The Calculus of M-Estimation

By Leonard A. Stefanski, Dennis D. Boos. 2002

530 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/8c01ead0ced53cf2288dfe435f47c93f2c7964e8

How researchers see this paper

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

In Statistics and Probability

Citations in the corpus

Object-oriented Computation of Sandwich Estimators (2006, methodology): “For the covariance matrix S ( θ ), a sandwich formula can be given (5) see Theorem 6.10 in White (1994), Chapter 5 in Cameron and Trivedi (2005), or Stefanski and Boos (2002) for further details.”
An Automatic Finite-Sample Robustness Metric: When Can Dropping a Little Data Make a Big Difference? (2020, methodology): “In the case of Z-estimators, we can show by direct computation that ˆ σ 2 ψ is the estimator of the variance of the limiting distribution of √ Nφ ( ˆ θ ) given by the delta method and the “sandwich” or “robust” covariance estimator (Huber, 1967; Stefanski and Boos, 2002).”
Democracy Does Cause Growth (2019, unknown): “Papaioannou, Elias and Gregorios Siourounis (2008) “Democratisation and Growth,” Economic Journal, 118(532), 1520–1551. Park, Joon Y. and Peter C.B. Phillips (2000) “Nonstationary Binary Choice, ” Economet-”
The IOS Test for Model Misspecification (2004, methodology): “These concerns have led to a long and continuing history of "specification tests" in the econometrics literature, beginning with Hausman (1978) and White (1982). The statistics literature also has seen renewed interest in general methods for testing model adequacy, as exemplified by work of Bayarri ”
A regression discontinuity design for ordinal running variables: Evaluating central bank purchases of corporate bonds (2019, methodology): “We derive an M-estimation-based sandwich variance estimator (Huber, 1964; van der Vaart, 1998; Stefanski and Boos, 2002) of the moment estimator (4), which accounts for the uncer-”
Strati cation and weighting via the propensity score in estimation of causal treatment e ects : a comparative study (2004, methodology): “The properties of ̂S may be derived from (26) by appealing to M -estimation arguments [18].”
Simultaneous Inference in General Parametric Models (2008, unknown): “An alternative is to apply robust estimation techniques in linear models, for example S, M-or MM-estimation (see Rousseeuw and Leroy, 2003; Stefanski and Boos, 2002; Yohai, 1987, for example), which again provide us with asymptotically normal estimates.”
A Robust Method for Estimating Optimal Treatment Regimes (2012, background): “so that the asymptotic variance of the left-hand side of (4) can be approximated by that of the leading term on the right, which can be estimated by the usual sandwich technique (Stefanski and Boos, 2002).”
Improving efficiency and robustness of the doubly robust estimator for a population mean with incomplete data (2009, methodology): “All of the estimators μ̂USUAL, μ̂PROJ and μ̂TAN involve solving jointly a set of M-estimating equations (Stefanski & Boos, 2002); for example, μ̂USUAL is found by solving the usual score equation for γ , the ordinary least-squares equation (9) and the estimating equation implied by (4).”
Entropy Balancing is Doubly Robust (2015, methodology): “Alternatively, variance estimates may be obtained via the empirical sandwich method (e.g. Stefanski and Boos, 2002).”
Bias-Reduced Doubly Robust Estimation (2015, methodology): “A modification of this IPTW estimator is also suggested in the discussion by Stijn Vansteelandt (Vansteelandt 2012) of the read paper Thas et al. (2012), see equation (40), so as to make the IPTW estimator sample bounded (SB) (Robins et al.”
Robust estimation of optimal dynamic treatment regimes for sequential treatment decisions (2013, methodology): “Standard errors for these estimators for may be obtained via the sandwich technique (Stefanski & Boos, 2002) based on the argument in Zhang et al. (2012, Equation (4)).”
Generalized M‐fluctuation tests for parameter instability (2007, result): “Proof: As the asymptotic properties of M-estimators are very similar to those of ML estimators (see e.g., White 1994; Stefanski and Boos 2002), the arguments of (Hjort and Koning 2002, Section 2.”
Cluster–Robust Variance Estimation for Dyadic Data (2013, unknown): “An implementation for generalized linear models follows the usual M -estimation results (Stefanski and Boos, 2002; Wooldridge, 2010, Ch. 12).”
The Robust Variance Estimator for Two-stage Models (2002, background): “The results we present follow from the lucid presentation of the theoretical justifications given in Stefanski and Boos (2002). Our goal is”
Covariate adjustment for two-sample treatment comparisons in randomized clinical trials: A principled yet flexible approach (2008, methodology): “2], [23], from whence the standard “sandwich” technique may be used to derive a variance estimator.”