A GEE-type approach to untangle structural and random zeros in predictors

Abstract

Count outcomes with excessive zeros are common in behavioral and social studies, and zero-inflated count models such as zero-inflated Poisson (ZIP) and zero-inflated Negative Binomial (ZINB) can be applied when such zero-inflated count data are used as response variable. However, when the zero-inflated count data are used as predictors, ignoring the difference of structural and random zeros can result in biased estimates. In this paper, a generalized estimating equation (GEE)-type mixture model is proposed to jointly model the response of interest and the zero-inflated count predictors. Simulation studies show that the proposed method performs well for practical settings and is more robust for model misspecification than the likelihood-based approach. A case study is also provided for illustration.

Keywords

Generalized estimating equations mixture model structural zeros zero-inflated explanatory variables zero-inflated Poisson

Get full access to this article

View all access options for this article.

References

Burger

Van Oort

Linders

G-J

. On the specification of the gravity model of trade: zeros, excess zeros and zero-inflated estimation. Spatial Economic Analys 2009; 4: 167–190.

Zorn

CJW

. An analytic and empirical examination of zero-inflated and hurdle Poisson specifications. Sociol Meth Res 1998; 26: 368–400.

Clark

. Can strategic interaction divert diversionary behavior? a model of us conflict propensity. J Politics 2003; 65: 1013–1039.

Lord

Washington

Ivan

. Poisson, Poisson-gamma and zero-inflated regression models of motor vehicle crashes: balancing statistical fit and theory. Accident Analys Prevent 2005; 37: 35–46.

Horton

Bebchuk

Jones

, et al. Goodness-of-fit for GEE: an example with mental health service utilization. Stat Med 1999; 18: 213–222.

Pardini

White

Stouthamer-Loeber

. Early adolescent psychopathology as a predictor of alcohol use disorders by young adulthood. Drug Alcohol Depend 2007; 88: S38–S49.

Neal

Sugarman

Hustad

JTP

, et al. It's all fun and games... or is it? Collegiate sporting events and celebratory drinking. J Studies Alcohol Drugs 2005; 66: 291–294.

Hagger-Johnson

Bewick

Conner

, et al. Alcohol, conscientiousness and event-level condom use. Br J Health Psychol 2011; 16: 828–845.

Connor

Kypri

Bell

, et al. Alcohol outlet density, levels of drinking and alcohol-related harm in New Zealand: a national study. J Epidemiol Commun Health 2011; 65: 841–846.

10.

Buu

Johnson

, et al. New variable selection methods for zero-inflated count data with applications to the substance abuse field. Stat Med 2011; 30: 2326–2340.

11.

Fernandez

Wood

Laforge

, et al. Randomized trials of alcohol-use interventions with college students and their parents: lessons from the transitions project. Clin Trial 2011; 8: 205–213.

12.

Cranford

Zucker

Jester

, et al. Parental alcohol involvement and adolescent alcohol expectancies predict alcohol involvement in male adolescents. Psychol Addict Behav 2010; 24: 386–396.

13.

Hildebrandt

McCrady

Epstein

, et al. When should clinicians switch treatments? An application of signal detection theory to two treatments for women with alcohol use disorders. Behav Res Ther 2010; 48: 524–530.

14.

Hernandez-Avila

Song

Kuo

, et al. Targeted versus daily naltrexone: secondary analysis of effects on average daily drinking. Alcohol: Clin Exp Res 2006; 30: 860–865.

15.

Hall

. Zero-inflated Poisson and binomial regression with random effects: a case study. Biometrics 2000; 56: 1030–1039.

16.

Hall

Zhang

. Marginal models for zero inflated clustered data. Stat Model 2004; 4: 161–180.

17.

Chen

Tang

, et al. Distribution-free models for longitudinal count responses with overdispersion and structural zeros. Stat Med 2013; 32: 2390–405.

18.

Tang

. Applied categorical and count data analysis, Boca Raton, FL: Chapman & Hall/CRC, 2012.

19.

Dean

Lawless

. Tests for detecting overdispersion in Poisson regression models. J Am Stat Assoc 1989; 84: 467–472.

20.

Kowalski

. Modern applied U-statistics, Hoboken, NJ: Wiley-Interscience, 2008. Wiley Series in Probability and Statistics.

21.

Xia

Morrison-Beedy

, et al. Modeling count outcomes from HIV risk reduction interventions: a comparison of competing statistical models for count responses. AIDS Res Treat 2012; 25: 1–11. .

22.

Crits-Christoph

Gallop

Sadicario

, et al. Predictors and moderators of outcomes of HIV/STD sex risk reduction interventions in substance abuse treatment programs: a pooled analysis of two randomized controlled trials. Substance Abuse Treat Prevent Policy 2014; 9: 3.

23.

Wang

Crits-Christoph

, et al. On the implication of structural zeros as independent variables in regression analysis: applications to alcohol research. J Data Sci 2014; 12: 439–460.

24.

Tang

Wang

, et al. Untangle the structural and random zeros in statistical modelings. J Appl Stat 2018; 45: 1714–1733.

25.

Tang

Chen

, et al. On performance of parametric and distribution-free models for zero-inflated and over-dispersed count responses. Stat Med 2015; 34: 3235–3245.

26.

Wilde

McMahon

McDonald

, et al. Self-management intervention for long-term indwelling urinary catheter users: randomized clinical trial. Nurs Res 2015; 64: 24–34.

27.

He H, Zhang H, Ye P, et al. A test of inflated zeros for poisson regression models. Stat Meth Med Res (in press).

28.

Zhang

Tian

G-L

K-W

. Properties of the zero-and-one inflated poisson distribution and likelihood-based inference methods. Stat Interface 2016; 9: 11–32.

29.

Bagozzi

Mukherjee

. A mixture model for middle category inflation in ordered survey responses. Political Analys 2012; 20: 369–386.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.19 MB