Bias reduction in standard errors for linear regression with multi-stage samples

By Daniel F McCaffrey, R. Bell. 2003

413 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/a9520b329ce78c63600188919ab8b315c6b9aba2

How researchers see this paper

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

Citations in the corpus

Rational Ignorance in Education: A Field Experiment in Student Plagiarism (2010, unknown): “To do so, we calculate and report bias-corrected clustered standard errors using the method proposed by Bell and McCaffrey (2002).”
Ability Peer Effects in University: Evidence from a Randomized Experiment (2016, methodology): “To ensure that this method is sufficiently conservative, we compare the standard errors with Bias Reduced Linearization (BRL) standard errors (Bell and McCaffrey, 2002).”
Various Versatile Variances: An Object-Oriented Implementation of Clustered Covariances in R (2020, background): “Originally, Bell and McCaﬀrey (2002) recommended to use the factor ( G − 1) /G for HC3 (i.e., without cluster adjustment) but not for HC2 (i.e., with cluster adjustment).”
Inference in Regression Discontinuity Designs with a Discrete Running Variable (2016, methodology): “To address this concern, we repeat both the CPS placebo study and the simulation exercise described in Remark 1 using a bias-reduction modification of the STATA formula developed by Bell and McCaffrey (2002) that is analogous to the HC2 modification of the EHW standard error proposed by MacKinnon an”
Small-Sample Adjustments for Tests of Moderators and Model Fit Using Robust Variance Estimation in Meta-Regression (2015, methodology): “Another approach, introduced by Bell and McCaffrey (2002) and followed by Tipton (2015), is to instead use the same working model that was used to develop the weighting matrices Wj and adjustment matrices Aj. Results from simulation studies conducted by Bell and McCaffrey (2002) found that using emp”
A Practitioner’s Guide to Cluster-Robust Inference (2015, methodology): “For clustered errors with u ∼ N[0,Ω] and using the CRVE defi ned in Section IIC, or using CR2VE or CR3VE defi ned in Section VIB, Bell and McCaffrey (2002) shows that the distribution of the Wald t- statistic defi ned in Equation 23 can be approximated by the T(v*) distribution where (26) v* = (…”
Cluster-robust inference: A guide to empirical practice (2022, methodology): “Using Hotelling’s T 2 distribution with estimated degrees of freedom, Pustejovsky and Tipton (2018) generalizes the CV2 procedure of Bell and McCaffrey (2002) to the case of Wald tests based on (25).”
Asymptotic properties of a robust variance matrix estimator for panel data when T is large (2007, methodology): “Liang and Zeger (1986) and Bell and McCaffrey (2002). For example, in a schooling study, one might have data on individual outcomes where the individuals are grouped into classes.”
Generalized least squares inference in panel and multilevel models with serial correlation and fixed effects (2007, background): “It would be interesting to see if performance in these cases could be further improved using the bias-reduction and degrees of freedom corrections outlined in Bell and McCaffrey (2002).”
Placebo inference on treatment effects when the number of clusters is small (2018, methodology): “Imbens and Kolesár (2016) derive degrees-of-freedom and standard error corrections following the approach of Bell and McCaffrey (2002). Carter, Schnepel, and Steigerwald (2013) develop measures that can be used to determine degreesof-freedom corrections. Early papers that recognize the necessity of ”
Inference in Differences-in-Differences with Few Treated Groups and Heteroskedasticity (2019, background): “Not taking these problems into account can lead to severe underestimation of the DID standard errors, as highlighted in Bertrand et al. (2004). Still, there is as yet no unified approach to deal with this problem. As stated in Angrist and Pischke (2009), “.”