RANDOM EFFECTS ESTIMATORS WITH MANY INSTRUMENTAL VARIABLES

By Gary Chamberlain, Guido W. Imbens. 2004

91 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

Citations in the corpus

Instrumental Variables: An Econometrician's Perspective (2014, background): “…subsequently found that with weak instruments the TSLS estimator, especially with many instruments, was biased, and that the standard variance estimator led to confidence intervals with substantial undercoverage (Bound, Jaeger and Baker, 1995; Staiger and Stock, 1997; Chamberlain and Imbens, 2004).”
Select the Valid and Relevant Moments: An Information-Based LASSO for GMM with Many Moments (2013, methodology): “Shrinkage estimation for homoskedastic linear IV models is considered by Chamberlain and Imbens (2004) and Okui (2011).”
Estimation With Many Instrumental Variables (2006, background): “Also, the random effects estimator of Chamberlain and Imbens (2004) leads to accurate inference with many instruments.”
Spending more of the school day in math class: Evidence from a regression discontinuity in middle school (2014, methodology): “I estimate equation 2 using limited information maximum likelihood; LIML is preferable to two-stage least squares in a setting, like this, with many instruments derived from the multi-site structure of treatment assignment (Chamberlain and Imbens 2004).”
Robust priors in nonlinear panel data models (2007, background): “Specifying the a priori distribution of the fixed effects as in (15) is intuitively appealing.”
Have We Identified Effective Teachers? Validating Measures of Effective Teaching Using Random Assignment. Research Paper. MET Project. (2013, unknown): “In our setting, LIML is the optimal (maximum likelihood) estimator if we consider each school (or randomization block) as a separate experiment in which the compliance rate varied randomly across the experiments (Chamberlain and Imbens, 2004).”
Instrumental variables estimation with many weak instruments using regularized JIVE (2014, methodology): “Chamberlain and Imbens (2004) considers IV estimation with many instruments using a shrinkage estimator based on putting a Gaussian random coefficients structure over the firststage coefficients in a homoskedastic setting which is closely related to using ridge regression in the first-stage.”
Finite sample evidence of IV estimators under weak instruments (2007, methodology): “We further estimate both specifications using FULLER, BCTSLS, BCLIML, BCFULL and J2SLS, while the REQML estimate is taken from Chamberlain and Imbens (2004) .”
Consistent Estimation with a Large Number of Weak Instruments (2005, background): “Other influential papers in this area include Angrist and Krueger (1995), Donald and Newey (2001), Hahn, Hausman, and Kuersteiner (2001), Hahn (2002), Hahn and Inoue (2002), and Chamberlain and Imbens (2004).”
Massachusetts Institute of Technology Department of Economics Working Paper Series Sparse Models and Methods for Optimal Instruments with an Application to Eminent Domain Sparse Models and Methods for Optimal Instruments with an Application to Eminent Domain (unknown): “The current paper expressly allows for this case and also for " very many-instrument " asymptotics where p n. 2 [16] considers an alternate shrinkage estimator in the context of IV estimation with many instruments.”
High-dimensional econometrics and regularized GMM (2018, unknown): “See, for example, [41], [100], [37], and [71] for approaches that explicitly use regularized first-stage estimation within a dense model framework.”
Decision Theory Applied to an Instrumental Variables Model (2007, methodology): “The first version of the confidence interval procedure in Section 7, which inverts a likelihood ratio test based on the integrated likelihood function, is in Chamberlain and Imbens (2004).”
Finite Sample Inference for Quantile Regression Models (2006, unknown): “In contrast with conventional asymptotic approaches to inference in quantile models, the validity of the finite sample approach does not depend upon having a well-behaved density for Y : it does not rely on the density of Y given D = d and Z = z being continuous or differentiable in y or having conn”