Distribution-free estimation of zero-inflated models with unobserved heterogeneity

Rodica Gilles, Seik Kim

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper presents a quasi-conditional likelihood method for the consistent estimation of both continuous and count data models with excess zeros and unobserved individual heterogeneity when the true data generating process is unknown. Monte Carlo simulation studies show that our zero-inflated quasi-conditional maximum likelihood (ZI-QCML) estimator outperforms other methods and is robust to distributional misspecifications. We apply the ZI-QCML estimator to analyze the frequency of doctor visits.

Original languageEnglish
Pages (from-to)1532-1542
Number of pages11
JournalStatistical Methods in Medical Research
Volume26
Issue number3
DOIs
Publication statusPublished - 2017 Jun 1

Fingerprint

Unobserved Heterogeneity
Distribution-free
Conditional Maximum Likelihood
Maximum Likelihood Estimator
Zero
Conditional Likelihood
Consistent Estimation
Misspecification
Count Data
Likelihood Methods
Data Model
Excess
Monte Carlo Simulation
Simulation Study
Model
Unknown

Keywords

  • Excess zeros
  • nonnegative data
  • quasi-likelihood estimation
  • robust estimation
  • zero inflation

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability
  • Health Information Management

Cite this

Distribution-free estimation of zero-inflated models with unobserved heterogeneity. / Gilles, Rodica; Kim, Seik.

In: Statistical Methods in Medical Research, Vol. 26, No. 3, 01.06.2017, p. 1532-1542.

Research output: Contribution to journalArticle

@article{6688bec62dca42f6a9350ac34ebcc1fe,
title = "Distribution-free estimation of zero-inflated models with unobserved heterogeneity",
abstract = "This paper presents a quasi-conditional likelihood method for the consistent estimation of both continuous and count data models with excess zeros and unobserved individual heterogeneity when the true data generating process is unknown. Monte Carlo simulation studies show that our zero-inflated quasi-conditional maximum likelihood (ZI-QCML) estimator outperforms other methods and is robust to distributional misspecifications. We apply the ZI-QCML estimator to analyze the frequency of doctor visits.",
keywords = "Excess zeros, nonnegative data, quasi-likelihood estimation, robust estimation, zero inflation",
author = "Rodica Gilles and Seik Kim",
year = "2017",
month = "6",
day = "1",
doi = "10.1177/0962280215588940",
language = "English",
volume = "26",
pages = "1532--1542",
journal = "Statistical Methods in Medical Research",
issn = "0962-2802",
publisher = "SAGE Publications Ltd",
number = "3",

}

TY - JOUR

T1 - Distribution-free estimation of zero-inflated models with unobserved heterogeneity

AU - Gilles, Rodica

AU - Kim, Seik

PY - 2017/6/1

Y1 - 2017/6/1

N2 - This paper presents a quasi-conditional likelihood method for the consistent estimation of both continuous and count data models with excess zeros and unobserved individual heterogeneity when the true data generating process is unknown. Monte Carlo simulation studies show that our zero-inflated quasi-conditional maximum likelihood (ZI-QCML) estimator outperforms other methods and is robust to distributional misspecifications. We apply the ZI-QCML estimator to analyze the frequency of doctor visits.

AB - This paper presents a quasi-conditional likelihood method for the consistent estimation of both continuous and count data models with excess zeros and unobserved individual heterogeneity when the true data generating process is unknown. Monte Carlo simulation studies show that our zero-inflated quasi-conditional maximum likelihood (ZI-QCML) estimator outperforms other methods and is robust to distributional misspecifications. We apply the ZI-QCML estimator to analyze the frequency of doctor visits.

KW - Excess zeros

KW - nonnegative data

KW - quasi-likelihood estimation

KW - robust estimation

KW - zero inflation

UR - http://www.scopus.com/inward/record.url?scp=85020713139&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020713139&partnerID=8YFLogxK

U2 - 10.1177/0962280215588940

DO - 10.1177/0962280215588940

M3 - Article

C2 - 26113384

AN - SCOPUS:85020713139

VL - 26

SP - 1532

EP - 1542

JO - Statistical Methods in Medical Research

JF - Statistical Methods in Medical Research

SN - 0962-2802

IS - 3

ER -