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

[Estimates from a complex survey].

Maria Helena de Sousa1, Nilza Nunes da Silva

  • 1Centro de Pesquisas Materno-Infantis de Campinas, Campinas, SP, Brasil. mhsousa@cemicamp.org.br

Revista De Saude Publica
|October 22, 2003
PubMed
Summary

This study assessed the 1996 Brazilian National Survey on Demography and Health data. Cluster sampling affected estimate precision for some variables, while weighting had no significant impact.

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

Compensatory sweating after thoracoscopic sympathectomy for primary focal hyperhidrosis: a series of 820 cases.

Interdisciplinary cardiovascular and thoracic surgery·2025
Same author

Mapping the learning styles of medical students in Brazil.

BMC medical education·2024
Same author

Perception and knowledge of pharmacogenetics among Brazilian psychiatrists.

Psychiatry research·2021
Same author

Continuation Rates of the 52-mg Levonorgestrel-releasing Intrauterine System according to the Primary Reason for its Use.

Revista brasileira de ginecologia e obstetricia : revista da Federacao Brasileira das Sociedades de Ginecologia e Obstetricia·2021
Same author

10 Years of SABE Study: background, methodology and organization of the study.

Revista brasileira de epidemiologia = Brazilian journal of epidemiology·2019
Same author

Cardiometabolic risk markers of normal weight and excess body weight in Brazilian adolescents.

Applied physiology, nutrition, and metabolism = Physiologie appliquee, nutrition et metabolisme·2016

Area of Science:

  • Demography
  • Public Health
  • Survey Methodology

Background:

  • The 1996 Brazilian National Survey on Demography and Health (BNDS) is a crucial data source for understanding population health.
  • Evaluating the impact of survey design elements is essential for accurate data interpretation.

Purpose of the Study:

  • To evaluate the impact of sampling design and weighting on data from the 1996 Brazilian National Survey on Demography and Health.
  • To assess the precision and validity of estimates derived from the survey.

Main Methods:

  • Secondary data analysis of 1,355 interviewed women from São Paulo.
  • Utilized the National Survey of Household Sampling (PNAD) design, with municipalities as primary sampling units.
  • Calculated ratio estimators and Taylor's approximation for variance, assessing confidence intervals, design effects (Deff), and biases.

Main Results:

  • Prevalence estimate differences were within 10%, and confidence interval ranges varied by less than 20%.
  • Condom use and hormone injection variables exhibited design effects greater than 1.5 and biases exceeding 0.20.
  • Cluster sampling impacted the precision of estimates for two out of six variables.

Conclusions:

  • Cluster sampling demonstrably affected the precision of estimates for specific variables in the 1996 BNDS.
  • Weighting procedures applied in the analysis did not yield statistically significant impacts on the data's validity.

Related Experiment Videos