Modeling of the learning process in centipede games

Anton WESTVELD III, Peter David Hoff

    Research output: Contribution to journalArticle

    Abstract

    According to classic game theory, individuals playing a centipede game learn about the subgame perfect Nash equilibrium via repeated play of the game. We employ statistical modeling to evaluate the evidence of such learning processes while accounting for the substantial within-player correlation observed for the players' decisions and rates of learning. We determine the probabilities of players' choices through a quantal response equilibrium. Our statistical approach additionally (i) relaxes the assumption of players' a priori global knowledge of opponents' strategies, (ii) incorporates within-subject dependency through random effects, and (iii) allows players' decision probabilities to change with repeated play through an explicit covariate. Hence, players' tendencies to correctly assess the utility of decisions are allowed to evolve over the course of the game, and both adaptive behavior as one accrues experience and the difference in this behavior between players are appropriately reflected by the model.
    Original languageEnglish
    Pages (from-to)242-254
    Number of pages13
    JournalStat
    Volume2
    Issue number1
    DOIs
    Publication statusPublished - 2013

    Fingerprint

    Centipede game
    Modeling
    Learning process
    Covariates
    Game theory
    Random effects
    Quantal response equilibrium
    Subgame perfect Nash equilibrium
    Adaptive behavior

    Cite this

    WESTVELD III, A., & Hoff, P. D. (2013). Modeling of the learning process in centipede games. Stat, 2(1), 242-254. https://doi.org/10.1002/sta4.32
    WESTVELD III, Anton ; Hoff, Peter David. / Modeling of the learning process in centipede games. In: Stat. 2013 ; Vol. 2, No. 1. pp. 242-254.
    @article{7c96be5d819d4ef5bbd8a5c69fd5e61d,
    title = "Modeling of the learning process in centipede games",
    abstract = "According to classic game theory, individuals playing a centipede game learn about the subgame perfect Nash equilibrium via repeated play of the game. We employ statistical modeling to evaluate the evidence of such learning processes while accounting for the substantial within-player correlation observed for the players' decisions and rates of learning. We determine the probabilities of players' choices through a quantal response equilibrium. Our statistical approach additionally (i) relaxes the assumption of players' a priori global knowledge of opponents' strategies, (ii) incorporates within-subject dependency through random effects, and (iii) allows players' decision probabilities to change with repeated play through an explicit covariate. Hence, players' tendencies to correctly assess the utility of decisions are allowed to evolve over the course of the game, and both adaptive behavior as one accrues experience and the difference in this behavior between players are appropriately reflected by the model.",
    author = "{WESTVELD III}, Anton and Hoff, {Peter David}",
    year = "2013",
    doi = "10.1002/sta4.32",
    language = "English",
    volume = "2",
    pages = "242--254",
    journal = "Stat",
    issn = "2049-1573",
    number = "1",

    }

    WESTVELD III, A & Hoff, PD 2013, 'Modeling of the learning process in centipede games', Stat, vol. 2, no. 1, pp. 242-254. https://doi.org/10.1002/sta4.32

    Modeling of the learning process in centipede games. / WESTVELD III, Anton; Hoff, Peter David.

    In: Stat, Vol. 2, No. 1, 2013, p. 242-254.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Modeling of the learning process in centipede games

    AU - WESTVELD III, Anton

    AU - Hoff, Peter David

    PY - 2013

    Y1 - 2013

    N2 - According to classic game theory, individuals playing a centipede game learn about the subgame perfect Nash equilibrium via repeated play of the game. We employ statistical modeling to evaluate the evidence of such learning processes while accounting for the substantial within-player correlation observed for the players' decisions and rates of learning. We determine the probabilities of players' choices through a quantal response equilibrium. Our statistical approach additionally (i) relaxes the assumption of players' a priori global knowledge of opponents' strategies, (ii) incorporates within-subject dependency through random effects, and (iii) allows players' decision probabilities to change with repeated play through an explicit covariate. Hence, players' tendencies to correctly assess the utility of decisions are allowed to evolve over the course of the game, and both adaptive behavior as one accrues experience and the difference in this behavior between players are appropriately reflected by the model.

    AB - According to classic game theory, individuals playing a centipede game learn about the subgame perfect Nash equilibrium via repeated play of the game. We employ statistical modeling to evaluate the evidence of such learning processes while accounting for the substantial within-player correlation observed for the players' decisions and rates of learning. We determine the probabilities of players' choices through a quantal response equilibrium. Our statistical approach additionally (i) relaxes the assumption of players' a priori global knowledge of opponents' strategies, (ii) incorporates within-subject dependency through random effects, and (iii) allows players' decision probabilities to change with repeated play through an explicit covariate. Hence, players' tendencies to correctly assess the utility of decisions are allowed to evolve over the course of the game, and both adaptive behavior as one accrues experience and the difference in this behavior between players are appropriately reflected by the model.

    U2 - 10.1002/sta4.32

    DO - 10.1002/sta4.32

    M3 - Article

    VL - 2

    SP - 242

    EP - 254

    JO - Stat

    JF - Stat

    SN - 2049-1573

    IS - 1

    ER -