Concept-Based Bayesian Model Averaging and Growth Empirics

J.R. Magnus, W. Wang

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

In specifying a regression equation, we need to specify which regressors to include, but also how these regressors are measured. This gives rise to two levels of uncertainty: concepts (level 1) and measurements within each concept (level 2). In this paper we propose a hierarchical weighted least squares (HWALS) method to address these uncertainties. We examine the effects of different growth determinants taking explicit account of the measurement problem in the growth regressions. We find that estimates produced by HWALS provide intuitive and robust explanations. We also consider approximation techniques which are useful when the number of variables is large or when computing time is limited.
Original languageEnglish
Pages (from-to)874-897
JournalOxford Bulletin of Economics and Statistics
Volume76
Issue number6
DOIs
Publication statusPublished - 2014

Fingerprint

Bayesian Model Averaging
empirics
Regression
uncertainty
Uncertainty
regression
Weighted Least Squares
Least Square Method
Intuitive
Determinant
determinants
Computing
Approximation
Estimate
Concepts
Bayesian model averaging
Empirics
time
Growth regressions
Least square method

Bibliographical note

PT: J; NR: 31; TC: 0; J9: OXFORD B ECON STAT; PG: 24; GA: AS6BQ; UT: WOS:000344350300004

Cite this

@article{c7764e2feeb74995845460c1dd18cca6,
title = "Concept-Based Bayesian Model Averaging and Growth Empirics",
abstract = "In specifying a regression equation, we need to specify which regressors to include, but also how these regressors are measured. This gives rise to two levels of uncertainty: concepts (level 1) and measurements within each concept (level 2). In this paper we propose a hierarchical weighted least squares (HWALS) method to address these uncertainties. We examine the effects of different growth determinants taking explicit account of the measurement problem in the growth regressions. We find that estimates produced by HWALS provide intuitive and robust explanations. We also consider approximation techniques which are useful when the number of variables is large or when computing time is limited.",
author = "J.R. Magnus and W. Wang",
note = "PT: J; NR: 31; TC: 0; J9: OXFORD B ECON STAT; PG: 24; GA: AS6BQ; UT: WOS:000344350300004",
year = "2014",
doi = "10.1111/obes.12068",
language = "English",
volume = "76",
pages = "874--897",
journal = "Oxford Bulletin of Economics and Statistics",
issn = "0305-9049",
publisher = "Wiley-Blackwell",
number = "6",

}

Concept-Based Bayesian Model Averaging and Growth Empirics. / Magnus, J.R.; Wang, W.

In: Oxford Bulletin of Economics and Statistics, Vol. 76, No. 6, 2014, p. 874-897.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Concept-Based Bayesian Model Averaging and Growth Empirics

AU - Magnus, J.R.

AU - Wang, W.

N1 - PT: J; NR: 31; TC: 0; J9: OXFORD B ECON STAT; PG: 24; GA: AS6BQ; UT: WOS:000344350300004

PY - 2014

Y1 - 2014

N2 - In specifying a regression equation, we need to specify which regressors to include, but also how these regressors are measured. This gives rise to two levels of uncertainty: concepts (level 1) and measurements within each concept (level 2). In this paper we propose a hierarchical weighted least squares (HWALS) method to address these uncertainties. We examine the effects of different growth determinants taking explicit account of the measurement problem in the growth regressions. We find that estimates produced by HWALS provide intuitive and robust explanations. We also consider approximation techniques which are useful when the number of variables is large or when computing time is limited.

AB - In specifying a regression equation, we need to specify which regressors to include, but also how these regressors are measured. This gives rise to two levels of uncertainty: concepts (level 1) and measurements within each concept (level 2). In this paper we propose a hierarchical weighted least squares (HWALS) method to address these uncertainties. We examine the effects of different growth determinants taking explicit account of the measurement problem in the growth regressions. We find that estimates produced by HWALS provide intuitive and robust explanations. We also consider approximation techniques which are useful when the number of variables is large or when computing time is limited.

U2 - 10.1111/obes.12068

DO - 10.1111/obes.12068

M3 - Article

VL - 76

SP - 874

EP - 897

JO - Oxford Bulletin of Economics and Statistics

JF - Oxford Bulletin of Economics and Statistics

SN - 0305-9049

IS - 6

ER -