Forecasting multivariate longitudinal binary data with marginal and marginally specified models

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

Published

Standard

Forecasting multivariate longitudinal binary data with marginal and marginally specified models. / Asar, Özgür; Ilk, Ozlem.
In: Journal of Statistical Computation and Simulation, Vol. 86, No. 2, 2015, p. 414-429.

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

Harvard

Asar, Ö & Ilk, O 2015, 'Forecasting multivariate longitudinal binary data with marginal and marginally specified models', Journal of Statistical Computation and Simulation, vol. 86, no. 2, pp. 414-429. https://doi.org/10.1080/00949655.2015.1016025

APA

Asar, Ö., & Ilk, O. (2015). Forecasting multivariate longitudinal binary data with marginal and marginally specified models. Journal of Statistical Computation and Simulation, 86(2), 414-429. https://doi.org/10.1080/00949655.2015.1016025

Vancouver

Asar Ö, Ilk O. Forecasting multivariate longitudinal binary data with marginal and marginally specified models. Journal of Statistical Computation and Simulation. 2015;86(2):414-429. Epub 2015 Feb 25. doi: 10.1080/00949655.2015.1016025

Author

Asar, Özgür ; Ilk, Ozlem. / Forecasting multivariate longitudinal binary data with marginal and marginally specified models. In: Journal of Statistical Computation and Simulation. 2015 ; Vol. 86, No. 2. pp. 414-429.

Bibtex

@article{0e33e634e35146e08016a0ff64830343,

title = "Forecasting multivariate longitudinal binary data with marginal and marginally specified models",

abstract = "Forecasting with longitudinal data has been rarely studied. Most of the available studies are for continuous response and all of them are for univariate response. In this study, we consider forecasting multivariate longitudinal binary data. Five different models including simple ones, univariate and multivariate marginal models, and complex ones, marginally specified models, are studied to forecast such data. Model forecasting abilities are illustrated via a real-life data set and a simulation study. The simulation study includes a model independent data generation to provide a fair environment for model competitions. Independent variables are forecast as well as the dependent ones to mimic the real-life cases best. Several accuracy measures are considered to compare model forecasting abilities. Results show that complex models yield better forecasts.",

keywords = "comparative studies, dichotomous data, exponential smoothing, forecasting competitions, marginalized models, medical statistics",

author = "{\"O}zg{\"u}r Asar and Ozlem Ilk",

year = "2015",

doi = "10.1080/00949655.2015.1016025",

language = "English",

volume = "86",

pages = "414--429",

journal = "Journal of Statistical Computation and Simulation",

issn = "1563-5163",

publisher = "Taylor and Francis Ltd.",

number = "2",

}

RIS

TY - JOUR

T1 - Forecasting multivariate longitudinal binary data with marginal and marginally specified models

AU - Asar, Özgür

AU - Ilk, Ozlem

PY - 2015

Y1 - 2015

N2 - Forecasting with longitudinal data has been rarely studied. Most of the available studies are for continuous response and all of them are for univariate response. In this study, we consider forecasting multivariate longitudinal binary data. Five different models including simple ones, univariate and multivariate marginal models, and complex ones, marginally specified models, are studied to forecast such data. Model forecasting abilities are illustrated via a real-life data set and a simulation study. The simulation study includes a model independent data generation to provide a fair environment for model competitions. Independent variables are forecast as well as the dependent ones to mimic the real-life cases best. Several accuracy measures are considered to compare model forecasting abilities. Results show that complex models yield better forecasts.

AB - Forecasting with longitudinal data has been rarely studied. Most of the available studies are for continuous response and all of them are for univariate response. In this study, we consider forecasting multivariate longitudinal binary data. Five different models including simple ones, univariate and multivariate marginal models, and complex ones, marginally specified models, are studied to forecast such data. Model forecasting abilities are illustrated via a real-life data set and a simulation study. The simulation study includes a model independent data generation to provide a fair environment for model competitions. Independent variables are forecast as well as the dependent ones to mimic the real-life cases best. Several accuracy measures are considered to compare model forecasting abilities. Results show that complex models yield better forecasts.

KW - comparative studies

KW - dichotomous data

KW - exponential smoothing

KW - forecasting competitions

KW - marginalized models

KW - medical statistics

U2 - 10.1080/00949655.2015.1016025

DO - 10.1080/00949655.2015.1016025

M3 - Journal article

VL - 86

SP - 414

EP - 429

JO - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

SN - 1563-5163

IS - 2

ER -

Research

Links

Text available via DOI:

Keywords