Sensitivity analysis for inference in 2SLS/GMM estimation with possibly flawed instruments

Richard A. Ashley, Christopher Parmeter

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Credible inference requires attention to the possible fragility of the results (p values for key hypothesis tests) to flaws in the model assumptions, notably accounting for the validity of the instruments used. Past sensitivity analysis has mainly consisted of experimentation with alternative model specifications and with tests of over-identifying restrictions which actually presuppose instrument validity. We provide a feasible sensitivity analysis of two-stage least-squares and GMM estimation, quantifying the fragility/robustness of inference with respect to possible flaws in the exogeneity assumptions made, and also indicating which of these assumptions are most crucial. The method is illustrated via application to a well-known study of the education–earnings relationship.

Original languageEnglish (US)
Pages (from-to)1153-1171
Number of pages19
JournalEmpirical Economics
Volume49
Issue number4
DOIs
StatePublished - Dec 1 2015

Fingerprint

Sensitivity Analysis
Two-stage Least Squares
Model Specification
Hypothesis Test
p-Value
Experimentation
Robustness
Restriction
Alternatives
Fragility
Sensitivity analysis
Inference
GMM estimation
Model
Hypothesis test
P value
Exogeneity
Two-stage least squares
Model specification
Alternative models

Keywords

  • Flawed instruments
  • Instrumental variables
  • Invalid instruments
  • Robustness
  • Sensitivity analysis
  • Two-stage least squares

ASJC Scopus subject areas

  • Economics and Econometrics
  • Social Sciences (miscellaneous)
  • Mathematics (miscellaneous)
  • Statistics and Probability

Cite this

Sensitivity analysis for inference in 2SLS/GMM estimation with possibly flawed instruments. / Ashley, Richard A.; Parmeter, Christopher.

In: Empirical Economics, Vol. 49, No. 4, 01.12.2015, p. 1153-1171.

Research output: Contribution to journalArticle

@article{42b1bac109124e5fbfe2ea09a0c34fb9,
title = "Sensitivity analysis for inference in 2SLS/GMM estimation with possibly flawed instruments",
abstract = "Credible inference requires attention to the possible fragility of the results (p values for key hypothesis tests) to flaws in the model assumptions, notably accounting for the validity of the instruments used. Past sensitivity analysis has mainly consisted of experimentation with alternative model specifications and with tests of over-identifying restrictions which actually presuppose instrument validity. We provide a feasible sensitivity analysis of two-stage least-squares and GMM estimation, quantifying the fragility/robustness of inference with respect to possible flaws in the exogeneity assumptions made, and also indicating which of these assumptions are most crucial. The method is illustrated via application to a well-known study of the education–earnings relationship.",
keywords = "Flawed instruments, Instrumental variables, Invalid instruments, Robustness, Sensitivity analysis, Two-stage least squares",
author = "Ashley, {Richard A.} and Christopher Parmeter",
year = "2015",
month = "12",
day = "1",
doi = "10.1007/s00181-015-0916-0",
language = "English (US)",
volume = "49",
pages = "1153--1171",
journal = "Empirical Economics",
issn = "0377-7332",
publisher = "Physica-Verlag",
number = "4",

}

TY - JOUR

T1 - Sensitivity analysis for inference in 2SLS/GMM estimation with possibly flawed instruments

AU - Ashley, Richard A.

AU - Parmeter, Christopher

PY - 2015/12/1

Y1 - 2015/12/1

N2 - Credible inference requires attention to the possible fragility of the results (p values for key hypothesis tests) to flaws in the model assumptions, notably accounting for the validity of the instruments used. Past sensitivity analysis has mainly consisted of experimentation with alternative model specifications and with tests of over-identifying restrictions which actually presuppose instrument validity. We provide a feasible sensitivity analysis of two-stage least-squares and GMM estimation, quantifying the fragility/robustness of inference with respect to possible flaws in the exogeneity assumptions made, and also indicating which of these assumptions are most crucial. The method is illustrated via application to a well-known study of the education–earnings relationship.

AB - Credible inference requires attention to the possible fragility of the results (p values for key hypothesis tests) to flaws in the model assumptions, notably accounting for the validity of the instruments used. Past sensitivity analysis has mainly consisted of experimentation with alternative model specifications and with tests of over-identifying restrictions which actually presuppose instrument validity. We provide a feasible sensitivity analysis of two-stage least-squares and GMM estimation, quantifying the fragility/robustness of inference with respect to possible flaws in the exogeneity assumptions made, and also indicating which of these assumptions are most crucial. The method is illustrated via application to a well-known study of the education–earnings relationship.

KW - Flawed instruments

KW - Instrumental variables

KW - Invalid instruments

KW - Robustness

KW - Sensitivity analysis

KW - Two-stage least squares

UR - http://www.scopus.com/inward/record.url?scp=84951877050&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951877050&partnerID=8YFLogxK

U2 - 10.1007/s00181-015-0916-0

DO - 10.1007/s00181-015-0916-0

M3 - Article

VL - 49

SP - 1153

EP - 1171

JO - Empirical Economics

JF - Empirical Economics

SN - 0377-7332

IS - 4

ER -