IV Estimation with Heteroskedasticity and Many Instruments

Abstract

It is common practice in econometrics to correct for heteroskedas- ticity. This paper does this for instrumental variables estimation with many in- struments. We give a heteroskedasticity robust versions of the limited information maximum likelihood (LIML) and Fuller (1977, FULL) estimators and heteroskedas- ticity consistent standard errors. These estimators are based on removing the own observations terms in the numerator of a variance ratio. We give asymptotic theory under many and many weak instruments. We …nd in Monte Carlo results that these estimators perform as well or better than LIML or FULL with heteroskedasticity in nearly all cases.

Keywords

HeteroscedasticityEstimatorEconometricsInstrumental variableMonte Carlo methodVariance (accounting)EstimationMathematicsMaximum likelihoodStatisticsEconomics

Related Publications

Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation

Robert F. Engle

Traditional econometric models assume a constant one-period forecast variance. To generalize this implausible assumption, a new class of stochastic processes called autoregressi...

1982 Econometrica 20147 citations

The many weak instruments problem and Mendelian randomization

Neil M Davies , Stephanie von Hinke , Helmut Farbmacher +3 more

Instrumental variable estimates of causal effects can be biased when using many instruments that are only weakly associated with the exposure. We describe several techniques to ...

2014 Statistics in Medicine 145 citations

Semiparametric ARCH Models

Robert F. Engle , Gloria González‐Rivera

This article introduces a semiparametric autoregressive conditional heteroscedasticity (ARCH) model that has conditional first and second moments given by autoregressive moving ...

1991 Journal of Business and Economic Stat... 477 citations

Econometric Analysis of Cross Section and Panel Data

Jeffrey M. Wooldridge

The second edition of this acclaimed graduate text provides a unified treatment of two methods used in contemporary econometric research, cross section and data panel methods. B...

2001 RePEc: Research Papers in Economics 28313 citations

Modelling the persistence of conditional variances

Robert F. Engle , Tim Bollerslev

This paper will discuss the current research in building models of conditional variances using the Autoregressive Conditional Heteroskedastic (ARCH) and Generalized ARCH (GARCH)...

1986 Econometric Reviews 2042 citations

Publication Info

Year: 2007
Type: article
Citations: 10
Access: Closed

External Links

Citation Metrics

OpenAlex

Cite This

APA Style

                            
                                    Jerry A. Hausman, 
                                
                                    Whitney K. Newey, 
                                
                                    Tiemen Woutersen
                                
                            (2007). 
                            IV Estimation with Heteroskedasticity and Many Instruments. 
                            
                            .