Are marginalized two-part models superior to non-marginalized two-part models for count data with excess zeroes? Estimation of marginal effects, model misspecification, and model selection

Xueyan Liu; Bo Zhang; Li Tang; Zhiwei Zhang; Ning Zhang; Jeroan J. Allison; Deo Kumar Srivastava; Hui Zhang

doi:10.1007/s10742-018-0183-6

Are marginalized two-part models superior to non-marginalized two-part models for count data with excess zeroes? Estimation of marginal effects, model misspecification, and model selection

Xueyan Liu, Bo Zhang, Li Tang, Zhiwei Zhang, Ning Zhang, Jeroan J. Allison, Deo Kumar Srivastava, Hui Zhang

Research output: Contribution to journal › Article › peer-review

Original language	English
Pages (from-to)	175-214
Number of pages	40
Journal	Health Services and Outcomes Research Methodology
Volume	18
Issue number	3
DOIs	https://doi.org/10.1007/s10742-018-0183-6
State	Published - Sep 1 2018
Externally published	Yes

ASJC Scopus Subject Areas

Health Policy
Public Health, Environmental and Occupational Health

Keywords

Count data
Excess zeroes
Healthcare utilization
Marginal inference
Marginalization
Two-part models

Access to Document

10.1007/s10742-018-0183-6

OpenUrl availability

Full text

Cite this

Liu, X., Zhang, B., Tang, L., Zhang, Z., Zhang, N., Allison, J. J., Srivastava, D. K., & Zhang, H. (2018). Are marginalized two-part models superior to non-marginalized two-part models for count data with excess zeroes? Estimation of marginal effects, model misspecification, and model selection. Health Services and Outcomes Research Methodology, 18(3), 175-214. https://doi.org/10.1007/s10742-018-0183-6

Are marginalized two-part models superior to non-marginalized two-part models for count data with excess zeroes? Estimation of marginal effects, model misspecification, and model selection. / Liu, Xueyan; Zhang, Bo; Tang, Li et al.
In: Health Services and Outcomes Research Methodology, Vol. 18, No. 3, 01.09.2018, p. 175-214.

Research output: Contribution to journal › Article › peer-review

Liu, X, Zhang, B, Tang, L, Zhang, Z, Zhang, N, Allison, JJ, Srivastava, DK & Zhang, H 2018, 'Are marginalized two-part models superior to non-marginalized two-part models for count data with excess zeroes? Estimation of marginal effects, model misspecification, and model selection', Health Services and Outcomes Research Methodology, vol. 18, no. 3, pp. 175-214. https://doi.org/10.1007/s10742-018-0183-6

@article{9cf9a91ceea6427aa7412d642b7abee6,

title = "Are marginalized two-part models superior to non-marginalized two-part models for count data with excess zeroes? Estimation of marginal effects, model misspecification, and model selection",

keywords = "Count data, Excess zeroes, Healthcare utilization, Marginal inference, Marginalization, Two-part models",

author = "Xueyan Liu and Bo Zhang and Li Tang and Zhiwei Zhang and Ning Zhang and Allison, {Jeroan J.} and Srivastava, {Deo Kumar} and Hui Zhang",

note = "Publisher Copyright: {\textcopyright} 2018, Springer Science+Business Media, LLC, part of Springer Nature.",

year = "2018",

month = sep,

day = "1",

doi = "10.1007/s10742-018-0183-6",

language = "English",

volume = "18",

pages = "175--214",

journal = "Health Services and Outcomes Research Methodology",

issn = "1387-3741",

number = "3",

}

TY - JOUR

T1 - Are marginalized two-part models superior to non-marginalized two-part models for count data with excess zeroes? Estimation of marginal effects, model misspecification, and model selection

AU - Liu, Xueyan

AU - Zhang, Bo

AU - Tang, Li

AU - Zhang, Zhiwei

AU - Zhang, Ning

AU - Allison, Jeroan J.

AU - Srivastava, Deo Kumar

AU - Zhang, Hui

PY - 2018/9/1

Y1 - 2018/9/1

KW - Count data

KW - Excess zeroes

KW - Healthcare utilization

KW - Marginal inference

KW - Marginalization

KW - Two-part models

UR - http://www.scopus.com/inward/record.url?scp=85048048234&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048048234&partnerID=8YFLogxK

U2 - 10.1007/s10742-018-0183-6

DO - 10.1007/s10742-018-0183-6

M3 - Article

AN - SCOPUS:85048048234

SN - 1387-3741

VL - 18

SP - 175

EP - 214

JO - Health Services and Outcomes Research Methodology

JF - Health Services and Outcomes Research Methodology

IS - 3

ER -

Are marginalized two-part models superior to non-marginalized two-part models for count data with excess zeroes? Estimation of marginal effects, model misspecification, and model selection

ASJC Scopus Subject Areas

Keywords

Access to Document

OpenUrl availability

Other files and links

Cite this