Home > Research > Publications & Outputs > First-order marginalised transition random effe...

Research

Electronic data

  • pnmtrem_jas_r1

    Rights statement: This is an Accepted Manuscript of an article published by Taylor & Francis in Journal of Applied Statistics on 11/09/2015, available online: http://wwww.tandfonline.com/doi/abs/10.1080/02664763.2015.1080670

    Accepted author manuscript, 182 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

Keywords

View graph of relations

First-order marginalised transition random effects models with probit link function

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

First-order marginalised transition random effects models with probit link function. / Asar, Özgür; Ilk, Ozlem.
In: Journal of Applied Statistics, Vol. 43, No. 5, 04.2016, p. 925-942.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Asar, Ö & Ilk, O 2016, 'First-order marginalised transition random effects models with probit link function', Journal of Applied Statistics, vol. 43, no. 5, pp. 925-942. https://doi.org/10.1080/02664763.2015.1080670

APA

Asar, Ö., & Ilk, O. (2016). First-order marginalised transition random effects models with probit link function. Journal of Applied Statistics, 43(5), 925-942. https://doi.org/10.1080/02664763.2015.1080670

Vancouver

Asar Ö, Ilk O. First-order marginalised transition random effects models with probit link function. Journal of Applied Statistics. 2016 Apr;43(5):925-942. Epub 2015 Sept 11. doi: 10.1080/02664763.2015.1080670

Author

Asar, Özgür ; Ilk, Ozlem. / First-order marginalised transition random effects models with probit link function. In: Journal of Applied Statistics. 2016 ; Vol. 43, No. 5. pp. 925-942.

Bibtex

@article{f136a15d625944fc869b80dd2e051a0d,
title = "First-order marginalised transition random effects models with probit link function",
abstract = "Marginalised models, also known as marginally specified models, have recently become a popular tool for analysis of discrete longitudinal data. Despite being a novel statistical methodology, these models introduce complex constraint equations and model fitting algorithms. On the other hand, there is a lack of publicly available software to fit these models. In this paper, we propose a three-level marginalised model for analysis of multivariate longitudinal binary outcome.The implicit function theorem is introduced to approximately solve the marginal constraint equations explicitly. probit link enables direct solutions to the convolution equations. Parameters are estimated by maximum likelihood via a Fisher-Scoring algorithm. A simulation study is conducted to examine the finite-sample properties of the estimator. We illustrate the model with an application to the data set from the Iowa Youth and Families Project. The R package pnmtrem is prepared to fit the model.",
keywords = "correlated data, implicit differentiation, link functions, maximum likelihood estimation, subject-specific inference, statistical software, 62H12, 62J12, 62P15",
author = "{\"O}zg{\"u}r Asar and Ozlem Ilk",
note = "This is an Accepted Manuscript of an article published by Taylor & Francis in Journal of Applied Statistics on 11/09/2015, available online: http://wwww.tandfonline.com/doi/abs/10.1080/02664763.2015.1080670",
year = "2016",
month = apr,
doi = "10.1080/02664763.2015.1080670",
language = "English",
volume = "43",
pages = "925--942",
journal = "Journal of Applied Statistics",
issn = "0266-4763",
publisher = "Routledge",
number = "5",

}

RIS

TY - JOUR

T1 - First-order marginalised transition random effects models with probit link function

AU - Asar, Özgür

AU - Ilk, Ozlem

N1 - This is an Accepted Manuscript of an article published by Taylor & Francis in Journal of Applied Statistics on 11/09/2015, available online: http://wwww.tandfonline.com/doi/abs/10.1080/02664763.2015.1080670

PY - 2016/4

Y1 - 2016/4

N2 - Marginalised models, also known as marginally specified models, have recently become a popular tool for analysis of discrete longitudinal data. Despite being a novel statistical methodology, these models introduce complex constraint equations and model fitting algorithms. On the other hand, there is a lack of publicly available software to fit these models. In this paper, we propose a three-level marginalised model for analysis of multivariate longitudinal binary outcome.The implicit function theorem is introduced to approximately solve the marginal constraint equations explicitly. probit link enables direct solutions to the convolution equations. Parameters are estimated by maximum likelihood via a Fisher-Scoring algorithm. A simulation study is conducted to examine the finite-sample properties of the estimator. We illustrate the model with an application to the data set from the Iowa Youth and Families Project. The R package pnmtrem is prepared to fit the model.

AB - Marginalised models, also known as marginally specified models, have recently become a popular tool for analysis of discrete longitudinal data. Despite being a novel statistical methodology, these models introduce complex constraint equations and model fitting algorithms. On the other hand, there is a lack of publicly available software to fit these models. In this paper, we propose a three-level marginalised model for analysis of multivariate longitudinal binary outcome.The implicit function theorem is introduced to approximately solve the marginal constraint equations explicitly. probit link enables direct solutions to the convolution equations. Parameters are estimated by maximum likelihood via a Fisher-Scoring algorithm. A simulation study is conducted to examine the finite-sample properties of the estimator. We illustrate the model with an application to the data set from the Iowa Youth and Families Project. The R package pnmtrem is prepared to fit the model.

KW - correlated data

KW - implicit differentiation

KW - link functions

KW - maximum likelihood estimation

KW - subject-specific inference

KW - statistical software

KW - 62H12

KW - 62J12

KW - 62P15

U2 - 10.1080/02664763.2015.1080670

DO - 10.1080/02664763.2015.1080670

M3 - Journal article

VL - 43

SP - 925

EP - 942

JO - Journal of Applied Statistics

JF - Journal of Applied Statistics

SN - 0266-4763

IS - 5

ER -