Measurement Error Models with Auxiliary Data

By Xiaohong Chen, Han Hong, Elie Tamer. 2005

196 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/ccc6ab9f83011a45736a0b74d4940e46e35e8c37

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

Calculating Comparable Statistics From Incomparable Surveys, With an Application to Poverty in India (2004, methodology): “Chen et al. (2005a) proposed an alternative semiparametric two-step estimator in which the first step is a sievebased nonparametric estimation of the conditional expectation of g(y;φ0) given v. Chen et al. (2005b) also considered estimation with a parametric or nonparametric inverse probability…”
Sieve estimation of panel data models with cross section dependence (2012, methodology): “To allow for the unboundedness of Xi (e.g., Xi = Rd), we follow Chen et al. (2005) (see also Blundell et al. (2007)) and use a weighted sup-norm metric defined as ∥gi∥∞,ω ≡ sup x∈Xi |gi(x)|[1 + ∥x∥2]−ω/2 for some ω ≥ 0.”
Identification and Estimation of Regression Models with Misclassification (2006, unknown): “Chen, Hong, and Tamer (2002) relax the independence assumptions between errors and the true values of the variables in the presence of an auxiliary data set and derive distribution theory for estimates based on nonlinear unconditional moment restrictions.”
Series estimation under cross-sectional dependence (2013, methodology): “Chen et al. (2005) noted that the weight function (1 + ∥x∥2)−w/2 used here could be regarded as an alternative to the trimming used in kernel estimation when support is unbounded, X = Rq. Conditions imposing an upper bound on κ may necessitate stronger smoothness ofm.”
Chapter 76 Large Sample Sieve Estimation of Semi-Nonparametric Models (2007, methodology): “Chen et al. (2005) made use of spline sieves to estimate nonlinear non-classical measurement error models with an auxiliary sample.”
Testing Models With Multiple Equilibria by Quantile Methods (2009, background): “In some applications, these assumptions may be justified, but in others they are merely convenient (e.g. see Chen, Hong, and Tamer (2005) for an excellent discussion).”
Semiparametric efficiency in GMM models with auxiliary data (2007, unknown): “Our results can also be applied to the estimation of parametric nonlinear models with nonclassical measurement errors with validation data, a topic that has been studied in [6], [29], [5], [20], [8] among others.”
Efficiency Bounds for Missing Data Models with Semiparametric Restrictions (2008, result): “= D p0 (X) (Z; 0) q (X; 0) p0 (X) (D p0 (X)) : That this population residual is equal to the e¢ cient score function derived by Robins, Rotnitzky and Zhao (1994) strongly suggests an equivalence between the GMM problem de ned by restrictions (4) and (5) and the MAR setup outlined above.”
Regression Discontinuity Design with Continuous Measurement Error in the Running Variable (2017, unknown): “Note also that the approach of Chen et al. (2005) requires a parametric model for T (z∗), while we do not need any parametric assumption here.”
Using Census and Survey Data to Estimate Poverty and Inequality for Small Areas (2009, methodology): “In this case the requirement is that the distribution of the mis-measured variables conditional on a set of proxies is the same in the main and in the auxiliary sample (see e.g. Lee and Sepanski (1995), Chen et al. (2005), Chen et al. (2007)).”
Bias From Censored Regressors (2009, background): “The question of interest is what happens if we estimate the model yi = a+ bx cen i + f 0 wi + ui i = 1; :::; n; (3) How are the estimates â; b̂; f̂ biased as estimators of ; ; ? While the censoring process can be quite general, for our analysis of regression, we exclude the problems that arise from ”
A Test of Non-Identifying Restrictions and Confidence Regions for Partially Identified Parameters (2009, background): “In policy and program evaluation (Manski, 1990) and more general contexts with censored or missing data (Molinari, 2003, Magnac and Maurin, 2008) and measurement error (Chen et al., 2005), ad hoc imputation rules lead to fragile inference.”
Semiparametric Efficiency in GMM Models of Nonclassical Measurement Errors, Missing Data and Treatment Effects (2008, unknown): “As in Chen, Hong, and Tamer (2003), our maintained assumption is that Social Security (SS) earnings are accurate, so that we treat observations for which SS reports are available as the auxiliary dataset.”
Efficient semiparametric estimation of multi-valued treatment effects under ignorability (2010, unknown): “…where the missingness indicator is binary that involves the parametric estimation of both a regression function and the propensity score, while Chen et al. (2005) and Chen et al. (2008) study efficient GMM estimation in the context of (non-classical) measurement error models when two samples…”