Assessing the performance of estimators dealing with measurement errors

Heitor Almeida, Murillo Campello, Antonio F. Galvao

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

We describe different procedures to deal with measurement error in linear models and assess their performance in finite samples using Monte Carlo simulations and data on corporate investment. We consider the standard instrumental variable approach proposed by Griliches and Hausman (Journal of Econometrics 31:93–118, 1986) as extended by Biorn (Econometric Reviews 19:391–424, 2000) [OLS-IV], the Arellano and Bond (Review of Economic Studies 58:277–297, 1991) instrumental variable estimator, and the higher-order moment estimator proposed by Erickson and Whited (Journal of Political Economy 108:1027–1057, 2000, Econometric Theory 18:776–799, 2002). Our analysis focuses on characterizing the conditions under which each of these estimators produce unbiased and efficient estimates in a standard “errors-invariables” setting. In the presence of fixed effects, under heteroscedasticity, or in the absence of a very high degree of skewness in the data, the EW estimator is inefficient and returns biased estimates for mismeasured and perfectly measured regressors. In contrast to the EW estimator, IV–type estimators (OLS–IV and AB-GMM) easily handle individual effects, heteroscedastic errors, and different degrees of data skewness. The IV approach, however, requires assumptions about the autocorrelation structure of the mismeasured regressor and the measurement error. We illustrate the application of the different estimators using empirical investment models. Our results show that the EW estimator produces inconsistent results when applied to real-world investment data, while the IV estimators tend to return results that are consistent with theoretical priors.​

LanguageEnglish (US)
Title of host publicationHandbook of Financial Econometrics and Statistics
PublisherSpringer New York
Pages1563-1617
Number of pages55
ISBN (Electronic)9781461477501
ISBN (Print)9781461477495
DOIs
StatePublished - Jan 1 2015

Fingerprint

Measurement Error
Estimator
Econometrics
Instrumental Variables
Skewness
Empirical Estimator
Heteroscedastic Errors
Higher Order Moments
Moment Estimator
Efficient Estimator
Heteroscedasticity
Fixed Effects
Unbiased estimator
Standard error
Autocorrelation
Inconsistent
Estimate
Biased
Measurement error
Linear Model

ASJC Scopus subject areas

  • Economics, Econometrics and Finance(all)
  • Business, Management and Accounting(all)
  • Mathematics(all)

Cite this

Almeida, H., Campello, M., & Galvao, A. F. (2015). Assessing the performance of estimators dealing with measurement errors. In Handbook of Financial Econometrics and Statistics (pp. 1563-1617). Springer New York. DOI: 10.1007/978-1-4614-7750-1_57

Assessing the performance of estimators dealing with measurement errors. / Almeida, Heitor; Campello, Murillo; Galvao, Antonio F.

Handbook of Financial Econometrics and Statistics. Springer New York, 2015. p. 1563-1617.

Research output: Chapter in Book/Report/Conference proceedingChapter

Almeida, H, Campello, M & Galvao, AF 2015, Assessing the performance of estimators dealing with measurement errors. in Handbook of Financial Econometrics and Statistics. Springer New York, pp. 1563-1617. DOI: 10.1007/978-1-4614-7750-1_57
Almeida H, Campello M, Galvao AF. Assessing the performance of estimators dealing with measurement errors. In Handbook of Financial Econometrics and Statistics. Springer New York. 2015. p. 1563-1617. Available from, DOI: 10.1007/978-1-4614-7750-1_57
Almeida, Heitor ; Campello, Murillo ; Galvao, Antonio F./ Assessing the performance of estimators dealing with measurement errors. Handbook of Financial Econometrics and Statistics. Springer New York, 2015. pp. 1563-1617
@inbook{328e0273d31a45dc9c78e4c869a06a98,
title = "Assessing the performance of estimators dealing with measurement errors",
abstract = "We describe different procedures to deal with measurement error in linear models and assess their performance in finite samples using Monte Carlo simulations and data on corporate investment. We consider the standard instrumental variable approach proposed by Griliches and Hausman (Journal of Econometrics 31:93–118, 1986) as extended by Biorn (Econometric Reviews 19:391–424, 2000) [OLS-IV], the Arellano and Bond (Review of Economic Studies 58:277–297, 1991) instrumental variable estimator, and the higher-order moment estimator proposed by Erickson and Whited (Journal of Political Economy 108:1027–1057, 2000, Econometric Theory 18:776–799, 2002). Our analysis focuses on characterizing the conditions under which each of these estimators produce unbiased and efficient estimates in a standard “errors-invariables” setting. In the presence of fixed effects, under heteroscedasticity, or in the absence of a very high degree of skewness in the data, the EW estimator is inefficient and returns biased estimates for mismeasured and perfectly measured regressors. In contrast to the EW estimator, IV–type estimators (OLS–IV and AB-GMM) easily handle individual effects, heteroscedastic errors, and different degrees of data skewness. The IV approach, however, requires assumptions about the autocorrelation structure of the mismeasured regressor and the measurement error. We illustrate the application of the different estimators using empirical investment models. Our results show that the EW estimator produces inconsistent results when applied to real-world investment data, while the IV estimators tend to return results that are consistent with theoretical priors.​",
author = "Heitor Almeida and Murillo Campello and Galvao, {Antonio F.}",
year = "2015",
month = "1",
day = "1",
doi = "10.1007/978-1-4614-7750-1_57",
language = "English (US)",
isbn = "9781461477495",
pages = "1563--1617",
booktitle = "Handbook of Financial Econometrics and Statistics",
publisher = "Springer New York",

