Please use this identifier to cite or link to this item:
Christopeit, Norbert
Massmann, Michael
Year of Publication: 
Series/Report no.: 
Tinbergen Institute Discussion Paper 15-106/III
This 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 first stage learning dynamics as given. In the case of constant gain learning, the structural model effectively 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.
adaptive learning
non-stationary regression
ordinary least squares
asymptotic distribution
Document Type: 
Working Paper

Files in This Item:
593.61 kB

Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.