Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A new non-randomized model for analysing sensitive questions with binary outcomes.

Guo-Liang Tian1, Jun-Wu Yu, Man-Lai Tang

  • 1Division of Biostatistics, University of Maryland Greenebaum Cancer Center, 22 South Greene Street, Baltimore, MD 21201, USA.

Statistics in Medicine
|March 14, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Spatially Correlated Analysis of Infectious Disease Outcomes Based on Bayesian Functional Hierarchical Models.

Statistics in medicine·2026
Same author

Universal Rapid Machine Learning Models for Predicting Unconvoluted and Convoluted X-ray Absorption Spectra.

The journal of physical chemistry. A·2026
Same author

Assessing interactive causes of an occurred outcome due to two binary exposures.

Biometrics·2026
Same author

EEG biomarkers can predict early-stage Alzheimer's disease and correlate with intracerebral pathology: a multimodal machine learning study.

Alzheimer's research & therapy·2026
Same author

Direct arylation polymerization of electron-rich arenes with polar-group tolerance enabled by ligand-coordination tuning.

Chemical science·2026
Same author

Effects of 40-Hz transcranial alternating current stimulation on cognition and neural markers in Alzheimer's disease: a randomized, sham-controlled trial.

Alzheimer's research & therapy·2026

This study introduces a privacy-preserving model for sensitive survey questions, allowing respondents to answer a single non-sensitive question. This method enhances data privacy and simplifies data collection in surveys.

Area of Science:

  • Statistics
  • Survey Methodology
  • Biostatistics

Background:

  • Assessing associations with sensitive questions poses privacy challenges.
  • Existing methods may require direct answers to sensitive questions or use randomizing devices.
  • There is a need for privacy-preserving, non-randomized models in survey research.

Purpose of the Study:

  • To propose a novel non-randomized statistical model for analyzing associations involving sensitive questions.
  • To enhance respondent privacy by replacing direct sensitive questions with a single non-sensitive question.
  • To provide methods for estimating and testing associations between binary variables under the new model.

Main Methods:

  • Development of a non-randomized model for sensitive question analysis.

Related Experiment Videos

  • Derivation of constrained maximum likelihood estimates (MLEs) for cell probabilities and odds ratios using the Expectation-Maximization (EM) algorithm.
  • Application of the bootstrap approach for standard error estimation.
  • Development of likelihood ratio and chi-squared tests for association.

    • Main Results:

    • The proposed model effectively protects respondent privacy while avoiding randomizing devices.
    • Constrained MLEs and bootstrap standard errors are derived for key parameters.
    • Statistical tests for association are developed and evaluated.
    • Simulations assess the performance of the tests and the impact of sample size on estimate validity.

    Conclusions:

    • The new model offers a viable alternative for studying sensitive topics, balancing privacy and data integrity.
    • The EM algorithm and bootstrap methods provide robust estimation and inference.
    • The methodology is applicable to both face-to-face and mail questionnaire surveys, demonstrated with an AIDS study dataset.