Model Discovery and Trygve Haavelmo's Legacy

David Hendry; Søren Johansen

doi:10.1017/S0266466614000218

Model Discovery and Trygve Haavelmo's Legacy

David Hendry, Søren Johansen

Økonomisk Institut

20 Citationer (Scopus)

Abstract

Trygve Haavelmo's Probability Approach aimed to implement economic theories, but he later recognized their incompleteness. Although he did not explicitly consider model selection, we apply it when theory-relevant variables, {x_{t}}, are retained without selection while selecting other candidate variables, {w_{t}}. Under the null that the {w_{t}} are irrelevant, by orthogonalizing with respect to the {x_{t}}, the estimator distributions of the x_{t}'s parameters are unaffected by selection even for more variables than observations and for endogenous variables. Under the alternative, when the joint model nests the generating process, an improved outcome results from selection. This implements Haavelmo's program relatively costlessly.

Originalsprog	Engelsk
Tidsskrift	Econometric Theory
Vol/bind	31
Udgave nummer	1
Sider (fra-til)	93-114
Antal sider	22
ISSN	0266-4666
DOI	https://doi.org/10.1017/S0266466614000218
Status	Udgivet - feb. 2015

Emneord

Det Samfundsvidenskabelige Fakultet

Adgang til dokumentet

10.1017/S0266466614000218Licens: Ikke-specificeret

Citationsformater

@article{aff15df725854a8aa44805448f262a0d,

title = "Model Discovery and Trygve Haavelmo's Legacy",

abstract = "Trygve Haavelmo's Probability Approach aimed to implement economic theories, but he later recognized their incompleteness. Although he did not explicitly consider model selection, we apply it when theory-relevant variables, {x_{t}}, are retained without selection while selecting other candidate variables, {w_{t}}. Under the null that the {w_{t}} are irrelevant, by orthogonalizing with respect to the {x_{t}}, the estimator distributions of the x_{t}'s parameters are unaffected by selection even for more variables than observations and for endogenous variables. Under the alternative, when the joint model nests the generating process, an improved outcome results from selection. This implements Haavelmo's program relatively costlessly.",

keywords = "Faculty of Social Sciences, C51, C22",

author = "David Hendry and S{\o}ren Johansen",

note = "JEL classifications: C51, C22.",

year = "2015",

month = feb,

doi = "10.1017/S0266466614000218",

language = "English",

volume = "31",

pages = "93--114",

journal = "Econometric Theory",

issn = "0266-4666",

publisher = "Cambridge University Press",

number = "1",

}

TY - JOUR

T1 - Model Discovery and Trygve Haavelmo's Legacy

AU - Hendry, David

AU - Johansen, Søren

N1 - JEL classifications: C51, C22.

PY - 2015/2

Y1 - 2015/2

N2 - Trygve Haavelmo's Probability Approach aimed to implement economic theories, but he later recognized their incompleteness. Although he did not explicitly consider model selection, we apply it when theory-relevant variables, {x_{t}}, are retained without selection while selecting other candidate variables, {w_{t}}. Under the null that the {w_{t}} are irrelevant, by orthogonalizing with respect to the {x_{t}}, the estimator distributions of the x_{t}'s parameters are unaffected by selection even for more variables than observations and for endogenous variables. Under the alternative, when the joint model nests the generating process, an improved outcome results from selection. This implements Haavelmo's program relatively costlessly.

AB - Trygve Haavelmo's Probability Approach aimed to implement economic theories, but he later recognized their incompleteness. Although he did not explicitly consider model selection, we apply it when theory-relevant variables, {x_{t}}, are retained without selection while selecting other candidate variables, {w_{t}}. Under the null that the {w_{t}} are irrelevant, by orthogonalizing with respect to the {x_{t}}, the estimator distributions of the x_{t}'s parameters are unaffected by selection even for more variables than observations and for endogenous variables. Under the alternative, when the joint model nests the generating process, an improved outcome results from selection. This implements Haavelmo's program relatively costlessly.

KW - Faculty of Social Sciences

KW - C51

KW - C22

U2 - 10.1017/S0266466614000218

DO - 10.1017/S0266466614000218

M3 - Journal article

SN - 0266-4666

VL - 31

SP - 93

EP - 114

JO - Econometric Theory

JF - Econometric Theory

IS - 1

ER -