponse is a major source of estimation error in sample surveys. The response rate is widely used to measure the quality of a sample survey associated with nonresponse. It is, however, inadequate as an indicator because of its limited relation with nonresponse bias. Schouten et al. (2009) proposed an alternative indicator, which they refer to as an indicator of representativeness or R-indicator. This indicator measures the variability of the probabilities of response for units in the population. This paper develops methods for the estimation of this R-indicator assuming that values of a set of auxiliary variables are observed for both respondents and nonrespondents. In particular, we consider the bias of point estimators proposed by Schouten et al. (2009) and propose bias adjustments and linearization variance estimators. The proposed procedures are evaluated in a simulation study and their use is illustrated in an application to two business surveys at Statistics Netherlands.
Southampton Statistical Sciences Research Institute, University of Southampton
Shlomo, Natalie
e749febc-b7b9-4017-be48-96d59dd03215
Skinner, Chris
dec5ef40-49ef-492a-8a1d-eb8c6315b8ce
Schouten, Barry
69cdfe11-7450-4728-ae34-51755985ab88
4 November 2009
Shlomo, Natalie
e749febc-b7b9-4017-be48-96d59dd03215
Skinner, Chris
dec5ef40-49ef-492a-8a1d-eb8c6315b8ce
Schouten, Barry
69cdfe11-7450-4728-ae34-51755985ab88
Shlomo, Natalie, Skinner, Chris and Schouten, Barry
(2009)
Estimation of an indicator of the representativeness of survey response
(S3RI Methodology Working Papers)
Southampton, UK.
Southampton Statistical Sciences Research Institute, University of Southampton
33pp.
Record type:
Monograph
(Working Paper)
Abstract
Nonresponse is a major source of estimation error in sample surveys. The response rate is widely used to measure the quality of a sample survey associated with nonresponse. It is, however, inadequate as an indicator because of its limited relation with nonresponse bias. Schouten et al. (2009) proposed an alternative indicator, which they refer to as an indicator of representativeness or R-indicator. This indicator measures the variability of the probabilities of response for units in the population. This paper develops methods for the estimation of this R-indicator assuming that values of a set of auxiliary variables are observed for both respondents and nonrespondents. In particular, we consider the bias of point estimators proposed by Schouten et al. (2009) and propose bias adjustments and linearization variance estimators. The proposed procedures are evaluated in a simulation study and their use is illustrated in an application to two business surveys at Statistics Netherlands.
Text
s3ri-workingpaper-M09-18.pdf
- Other
More information
Published date: 4 November 2009
Identifiers
Local EPrints ID: 69455
URI: http://eprints.soton.ac.uk/id/eprint/69455
PURE UUID: 976e743c-74da-4d95-95b6-874e3b9e1b27
Catalogue record
Date deposited: 17 Nov 2009
Last modified: 13 Mar 2024 19:33
Export record
Contributors
Author:
Natalie Shlomo
Author:
Chris Skinner
Author:
Barry Schouten
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics