LSE LSE Research Laboratory LSE
LSE Research Laboratory (RLAB)

Abstract for:

Autoregressions in Small Samples, Priors about Observables and Initial Conditions

Marek  Jarocinski,  Albert  Marcet,  July 2011
Paper No' CEPDP1061: | Full paper (pdf)
Save Reference as: BibTeX BibTeX File | Endote EndNote Import File
Keywords: Vector autoregression; initial condition, bayesian estimation, prior about growth rate, monetary policy shocks, small sample distribution, bias correction

JEL Classification: C11; C22; C32

Is hard copy/paper copy available? YES - Paper Copy Still In Print.
This Paper is published under the following series: CEP Discussion Papers
Share this page: Google Bookmarks Google Bookmarks | Facebook Facebook | Twitter Twitter


We propose a benchmark prior for the estimation of vector autoregressions: a prior about initial growth rates of the modelled series. We first show that the Bayesian vs frequentist small sample bias controversy is driven by different default initial conditions. These initial conditions are usually arbitrary and our prior serves to replace them in an intuitive way. To implement this prior we develop a technique for translating priors about observables into priors about parameters. We find that our prior makes a big difference for the estimated persistence of output responses to monetary policy shocks in the United States.