The randomized response log linear model as a composite link model
The randomized response log linear model as a composite link model
In randomized response (RR) designs, misclassification is used to protect the privacy of respondents when sensitive questions are asked. A generalized linear model with a composite link function is presented to formulate log linear models that take the RR design into account. The approach is extended to model the situation where some respondents do not follow the instructions of the RR design. For example, if there are three binary RR variables with regard to practicing fraud, the 2 × 2 × 2 cross-classification of the true answers is latent due to the misclassification. Using composite link functions, log linear models can be specified for the latent table to investigate possible association between the variables. Fast iteratively re-weighted least squares algorithms are presented.
57-67
van den Hout, Ardo
8df0fd5b-6578-4a1f-ba11-790b56e8af55
Gilchrist, Robert
8f0a8e1d-ff42-4d2a-9cef-9b94ac0c7aef
van der Heijden, Peter G.M.
85157917-3b33-4683-81be-713f987fd612
April 2010
van den Hout, Ardo
8df0fd5b-6578-4a1f-ba11-790b56e8af55
Gilchrist, Robert
8f0a8e1d-ff42-4d2a-9cef-9b94ac0c7aef
van der Heijden, Peter G.M.
85157917-3b33-4683-81be-713f987fd612
van den Hout, Ardo, Gilchrist, Robert and van der Heijden, Peter G.M.
(2010)
The randomized response log linear model as a composite link model.
Statistical Modelling, 10 (1), .
(doi:10.1177/1471082X0801000104).
Abstract
In randomized response (RR) designs, misclassification is used to protect the privacy of respondents when sensitive questions are asked. A generalized linear model with a composite link function is presented to formulate log linear models that take the RR design into account. The approach is extended to model the situation where some respondents do not follow the instructions of the RR design. For example, if there are three binary RR variables with regard to practicing fraud, the 2 × 2 × 2 cross-classification of the true answers is latent due to the misclassification. Using composite link functions, log linear models can be specified for the latent table to investigate possible association between the variables. Fast iteratively re-weighted least squares algorithms are presented.
This record has no associated files available for download.
More information
Published date: April 2010
Organisations:
Statistical Sciences Research Institute
Identifiers
Local EPrints ID: 344664
URI: http://eprints.soton.ac.uk/id/eprint/344664
ISSN: 1471-082X
PURE UUID: 8d3e6553-9cd9-4c10-b7cb-30d5e3ca62d9
Catalogue record
Date deposited: 26 Oct 2012 11:24
Last modified: 15 Mar 2024 03:46
Export record
Altmetrics
Contributors
Author:
Ardo van den Hout
Author:
Robert Gilchrist
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