Bayesian Model Averaging, Learning, and Model Selection*

Evans, George W.; Honkapohja, Seppo; Sargent, Thomas J.; Williams, Noah

doi:10.1093/acprof:oso/9780199666126.003.0007

Cited by 15 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A plausible learning algorithm could entail an endogenous switch between di¤erent gains, depending perhaps on the forecasting performance of the implied beliefs. Building on ideas …rst proposed by Brock and Hommes (1997), Marcet and Nicolini (2003), Evans, Honkapohja, Sargent, and Williams (2012) and Milani (2014) implement versions of such an algorithm.…”

Section: Further Directionsmentioning

confidence: 99%

The Science of Monetary Policy: An Imperfect Knowledge Perspective

Eusepi

Preston

2018

Journal of Economic Literature

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. "I think of economics as studying decision rules that are steady states of some adaptive process, decision rules that are found to work over a range of situations and hence are no longer revised appreciably as more experience accumulates." Robert E. Lucas Jr "Rational expectations imposes two requirements on economic models: individual rationality and mutual consistency of perception about the environment. [...] I interpret a proposal to build models with 'boundedly rational'agents as a call to retreat from the second piece of rational expectations (mutual consistency of perceptions) by expelling rational agents from our model's environment and replacing them with 'arti…cially intelligent' agents who behave like econometricians." Terms of use: Documents inThomas Sargent "The traditional rational-expectations model of in ‡ation and in ‡ation expectations has been a useful workhorse for thinking about issues of credibility and institutional design, but, to my mind, it is less helpful for thinking about economies in which (1) the structure of the economy is constantly evolving in ways that are imperfectly understood by both the public and policymakers and (2) the policymakers'objective function is not fully known by private agents. In particular, together with the assumption that the central bank's objective function is …xed and known to the public, the traditional rational-expectations approach implies that the public has …rm knowledge of the long-run equilibrium in ‡ation rate; consequently, their long-run in ‡ation expectations do not vary over time in response to new information."Ben S. BernankeThe authors thank Jim Bullard, Marc Giannoni and Mike Woodford for on-going discussions about much of the material contained here-in, and also a number of anonymous referees and the editors Janet Currie and Steven Durlauf for constructive feedback.

show abstract

Section: Further Directionsmentioning

confidence: 99%

The Science of Monetary Policy: An Imperfect Knowledge Perspective

Eusepi

Preston

2018

Journal of Economic Literature

View full text Add to dashboard Cite

show abstract

“…Conversely, when β < 1/2 ⇔ c > 1/2, then y t is already close toȳ and hence convergence towards it is slow. Indeed, the threshold of 1/2 is reminiscent of a similar boundary discussed in Evans et al (2013). In view of the aforementioned trade-o between the behaviour of a t and that of β T , one should expect the converse for the performance of β T .…”

Section: ȳ)mentioning

confidence: 89%

“…Christopeit & Massmann (2010) for details. Indeed, while most of the models in the literature presume that β ∈ (0, 1), there are some that consider negative values; see, for example, Evans, Honkapohja, Sargent & Williams (2013) and Brock & Hommes (1997) who analyse cobweb-type models with −0.5 < β < 1 and β < −1, respectively. With the question of convergence under decreasing gain settled, it is surprising that the second of the two questions above has to-date only received scarce attention in the literature.…”

Section: Introductionmentioning

confidence: 99%

Estimating Structural Parameters in Regression Models with Adaptive Learning

Christopeit

Massmann

2013

SSRN Journal

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in AbstractThis paper examines the ordinary least squares (OLS) estimator of the structural parameters in a class of stylised macroeconomic models in which agents are boundedly rational and use an adaptive learning rule to form expectations of the endogenous variable. The popularity of this type of model has recently increased amongst applied economists and policy makers who seek to estimate it empirically. Two prominent learning algorithms are considered, namely constant gain and decreasing gain learning. For each of the two learning rules, the analysis proceeds in two stages. First, the paper derives the asymptotic properties of agents' expectations. At the second stage, the paper derives the asymptotics of OLS in the structural model, taken the rst stage learning dynamics as given. In the case of constant gain learning, the structural model eectively amounts to a static, cointegrating or co-explosiveness regression. With decreasing gain learning, the regressors are asymptotically collinear such that OLS does not satisfy, in general, the Grenander conditions for consistent estimability. Nevertheless, this paper shows that the OLS estimator remains consistent in all models considered. It also shows, however, that its asymptotic distribution, and hence any inference based upon it, may be non-standard.

show abstract

“…Our analysis is inspired by the previous work of Evans, Honkapohja, Sargent, and Williams (2013). They study a standard cobweb model, in which a single agent considers two models, one with constant parameters and one with time-varying parameters.…”

Section: To Believe Is To Seementioning

confidence: 99%

Gresham's Law of Model Averaging

Cho

Kasa

2017

American Economic Review

View full text Add to dashboard Cite

A decision maker doubts the stationarity of his environment. In response, he uses two models, one with time-varying parameters, and another with constant parameters. Forecasts are then based on a Bayesian model averaging strategy, which mixes forecasts from the two models. In reality, structural parameters are constant, but the (unknown) true model features expectational feedback, which the reduced-form models neglect. This feedback permits fears of parameter instability to become self-confirming. Within the context of a standard asset-pricing model, we use the tools of large deviations theory to show that even though the constant parameter model would converge to the rational expectations equilibrium if considered in isolation, the mere presence of an unstable alternative drives it out of consideration. (JEL C63, D83, D84)

show abstract

Bayesian Model Averaging, Learning, and Model Selection*

Cited by 15 publications

References 8 publications

The Science of Monetary Policy: An Imperfect Knowledge Perspective

The Science of Monetary Policy: An Imperfect Knowledge Perspective

Estimating Structural Parameters in Regression Models with Adaptive Learning

Gresham's Law of Model Averaging

Contact Info

Product

Resources

About