Two-Part and Related Regression Models for Longitudinal Data

Overview

Journal Annu Rev Stat Appl

Publisher Annual Reviews

Specialty Public Health

Date 2017 Sep 12

PMID 28890906

Citations 43

Authors

V T Farewell

D L Long

B D M Tom

S Yiu

L Su

Affiliations

Soon will be listed here.

Abstract

Statistical models that involve a two-part mixture distribution are applicable in a variety of situations. Frequently, the two parts are a model for the binary response variable and a model for the outcome variable that is conditioned on the binary response. Two common examples are zero-inflated or hurdle models for count data and two-part models for semicontinuous data. Recently, there has been particular interest in the use of these models for the analysis of repeated measures of an outcome variable over time. The aim of this review is to consider motivations for the use of such models in this context and to highlight the central issues that arise with their use. We examine two-part models for semicontinuous and zero-heavy count data, and we also consider models for count data with a two-part random effects distribution.

Citing Articles

Naik H, Zhu B, Er L, Sbihi H, Janjua N, Smith P BMJ Public Health. 2025; 3(1):e001801.

PMID: 40017956 PMC: 11816324. DOI: 10.1136/bmjph-2024-001801.

Sex-specific and cell-type-specific changes in chaperone-mediated autophagy across tissues during aging.

Khawaja R, Martin-Segura A, Santiago-Fernandez O, Sereda R, Lindenau K, McCabe M Nat Aging. 2025; .

PMID: 39910244 DOI: 10.1038/s43587-024-00799-6.

Changes in food and drink purchasing behaviour in England during the first 3 months of the COVID-19 pandemic: an interrupted time series analysis.

Kalbus A, Cornelsen L, Ballatore A, Cummins S Public Health Nutr. 2024; 27(1):e252.

PMID: 39575500 PMC: 11705008. DOI: 10.1017/S1368980024001071.

Exploration of alive-and-ventilator free days as an outcome measure for clinical trials of Resuscitative interventions.

Moskowitz A, Xie X, Gong M, Wang H, Andrea L, Lo Y PLoS One. 2024; 19(7):e0308033.

PMID: 39083542 PMC: 11290648. DOI: 10.1371/journal.pone.0308033.

Economic outcomes among microfinance group members receiving community-based chronic disease care: Cluster randomized trial evidence from Kenya.

Wilson-Barthes M, Steingrimsson J, Lee Y, Tran D, Wachira J, Kafu C Soc Sci Med. 2024; 351:116993.

PMID: 38781744 PMC: 11180555. DOI: 10.1016/j.socscimed.2024.116993.

References

Solis-Trapala I, Farewell V . Regression analysis of overdispersed correlated count data with subject specific covariates. Stat Med. 2005; 24(16):2557-75. DOI: 10.1002/sim.2121. View

Heagerty P . Marginally specified logistic-normal models for longitudinal binary data. Biometrics. 2001; 55(3):688-98. DOI: 10.1111/j.0006-341x.1999.00688.x. View

Preisser J, Das K, Long D, Divaris K . Marginalized zero-inflated negative binomial regression with application to dental caries. Stat Med. 2015; 35(10):1722-35. PMC: 4826785. DOI: 10.1002/sim.6804. View

Tom B, Su L, Farewell V . A corrected formulation for marginal inference derived from two-part mixed models for longitudinal semi-continuous data. Stat Methods Med Res. 2013; 25(5):2014-2020. PMC: 5051603. DOI: 10.1177/0962280213509798. View

Moger T, Aalen O . A distribution for multivariate frailty based on the compound Poisson distribution with random scale. Lifetime Data Anal. 2005; 11(1):41-59. DOI: 10.1007/s10985-004-5639-z. View

Lachenbruch P . Analysis of data with excess zeros. Stat Methods Med Res. 2002; 11(4):297-302. DOI: 10.1191/0962280202sm289ra. View

Su L, Tom B, Farewell V . A likelihood-based two-part marginal model for longitudinal semicontinuous data. Stat Methods Med Res. 2011; 24(2):194-205. PMC: 4849555. DOI: 10.1177/0962280211414620. View

Su L, Tom B, Farewell V . Bias in 2-part mixed models for longitudinal semicontinuous data. Biostatistics. 2009; 10(2):374-89. PMC: 2648907. DOI: 10.1093/biostatistics/kxn044. View

Yang Y, Simpson D . Unified Computational Methods for Regression Analysis of Zero-Inflated and Bound-Inflated Data. Comput Stat Data Anal. 2010; 54(6):1525-1534. PMC: 2836522. DOI: 10.1016/j.csda.2009.12.012. View

10.

Taylor J . Semi-parametric estimation in failure time mixture models. Biometrics. 1995; 51(3):899-907. View

11.

Long D, Preisser J, Herring A, Golin C . A marginalized zero-inflated Poisson regression model with overall exposure effects. Stat Med. 2014; 33(29):5151-65. PMC: 4227945. DOI: 10.1002/sim.6293. View

12.

Golin C, Davis R, Przybyla S, Fowler B, Parker S, Earp J . SafeTalk, a multicomponent, motivational interviewing-based, safer sex counseling program for people living with HIV/AIDS: a qualitative assessment of patients' views. AIDS Patient Care STDS. 2010; 24(4):237-45. PMC: 2864060. DOI: 10.1089/apc.2009.0252. View

13.

Stiratelli R, Laird N, Ware J . Random-effects models for serial observations with binary response. Biometrics. 1984; 40(4):961-71. View

14.

Lin L, Bandyopadhyay D, Lipsitz S, Sinha D . Association models for clustered data with binary and continuous responses. Biometrics. 2009; 66(1):287-93. PMC: 2890259. DOI: 10.1111/j.1541-0420.2008.01232.x. View

15.

Liu L, Strawderman R, Cowen M, Shih Y . A flexible two-part random effects model for correlated medical costs. J Health Econ. 2009; 29(1):110-23. PMC: 2824028. DOI: 10.1016/j.jhealeco.2009.11.010. View

16.

Young P, Weeden S, Kirwan J . The analysis of a bivariate multi-state Markov transition model for rheumatoid arthritis with an incomplete disease history. Stat Med. 1999; 18(13):1677-90. DOI: 10.1002/(sici)1097-0258(19990715)18:13<1677::aid-sim154>3.0.co;2-n. View

17.

Munro R, Hampson R, McEntegart A, Thomson E, Madhok R, Capell H . Improved functional outcome in patients with early rheumatoid arthritis treated with intramuscular gold: results of a five year prospective study. Ann Rheum Dis. 1998; 57(2):88-93. PMC: 1752531. DOI: 10.1136/ard.57.2.88. View

18.

Lu S, Lin Y, Shih W . Analyzing excessive no changes in clinical trials with clustered data. Biometrics. 2004; 60(1):257-67. DOI: 10.1111/j.0006-341X.2004.00155.x. View

19.

Ghosh P, Albert P . A Bayesian analysis for longitudinal semicontinuous data with an application to an acupuncture clinical trial. Comput Stat Data Anal. 2009; 53(3):699-706. PMC: 2744988. DOI: 10.1016/j.csda.2008.09.011. View

20.

Smith V, Neelon B, Preisser J, Maciejewski M . A marginalized two-part model for longitudinal semicontinuous data. Stat Methods Med Res. 2015; 26(4):1949-1968. DOI: 10.1177/0962280215592908. View