Sample size determination for the non-randomised triangular model for sensitive questions in a survey

Guo Liang Tian, Man Lai Tang, Zhenqiu Liu, Ming Tan, Nian Sheng Tang

Research output: Contribution to journalReview article

11 Citations (Scopus)

Abstract

Sample size determination is an essential component in public health survey designs on sensitive topics (e.g. drug abuse, homosexuality, induced abortions and pre or extramarital sex). Recently, non-randomised models have been shown to be an efficient and cost effective design when comparing with randomised response models. However, sample size formulae for such non-randomised designs are not yet available. In this article, we derive sample size formulae for the non-randomised triangular design based on the power analysis approach. We first consider the one-sample problem. Power functions and their corresponding sample size formulae for the one- and two-sided tests based on the large-sample normal approximation are derived. The performance of the sample size formulae is evaluated in terms of (i) the accuracy of the power values based on the estimated sample sizes and (ii) the sample size ratio of the non-randomised triangular design and the design of direct questioning (DDQ). We also numerically compare the sample sizes required for the randomised Warner design with those required for the DDQ and the non-randomised triangular design. Theoretical justification is provided. Furthermore, we extend the one-sample problem to the two-sample problem. An example based on an induced abortion study in Taiwan is presented to illustrate the proposed methods.

Original languageEnglish (US)
Pages (from-to)159-173
Number of pages15
JournalStatistical Methods in Medical Research
Volume20
Issue number3
DOIs
StatePublished - Jun 1 2011

Fingerprint

Sample Size Determination
Sample Size
Triangular
Induced Abortion
Model
Two-sided test
Survey Design
Randomized Response
Two-sample Problem
Essential Component
Power Analysis
Design
Surveys and Questionnaires
Normal Approximation
Homosexuality
Public Health
Power Function
Taiwan
Health Surveys
Justification

All Science Journal Classification (ASJC) codes

  • Epidemiology
  • Statistics and Probability
  • Health Information Management

Cite this

Tian, Guo Liang ; Tang, Man Lai ; Liu, Zhenqiu ; Tan, Ming ; Tang, Nian Sheng. / Sample size determination for the non-randomised triangular model for sensitive questions in a survey. In: Statistical Methods in Medical Research. 2011 ; Vol. 20, No. 3. pp. 159-173.
@article{eb1e509fe41b45e7beafb5b50e5a7f3f,
title = "Sample size determination for the non-randomised triangular model for sensitive questions in a survey",
abstract = "Sample size determination is an essential component in public health survey designs on sensitive topics (e.g. drug abuse, homosexuality, induced abortions and pre or extramarital sex). Recently, non-randomised models have been shown to be an efficient and cost effective design when comparing with randomised response models. However, sample size formulae for such non-randomised designs are not yet available. In this article, we derive sample size formulae for the non-randomised triangular design based on the power analysis approach. We first consider the one-sample problem. Power functions and their corresponding sample size formulae for the one- and two-sided tests based on the large-sample normal approximation are derived. The performance of the sample size formulae is evaluated in terms of (i) the accuracy of the power values based on the estimated sample sizes and (ii) the sample size ratio of the non-randomised triangular design and the design of direct questioning (DDQ). We also numerically compare the sample sizes required for the randomised Warner design with those required for the DDQ and the non-randomised triangular design. Theoretical justification is provided. Furthermore, we extend the one-sample problem to the two-sample problem. An example based on an induced abortion study in Taiwan is presented to illustrate the proposed methods.",
author = "Tian, {Guo Liang} and Tang, {Man Lai} and Zhenqiu Liu and Ming Tan and Tang, {Nian Sheng}",
year = "2011",
month = "6",
day = "1",
doi = "10.1177/0962280208099444",
language = "English (US)",
volume = "20",
pages = "159--173",
journal = "Statistical Methods in Medical Research",
issn = "0962-2802",
publisher = "SAGE Publications Ltd",
number = "3",

}

Sample size determination for the non-randomised triangular model for sensitive questions in a survey. / Tian, Guo Liang; Tang, Man Lai; Liu, Zhenqiu; Tan, Ming; Tang, Nian Sheng.

In: Statistical Methods in Medical Research, Vol. 20, No. 3, 01.06.2011, p. 159-173.

Research output: Contribution to journalReview article

TY - JOUR

T1 - Sample size determination for the non-randomised triangular model for sensitive questions in a survey

AU - Tian, Guo Liang

AU - Tang, Man Lai

AU - Liu, Zhenqiu

AU - Tan, Ming

AU - Tang, Nian Sheng

PY - 2011/6/1

Y1 - 2011/6/1

N2 - Sample size determination is an essential component in public health survey designs on sensitive topics (e.g. drug abuse, homosexuality, induced abortions and pre or extramarital sex). Recently, non-randomised models have been shown to be an efficient and cost effective design when comparing with randomised response models. However, sample size formulae for such non-randomised designs are not yet available. In this article, we derive sample size formulae for the non-randomised triangular design based on the power analysis approach. We first consider the one-sample problem. Power functions and their corresponding sample size formulae for the one- and two-sided tests based on the large-sample normal approximation are derived. The performance of the sample size formulae is evaluated in terms of (i) the accuracy of the power values based on the estimated sample sizes and (ii) the sample size ratio of the non-randomised triangular design and the design of direct questioning (DDQ). We also numerically compare the sample sizes required for the randomised Warner design with those required for the DDQ and the non-randomised triangular design. Theoretical justification is provided. Furthermore, we extend the one-sample problem to the two-sample problem. An example based on an induced abortion study in Taiwan is presented to illustrate the proposed methods.

AB - Sample size determination is an essential component in public health survey designs on sensitive topics (e.g. drug abuse, homosexuality, induced abortions and pre or extramarital sex). Recently, non-randomised models have been shown to be an efficient and cost effective design when comparing with randomised response models. However, sample size formulae for such non-randomised designs are not yet available. In this article, we derive sample size formulae for the non-randomised triangular design based on the power analysis approach. We first consider the one-sample problem. Power functions and their corresponding sample size formulae for the one- and two-sided tests based on the large-sample normal approximation are derived. The performance of the sample size formulae is evaluated in terms of (i) the accuracy of the power values based on the estimated sample sizes and (ii) the sample size ratio of the non-randomised triangular design and the design of direct questioning (DDQ). We also numerically compare the sample sizes required for the randomised Warner design with those required for the DDQ and the non-randomised triangular design. Theoretical justification is provided. Furthermore, we extend the one-sample problem to the two-sample problem. An example based on an induced abortion study in Taiwan is presented to illustrate the proposed methods.

UR - http://www.scopus.com/inward/record.url?scp=80051866858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051866858&partnerID=8YFLogxK

U2 - 10.1177/0962280208099444

DO - 10.1177/0962280208099444

M3 - Review article

C2 - 19221169

AN - SCOPUS:80051866858

VL - 20

SP - 159

EP - 173

JO - Statistical Methods in Medical Research

JF - Statistical Methods in Medical Research

SN - 0962-2802

IS - 3

ER -