Contrasting Bayesian and Frequentist Approaches to Autoregressions: the Role of the Initial Condition

Marek Jarociński and Albert Marcet

No 776, Working Papers from Barcelona School of Economics

Abstract: The frequentist and the Bayesian approach to the estimation of autoregressions are often contrasted. Under standard assumptions, when the ordinary least squares (OLS) estimate is close to 1, a frequentist adjusts it upwards to counter the small sample bias, while a Bayesian who uses a at prior considers the OLS estimate to be the best point estimate. This contrast is surprising because a at prior is often interpreted as the Bayesian approach that is closest to the frequentist approach. We point out that the standard way that inference has been compared is misleading because frequentists and Bayesians tend to use different models, in particular, a different distribution of the initial condition. The contrast between the frequentist and the Bayesian at prior estimation of the autoregression disappears once we make the same assumption about the initial condition in both approaches.

Keywords: Bayesian estimation; bias correction; autoregression; initial condition; small sample distribution (search for similar items in EconPapers)
JEL-codes: C11 C22 C32 (search for similar items in EconPapers)
Date: 2015-09
New Economics Papers: this item is included in nep-ecm and nep-ets
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://bw.bse.eu/wp-content/uploads/2015/09/776-file.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bge:wpaper:776

Access Statistics for this paper

More papers in Working Papers from Barcelona School of Economics Contact information at EDIRC.
Bibliographic data for series maintained by Bruno Guallar ().