Using mixture models to detect sex bias in health outcomes in Bangladesh

Jonathan J. Morduch, Hal S. Stern

Research output: Contribution to journalArticle

Abstract

Many interesting economic hypotheses entail differences in behaviors of groups within a population, but analyses of pooled samples shed only partial light on underlying segmentations. Finite mixture models are considered as an alternative to methods based on pooling. Robustness checks using t-regressions and a Bayesian analogue to the likelihood ratio test for model evaluation are developed. The methodology is used to investigate pro-son bias in child health outcomes in Bangladesh. While regression analysis on the entire sample appears to wash out evidence of bias, the mixture models reveal systematic girl-boy differences in health outcomes.

Original languageEnglish (US)
Pages (from-to)259-276
Number of pages18
JournalJournal of Econometrics
Volume77
Issue number1
StatePublished - Mar 1997

Fingerprint

Mixture Model
Health
Finite Mixture Models
Model Evaluation
Pooling
Likelihood Ratio Test
Regression Analysis
Segmentation
Regression
Entire
Economics
Robustness
Analogue
Partial
Methodology
Alternatives
Health outcomes
Mixture model
Bangladesh
Evidence

Keywords

  • Bangladesh
  • Gender bias
  • Health production
  • Mixture model
  • Switching regression

ASJC Scopus subject areas

  • Economics and Econometrics
  • Finance
  • Statistics and Probability

Cite this

Using mixture models to detect sex bias in health outcomes in Bangladesh. / Morduch, Jonathan J.; Stern, Hal S.

In: Journal of Econometrics, Vol. 77, No. 1, 03.1997, p. 259-276.

Research output: Contribution to journalArticle

@article{eafc5b1a98e740009d6076f2a47898b2,
title = "Using mixture models to detect sex bias in health outcomes in Bangladesh",
abstract = "Many interesting economic hypotheses entail differences in behaviors of groups within a population, but analyses of pooled samples shed only partial light on underlying segmentations. Finite mixture models are considered as an alternative to methods based on pooling. Robustness checks using t-regressions and a Bayesian analogue to the likelihood ratio test for model evaluation are developed. The methodology is used to investigate pro-son bias in child health outcomes in Bangladesh. While regression analysis on the entire sample appears to wash out evidence of bias, the mixture models reveal systematic girl-boy differences in health outcomes.",
keywords = "Bangladesh, Gender bias, Health production, Mixture model, Switching regression",
author = "Morduch, {Jonathan J.} and Stern, {Hal S.}",
year = "1997",
month = "3",
language = "English (US)",
volume = "77",
pages = "259--276",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "1",

}

TY - JOUR

T1 - Using mixture models to detect sex bias in health outcomes in Bangladesh

AU - Morduch, Jonathan J.

AU - Stern, Hal S.

PY - 1997/3

Y1 - 1997/3

N2 - Many interesting economic hypotheses entail differences in behaviors of groups within a population, but analyses of pooled samples shed only partial light on underlying segmentations. Finite mixture models are considered as an alternative to methods based on pooling. Robustness checks using t-regressions and a Bayesian analogue to the likelihood ratio test for model evaluation are developed. The methodology is used to investigate pro-son bias in child health outcomes in Bangladesh. While regression analysis on the entire sample appears to wash out evidence of bias, the mixture models reveal systematic girl-boy differences in health outcomes.

AB - Many interesting economic hypotheses entail differences in behaviors of groups within a population, but analyses of pooled samples shed only partial light on underlying segmentations. Finite mixture models are considered as an alternative to methods based on pooling. Robustness checks using t-regressions and a Bayesian analogue to the likelihood ratio test for model evaluation are developed. The methodology is used to investigate pro-son bias in child health outcomes in Bangladesh. While regression analysis on the entire sample appears to wash out evidence of bias, the mixture models reveal systematic girl-boy differences in health outcomes.

KW - Bangladesh

KW - Gender bias

KW - Health production

KW - Mixture model

KW - Switching regression

UR - http://www.scopus.com/inward/record.url?scp=0000824892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0000824892&partnerID=8YFLogxK

M3 - Article

VL - 77

SP - 259

EP - 276

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 1

ER -