Identification of proportionality structure with two-part models using penalization

Kuangnan Fang, Xiaoyan Wang, Ben Chang Shia, Shuangge Ma

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Data with a mixture distribution are commonly encountered. A special example is zero-inflated data, where a proportion of the responses takes zero values, and the rest are continuously distributed. Such data routinely arise in public health, biomedicine, and many other fields. Two-part modeling is a natural choice for zero-inflated data, where the first part of the model describes whether the responses are equal to zero, and the second part describes the continuously distributed responses. With two-part models, an interesting problem is to identify the proportionality structure of covariate effects. Such a structure can lead to more efficient estimates and also provide scientific insights into the underlying data-generating mechanisms. To identify the proportionality structure, we adopt a penalization method. Compared to the alternatives, notable advantages of this method include computational simplicity, solid statistical properties, and others. For inference, we adopt a bootstrap approach. The proposed method shows satisfactory performance in simulation and the analysis of two public health datasets.

Original languageEnglish
Pages (from-to)12-24
Number of pages13
JournalComputational Statistics and Data Analysis
Volume99
DOIs
Publication statusPublished - Jul 1 2016

Fingerprint

Penalization
Public health
Identification (control systems)
Computational methods
Public Health
Zero
Penalization Method
Mixture Distribution
Model
Computational Methods
Bootstrap
Statistical property
Covariates
Simplicity
Proportion
Alternatives
Modeling
Estimate
Simulation

Keywords

  • Penalization
  • Proportionality
  • Two-part modeling
  • Zero-inflated data

ASJC Scopus subject areas

  • Computational Mathematics
  • Computational Theory and Mathematics
  • Statistics and Probability
  • Applied Mathematics

Cite this

Identification of proportionality structure with two-part models using penalization. / Fang, Kuangnan; Wang, Xiaoyan; Shia, Ben Chang; Ma, Shuangge.

In: Computational Statistics and Data Analysis, Vol. 99, 01.07.2016, p. 12-24.

Research output: Contribution to journalArticle

@article{c2885be027c845c682e30198534bcfd3,
title = "Identification of proportionality structure with two-part models using penalization",
abstract = "Data with a mixture distribution are commonly encountered. A special example is zero-inflated data, where a proportion of the responses takes zero values, and the rest are continuously distributed. Such data routinely arise in public health, biomedicine, and many other fields. Two-part modeling is a natural choice for zero-inflated data, where the first part of the model describes whether the responses are equal to zero, and the second part describes the continuously distributed responses. With two-part models, an interesting problem is to identify the proportionality structure of covariate effects. Such a structure can lead to more efficient estimates and also provide scientific insights into the underlying data-generating mechanisms. To identify the proportionality structure, we adopt a penalization method. Compared to the alternatives, notable advantages of this method include computational simplicity, solid statistical properties, and others. For inference, we adopt a bootstrap approach. The proposed method shows satisfactory performance in simulation and the analysis of two public health datasets.",
keywords = "Penalization, Proportionality, Two-part modeling, Zero-inflated data",
author = "Kuangnan Fang and Xiaoyan Wang and Shia, {Ben Chang} and Shuangge Ma",
year = "2016",
month = "7",
day = "1",
doi = "10.1016/j.csda.2016.01.002",
language = "English",
volume = "99",
pages = "12--24",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",

}

TY - JOUR

T1 - Identification of proportionality structure with two-part models using penalization

AU - Fang, Kuangnan

AU - Wang, Xiaoyan

AU - Shia, Ben Chang

AU - Ma, Shuangge

PY - 2016/7/1

Y1 - 2016/7/1

N2 - Data with a mixture distribution are commonly encountered. A special example is zero-inflated data, where a proportion of the responses takes zero values, and the rest are continuously distributed. Such data routinely arise in public health, biomedicine, and many other fields. Two-part modeling is a natural choice for zero-inflated data, where the first part of the model describes whether the responses are equal to zero, and the second part describes the continuously distributed responses. With two-part models, an interesting problem is to identify the proportionality structure of covariate effects. Such a structure can lead to more efficient estimates and also provide scientific insights into the underlying data-generating mechanisms. To identify the proportionality structure, we adopt a penalization method. Compared to the alternatives, notable advantages of this method include computational simplicity, solid statistical properties, and others. For inference, we adopt a bootstrap approach. The proposed method shows satisfactory performance in simulation and the analysis of two public health datasets.

AB - Data with a mixture distribution are commonly encountered. A special example is zero-inflated data, where a proportion of the responses takes zero values, and the rest are continuously distributed. Such data routinely arise in public health, biomedicine, and many other fields. Two-part modeling is a natural choice for zero-inflated data, where the first part of the model describes whether the responses are equal to zero, and the second part describes the continuously distributed responses. With two-part models, an interesting problem is to identify the proportionality structure of covariate effects. Such a structure can lead to more efficient estimates and also provide scientific insights into the underlying data-generating mechanisms. To identify the proportionality structure, we adopt a penalization method. Compared to the alternatives, notable advantages of this method include computational simplicity, solid statistical properties, and others. For inference, we adopt a bootstrap approach. The proposed method shows satisfactory performance in simulation and the analysis of two public health datasets.

KW - Penalization

KW - Proportionality

KW - Two-part modeling

KW - Zero-inflated data

UR - http://www.scopus.com/inward/record.url?scp=84957990953&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957990953&partnerID=8YFLogxK

U2 - 10.1016/j.csda.2016.01.002

DO - 10.1016/j.csda.2016.01.002

M3 - Article

AN - SCOPUS:84957990953

VL - 99

SP - 12

EP - 24

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

ER -