“…Researchers have for instance considered uncertainty about the parameters of the model and have used Bayesian methods to determine the policy that minimizes the expected loss, given a prior distribution on the parameters. This approach, initially started by Brainard (1967) and developed by Chow (1975) has more recently been followed by Clarida et al (1999), Wieland (1998), Estrella and Mishkin (1999), Hall et al (1999), Martin and Salmon (1999), Svensson (1999), Sack (2000), Rudebusch (2001), Söderström (2000Söderström ( , 2002, and Kurozumi (2003) among others. Most of these studies focus on backward-looking models, and support Brainard's popular result that optimal policy should be less aggressive in the face of parameter uncertainty.…”