TIME SERIES WITH MULTIPLE CHANGE POINTS AND CENSORED OBSERVATIONS
DOI:
https://doi.org/10.47163/agrociencia.v58i1.2856Palabras clave:
Parameter estimation, Bayesian inference, prior distributions, Metropolis algorithm, reversible jump Markov chain Monte Carlo algorithm.Resumen
This article examines a Bayesian model for a nonstationary time series with an unknown number of change points and censored observations. Each segment is assumed to be an autoregressive process with order one. To estimate the number and locations of change points, we use the reversible jump Markov chain Monte Carlo (RJMCMC) algorithm. The censored problem is solved by imputing the censored values from a multivariate normal distribution based on the observed part. A numerical example shows that the estimates of the number of change points and their localizations have little bias. Additionally, the estimates are robust to the censoring percentage.
Archivos adicionales
Publicado
Número
Sección
Licencia
Agrociencia es una publicación sesquimensual en formato totalmente en inglés, y editada por el Colegio de Postgraduados. Carretera México-Texcoco Km. 36.5, Montecillo, Texcoco, Estado de México, CP 56264, Teléfono (52) 5959284427. www.colpos.mx. Editor en Jefe de Agrociencia: Dr. Fernando Carlos Gómez Merino. Reservas de Derechos al Uso Exclusivo: 04-2021-031913431800-203, e-ISSN: 2521-9766, otorgados por el Instituto Nacional del Derecho de Autor.
