Under-reported data analysis with INAR-hidden Markov chains

Amanda Fernández-Fontelo; Alejandra Cabaña; Pedro Puig; David Moriña

doi:10.1002/sim.7026

Under-reported data analysis with INAR-hidden Markov chains

Amanda Fernández-Fontelo, Alejandra Cabaña, Pedro Puig, David Moriña

Research output: Contribution to journal › Article › Research › peer-review

34 Citations (Scopus)

Abstract

Copyright © 2016 John Wiley & Sons, Ltd. In this work, we deal with correlated under-reported data through INAR(1)-hidden Markov chain models. These models are very flexible and can be identified through its autocorrelation function, which has a very simple form. A naïve method of parameter estimation is proposed, jointly with the maximum likelihood method based on a revised version of the forward algorithm. The most-probable unobserved time series is reconstructed by means of the Viterbi algorithm. Several examples of application in the field of public health are discussed illustrating the utility of the models. Copyright © 2016 John Wiley & Sons, Ltd.

Original language	English
Pages (from-to)	4875-4890
Journal	Statistics in Medicine
Volume	35
Issue number	26
DOIs	https://doi.org/10.1002/sim.7026
Publication status	Published - 20 Nov 2016

Keywords

discrete time series
emission probabilities
integer-autoregressive models
thinning operator
under-recorded data

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1002/sim.7026

Cite this

@article{6d206d099f8a49768ca383e6017a3a6b,

title = "Under-reported data analysis with INAR-hidden Markov chains",

abstract = "Copyright {\textcopyright} 2016 John Wiley & Sons, Ltd. In this work, we deal with correlated under-reported data through INAR(1)-hidden Markov chain models. These models are very flexible and can be identified through its autocorrelation function, which has a very simple form. A na{\"i}ve method of parameter estimation is proposed, jointly with the maximum likelihood method based on a revised version of the forward algorithm. The most-probable unobserved time series is reconstructed by means of the Viterbi algorithm. Several examples of application in the field of public health are discussed illustrating the utility of the models. Copyright {\textcopyright} 2016 John Wiley & Sons, Ltd.",

keywords = "discrete time series, emission probabilities, integer-autoregressive models, thinning operator, under-recorded data",

author = "Amanda Fern{\'a}ndez-Fontelo and Alejandra Caba{\~n}a and Pedro Puig and David Mori{\~n}a",

year = "2016",

month = nov,

day = "20",

doi = "10.1002/sim.7026",

language = "English",

volume = "35",

pages = "4875--4890",

journal = "Statistics in Medicine",

issn = "0277-6715",

publisher = "John Wiley and Sons Ltd",

number = "26",

}

TY - JOUR

T1 - Under-reported data analysis with INAR-hidden Markov chains

AU - Fernández-Fontelo, Amanda

AU - Cabaña, Alejandra

AU - Puig, Pedro

AU - Moriña, David

PY - 2016/11/20

Y1 - 2016/11/20

N2 - Copyright © 2016 John Wiley & Sons, Ltd. In this work, we deal with correlated under-reported data through INAR(1)-hidden Markov chain models. These models are very flexible and can be identified through its autocorrelation function, which has a very simple form. A naïve method of parameter estimation is proposed, jointly with the maximum likelihood method based on a revised version of the forward algorithm. The most-probable unobserved time series is reconstructed by means of the Viterbi algorithm. Several examples of application in the field of public health are discussed illustrating the utility of the models. Copyright © 2016 John Wiley & Sons, Ltd.

AB - Copyright © 2016 John Wiley & Sons, Ltd. In this work, we deal with correlated under-reported data through INAR(1)-hidden Markov chain models. These models are very flexible and can be identified through its autocorrelation function, which has a very simple form. A naïve method of parameter estimation is proposed, jointly with the maximum likelihood method based on a revised version of the forward algorithm. The most-probable unobserved time series is reconstructed by means of the Viterbi algorithm. Several examples of application in the field of public health are discussed illustrating the utility of the models. Copyright © 2016 John Wiley & Sons, Ltd.

KW - discrete time series

KW - emission probabilities

KW - integer-autoregressive models

KW - thinning operator

KW - under-recorded data

U2 - 10.1002/sim.7026

DO - 10.1002/sim.7026

M3 - Article

SN - 0277-6715

VL - 35

SP - 4875

EP - 4890

JO - Statistics in Medicine

JF - Statistics in Medicine

IS - 26

ER -

Under-reported data analysis with INAR-hidden Markov chains

Abstract

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this