@techreport{Hu2010Nonparametric,
abstract = {How do people learn? We assess, in a distribution-free manner, subjects' learning and choice rules in dynamic two-armed bandit (probabilistic reversal learning) experiments. To aid in identification and estimation, we use auxiliary measures of subjects' beliefs, in the form of their eye-movements during the experiment. Our estimated choice probabilities and learning rules have some distinctive features; notably that subjects tend to update in a non-smooth manner following choices made in accordance with current beliefs. Moreover, the beliefs implied by our nonparametric learning rules are closer to those from a (non-Bayesian) reinforcement learning model, than a Bayesian learning model.},
address = {Baltimore, Md.},
author = {Yingyao Hu and Yutaka Kayaba and Matt Shum},
copyright = {http://www.econstor.eu/dspace/Nutzungsbedingungen},
keywords = {D83; C91; C14; 330; Learning; experiments; eye-tracking; Bayesian vs. non-Bayesian learning; nonparametric estimation; Sch\"{a}tztheorie; Lernen; Nichtparametrisches Verfahren; Simulation; Dynamisches Modell},
language = {eng},
number = {560},
publisher = {Johns Hopkins Univ., Dep. of Economics},
title = {Nonparametric learning rules from bandit experiments: The eyes have it!},
type = {Working papers // the Johns Hopkins University, Department of Economics},
url = {http://hdl.handle.net/10419/49877},
year = {2010}
}
