Pitfalls of estimating the marginal likelihood using the modified harmonic mean

被引：16
|
作者：
Chan, Joshua C. C. [1 ]
Grant, Angelia L. [2 ]
机构：
[1] Australian Natl Univ, Res Sch Econ, Canberra, ACT 2601, Australia
[2] Australian Natl Univ, Ctr Appl Macroecon Anal, Canberra, ACT 2601, Australia
来源：
ECONOMICS LETTERS | 2015年 / 131卷
基金：
澳大利亚研究理事会;
关键词：
Bayesian model comparison; State space; Unobserved components; Inflation; STOCHASTIC VOLATILITY MODELS; MACROECONOMIC FLUCTUATIONS; INFLATION; FORECAST;
D O I：
10.1016/j.econlet.2015.03.036
中图分类号：
F [经济];
学科分类号：
02 ;
摘要：
The modified harmonic mean is widely used for estimating the marginal likelihood. We investigate the empirical performance of two versions of this estimator: one based on the observed-data likelihood and the other on the complete-data likelihood. Through an empirical example using US and UK inflation, we show that the version based on the complete-data likelihood has a substantial bias and tends to select the wrong model, whereas the version based on the observed-data likelihood works well. (C) 2015 Elsevier B.V. All rights reserved.
引用
收藏
页码：29 / 33
页数：5
相关论文
共 50 条
  • [1] Estimating the Marginal Likelihood Using the Arithmetic Mean Identity
    Pajor, Anna
    [J]. BAYESIAN ANALYSIS, 2017, 12 (01): : 261 - 287
  • [2] OPTIMALITY OF MARGINAL LIKELIHOOD ESTIMATING EQUATIONS
    LLOYD, CJ
    [J]. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 1987, 16 (06) : 1733 - 1741
  • [3] Completeness and Optimality of Marginal Likelihood Estimating Equations
    [J]. Commun Stat Part A Theory Methods, 4 (945):
  • [4] COMPLETENESS AND OPTIMALITY OF MARGINAL LIKELIHOOD ESTIMATING EQUATIONS
    BHAPKAR, VP
    [J]. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 1995, 24 (04) : 945 - 952
  • [5] IMPROVED PRODUCT-TYPE ESTIMATOR FOR ESTIMATING POPULATION MEAN USING HARMONIC MEAN
    Sahoo, Nirupama
    Jena, Saradaprasan
    [J]. INTERNATIONAL JOURNAL OF AGRICULTURAL AND STATISTICAL SCIENCES, 2024, 20 (01): : 195 - 201
  • [6] An Approximate Bayesian Marginal Likelihood Approach for Estimating Finite Mixtures
    Martin, Ryan
    [J]. COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 2013, 42 (07) : 1533 - 1548
  • [7] Learning Invariances using the Marginal Likelihood
    van der Wilk, Mark
    Bauer, Matthias
    John, S. T.
    Hensman, James
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [8] α-STABLE LIMIT LAWS FOR HARMONIC MEAN ESTIMATORS OF MARGINAL LIKELIHOODS
    Wolpert, Robert L.
    Schmidler, Scott C.
    [J]. STATISTICA SINICA, 2012, 22 (03) : 1233 - 1251
  • [9] Quantifying the closeness to a set of random curves via the mean marginal likelihood
    Rommel, Cedric
    Frederic Bonnans, J.
    Gregorutti, Baptiste
    Martinon, Pierre
    [J]. ESAIM-PROBABILITY AND STATISTICS, 2021, 25 : 1 - 30
  • [10] Robustly estimating the marginal likelihood for cognitive models via importance sampling
    M.-N. Tran
    M. Scharth
    D. Gunawan
    R. Kohn
    S. D. Brown
    G. E. Hawkins
    [J]. Behavior Research Methods, 2021, 53 : 1148 - 1165
12345