Work

A ZIP model accounting for response bias in randomized response

Year: 2007

Type: conference-paper

Abstract: Randomized response (RR) is an interview technique that ensures confidentiality when sensitive questions are asked.In RR the answer to a sensitive question is partly determined by a randomizing device.Respondent may nevertheless feel uncomfortable with the RR design and give the least sensitive response, irrespective of the outcome of the randomizing device.This kind of self-protective response behavior yields biased prevalence estimates.In this paper we present the zero-inflated Poisson model to account for self-protective response bias in the presence of an RR variable with multiple, ordered response categories.An example from a Dutch social security survey is provided.

Source: Utrecht University Repository (Utrecht University)

Authors: Maarten Cruyff, Ulf Böckenholt, P.G.M. van der Heijden

Language: English

Topic: Survey Sampling and Estimation Techniques

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W1608749007

FWCI:

Cites: 6

Cited by:

Related to: 10