Home > Research > Publications & Outputs > An appraisal of methods for the analysis of lon...

Research

Links

Text available via DOI:

Keywords

View graph of relations

An appraisal of methods for the analysis of longitudinal ordinal response data with random dropout using a non-homogeneous Markov model

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

Published

Standard

An appraisal of methods for the analysis of longitudinal ordinal response data with random dropout using a non-homogeneous Markov model. / Rezaei Ghahroodi, Z; Ganjali, M; Navvabpour, H et al.
In: Communications in Statistics – Simulation and Computation, Vol. 39, No. 5, 2010, p. 1027-1048.

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

Harvard

Rezaei Ghahroodi, Z, Ganjali, M, Navvabpour, H & Berridge, D 2010, 'An appraisal of methods for the analysis of longitudinal ordinal response data with random dropout using a non-homogeneous Markov model', Communications in Statistics – Simulation and Computation, vol. 39, no. 5, pp. 1027-1048. https://doi.org/10.1080/03610911003778085

APA

Rezaei Ghahroodi, Z., Ganjali, M., Navvabpour, H., & Berridge, D. (2010). An appraisal of methods for the analysis of longitudinal ordinal response data with random dropout using a non-homogeneous Markov model. Communications in Statistics – Simulation and Computation, 39(5), 1027-1048. https://doi.org/10.1080/03610911003778085

Vancouver

Rezaei Ghahroodi Z, Ganjali M, Navvabpour H, Berridge D. An appraisal of methods for the analysis of longitudinal ordinal response data with random dropout using a non-homogeneous Markov model. Communications in Statistics – Simulation and Computation. 2010;39(5):1027-1048. doi: 10.1080/03610911003778085

Author

Rezaei Ghahroodi, Z ; Ganjali, M ; Navvabpour, H et al. / An appraisal of methods for the analysis of longitudinal ordinal response data with random dropout using a non-homogeneous Markov model. In: Communications in Statistics – Simulation and Computation. 2010 ; Vol. 39, No. 5. pp. 1027-1048.

Bibtex

@article{7c9c08a2d0694d6f847da5b8267fd445,
title = "An appraisal of methods for the analysis of longitudinal ordinal response data with random dropout using a non-homogeneous Markov model",
abstract = "There are many methods for analyzing longitudinal ordinal response data with random dropout. These include maximum likelihood (ML), weighted estimating equations (WEEs), and multiple imputations (MI). In this article, using a Markov model where the effect of previous response on the current response is investigated as an ordinal variable, the likelihood is partitioned to simplify the use of existing software. Simulated data, generated to present a three-period longitudinal study with random dropout, are used to compare performance of ML, WEE, and MI methods in terms of standardized bias and coverage probabilities. These estimation methods are applied to a real medical data set.",
keywords = "Multiple imputation, Nonhomogeneous Markov model , Random dropout , Short-period longitudinal data , Weighted estimating equations",
author = "{Rezaei Ghahroodi}, Z and M Ganjali and H Navvabpour and Damon Berridge",
year = "2010",
doi = "10.1080/03610911003778085",
language = "English",
volume = "39",
pages = "1027--1048",
journal = "Communications in Statistics – Simulation and Computation",
issn = "1532-4141",
publisher = "Taylor and Francis Ltd.",
number = "5",

}

RIS

TY - JOUR

T1 - An appraisal of methods for the analysis of longitudinal ordinal response data with random dropout using a non-homogeneous Markov model

AU - Rezaei Ghahroodi, Z

AU - Ganjali, M

AU - Navvabpour, H

AU - Berridge, Damon

PY - 2010

Y1 - 2010

N2 - There are many methods for analyzing longitudinal ordinal response data with random dropout. These include maximum likelihood (ML), weighted estimating equations (WEEs), and multiple imputations (MI). In this article, using a Markov model where the effect of previous response on the current response is investigated as an ordinal variable, the likelihood is partitioned to simplify the use of existing software. Simulated data, generated to present a three-period longitudinal study with random dropout, are used to compare performance of ML, WEE, and MI methods in terms of standardized bias and coverage probabilities. These estimation methods are applied to a real medical data set.

AB - There are many methods for analyzing longitudinal ordinal response data with random dropout. These include maximum likelihood (ML), weighted estimating equations (WEEs), and multiple imputations (MI). In this article, using a Markov model where the effect of previous response on the current response is investigated as an ordinal variable, the likelihood is partitioned to simplify the use of existing software. Simulated data, generated to present a three-period longitudinal study with random dropout, are used to compare performance of ML, WEE, and MI methods in terms of standardized bias and coverage probabilities. These estimation methods are applied to a real medical data set.

KW - Multiple imputation

KW - Nonhomogeneous Markov model

KW - Random dropout

KW - Short-period longitudinal data

KW - Weighted estimating equations

U2 - 10.1080/03610911003778085

DO - 10.1080/03610911003778085

M3 - Journal article

VL - 39

SP - 1027

EP - 1048

JO - Communications in Statistics – Simulation and Computation

JF - Communications in Statistics – Simulation and Computation

SN - 1532-4141

IS - 5

ER -