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

Modeling censored-in-the-middle condom use data.

S L Hershberger1, D G Fisher, G L Reynolds

  • 1Psychology Department, California State University, Long Beach, California 90840, USA. scotth@csulb.edu

AIDS Care
|July 23, 2005
PubMed
Summary

This study introduces Tobit regression to model condom use data, addressing issues like bimodality. Findings show each additional drug injecting sex partner reduces condom use probability by about 1%.

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

Replication Problems of Substance Abuser MMPI Cluster Types.

Multivariate behavioral research·2016
Same author

Studies on the leaf of Amaranthus retroflexus (Amaranthaceae): ultrastructure, plasmodesmatal frequency, and solute concentration in relation to phloem loading.

Planta·2013
Same author

Ultrastructure, plasmodesmatal frequency, and solute concentration in green areas of variegated Coleus blumei Benth. leaves.

Planta·2013
Same author

Isolation and identification of reaction products arising from the chlorination of cytosine in aqueous solution.

Environmental science & technology·2011
Same author

Reliability, sensitivity and specificity of self-report of HIV test results.

AIDS care·2007
Same author

Social support networks of lesbian, gay, and bisexual adults 60 years of age and older.

The journals of gerontology. Series B, Psychological sciences and social sciences·2002

Area of Science:

  • Public Health
  • Biostatistics
  • Epidemiology

Background:

  • HIV prevention programs often aim to increase condom use.
  • Condom use is typically measured as a proportion, which can lead to problematic bimodal distributions due to many 0% and 100% responses.
  • These censored-in-the-middle distributions pose statistical challenges for analysis.

Purpose of the Study:

  • To demonstrate the utility of Tobit regression for modeling censored condom use data.
  • To address the statistical limitations of traditional proportion analysis in HIV prevention research.
  • To provide a more accurate statistical approach for understanding factors influencing condom use.

Main Methods:

  • The study employed Tobit regression, a statistical model designed for censored data.
  • This method transforms observed condom use proportions into latent variable scores.
  • The latent variable scores were then modeled using explanatory variables, specifically the number of drug injecting sex partners.

Main Results:

  • Data from the National Institute on Drug Abuse Cooperative Agreement for HIV/AIDS Community-Based Outreach/Intervention Research program were analyzed.
  • A statistically significant inverse relationship was found between the number of drug injecting sex partners and condom use.
  • For each additional drug injecting sex partner, the probability of condom use decreased by approximately 1%.

Conclusions:

  • Tobit regression offers a valuable method for analyzing censored condom use data in HIV prevention research.
  • The findings highlight a concerning trend where increased numbers of drug injecting sex partners are associated with reduced condom use.
  • This underscores the need for targeted interventions to promote consistent condom use among high-risk populations.

Related Experiment Videos