TY - JOUR
T1 - Bayesian estimation of an autoregressive model using Markov chain Monte Carlo
AU - Barnett, Glen
AU - Kohn, Robert
AU - Sheather, Simon
PY - 1996/10
Y1 - 1996/10
N2 - We present a complete Bayesian treatment of autoregressive model estimation incorporating choice of autoregressive order, enforcement of stationarity, treatment of outliers, and allowance for missing values and multiplicative seasonality. The paper makes three distinct contributions. First, we enforce the stationarity conditions using a very efficient Metropolis-within-Gibbs algorithm to generate the partial autocorrelations. Second we show how to carry out the Gibbs sampler when the autoregressive order is unknown. Third, we show how to combine the various aspects of fitting an autoregressive model giving a more comprehensive and efficient treatment than previous work. We illustrate our methodology with a real example.
AB - We present a complete Bayesian treatment of autoregressive model estimation incorporating choice of autoregressive order, enforcement of stationarity, treatment of outliers, and allowance for missing values and multiplicative seasonality. The paper makes three distinct contributions. First, we enforce the stationarity conditions using a very efficient Metropolis-within-Gibbs algorithm to generate the partial autocorrelations. Second we show how to carry out the Gibbs sampler when the autoregressive order is unknown. Third, we show how to combine the various aspects of fitting an autoregressive model giving a more comprehensive and efficient treatment than previous work. We illustrate our methodology with a real example.
KW - Gibbs sampler
KW - Metropolis algorithm
KW - Missing data
KW - Order selection
KW - Outliers
UR - http://www.scopus.com/inward/record.url?scp=0002061759&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0002061759&partnerID=8YFLogxK
U2 - 10.1016/0304-4076(95)01744-5
DO - 10.1016/0304-4076(95)01744-5
M3 - Article
AN - SCOPUS:0002061759
SN - 0304-4076
VL - 74
SP - 237
EP - 254
JO - Journal of Econometrics
JF - Journal of Econometrics
IS - 2
ER -