}

TY - CHAP

T1 - Assessing the performance of estimators dealing with measurement errors

AU - Almeida,Heitor

AU - Campello,Murillo

AU - Galvao,Antonio F.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - We describe different procedures to deal with measurement error in linear models and assess their performance in finite samples using Monte Carlo simulations and data on corporate investment. We consider the standard instrumental variable approach proposed by Griliches and Hausman (Journal of Econometrics 31:93–118, 1986) as extended by Biorn (Econometric Reviews 19:391–424, 2000) [OLS-IV], the Arellano and Bond (Review of Economic Studies 58:277–297, 1991) instrumental variable estimator, and the higher-order moment estimator proposed by Erickson and Whited (Journal of Political Economy 108:1027–1057, 2000, Econometric Theory 18:776–799, 2002). Our analysis focuses on characterizing the conditions under which each of these estimators produce unbiased and efficient estimates in a standard “errors-invariables” setting. In the presence of fixed effects, under heteroscedasticity, or in the absence of a very high degree of skewness in the data, the EW estimator is inefficient and returns biased estimates for mismeasured and perfectly measured regressors. In contrast to the EW estimator, IV–type estimators (OLS–IV and AB-GMM) easily handle individual effects, heteroscedastic errors, and different degrees of data skewness. The IV approach, however, requires assumptions about the autocorrelation structure of the mismeasured regressor and the measurement error. We illustrate the application of the different estimators using empirical investment models. Our results show that the EW estimator produces inconsistent results when applied to real-world investment data, while the IV estimators tend to return results that are consistent with theoretical priors.​

AB - We describe different procedures to deal with measurement error in linear models and assess their performance in finite samples using Monte Carlo simulations and data on corporate investment. We consider the standard instrumental variable approach proposed by Griliches and Hausman (Journal of Econometrics 31:93–118, 1986) as extended by Biorn (Econometric Reviews 19:391–424, 2000) [OLS-IV], the Arellano and Bond (Review of Economic Studies 58:277–297, 1991) instrumental variable estimator, and the higher-order moment estimator proposed by Erickson and Whited (Journal of Political Economy 108:1027–1057, 2000, Econometric Theory 18:776–799, 2002). Our analysis focuses on characterizing the conditions under which each of these estimators produce unbiased and efficient estimates in a standard “errors-invariables” setting. In the presence of fixed effects, under heteroscedasticity, or in the absence of a very high degree of skewness in the data, the EW estimator is inefficient and returns biased estimates for mismeasured and perfectly measured regressors. In contrast to the EW estimator, IV–type estimators (OLS–IV and AB-GMM) easily handle individual effects, heteroscedastic errors, and different degrees of data skewness. The IV approach, however, requires assumptions about the autocorrelation structure of the mismeasured regressor and the measurement error. We illustrate the application of the different estimators using empirical investment models. Our results show that the EW estimator produces inconsistent results when applied to real-world investment data, while the IV estimators tend to return results that are consistent with theoretical priors.​

UR - http://www.scopus.com/inward/record.url?scp=84945151348&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945151348&partnerID=8YFLogxK

U2 - 10.1007/978-1-4614-7750-1_57

DO - 10.1007/978-1-4614-7750-1_57

M3 - Chapter

SN - 9781461477495

SP - 1563

EP - 1617

BT - Handbook of Financial Econometrics and Statistics

PB - Springer New York

ER -