Robust Standard Errors in Small Samples: Some Practical Advice

2016/07/19 by Guido W. Imbens, Michal Kolesár · 17 citations
Mathematics · #Advanced Statistical Methods and Models #Statistical Methods and Inference #Statistical Methods and Bayesian Inference

paper · doi:10.1162/rest_a_00552

Abstract

We study the properties of heteroskedasticity-robust confidence intervals for regression parameters. We show that confidence intervals based on a degrees-of-freedom correction suggested by Bell and McCaffrey (2002) are a natural extension of a principled approach to the Behrens-Fisher problem. We suggest a further improvement for the case with clustering. We show that these standard errors can lead to substantial improvements in coverage rates even for samples with fifty or more clusters.We recommend that researchers routinely calculate the Bell-McCaffrey degrees-of-freedom adjustment to assess potential problems with conventional robust standard errors.

Citations

• THE GENERALIZATION OF ‘STUDENT'S’ PROBLEM WHEN SEVERAL DIFFERENT POPULATION VARLANCES ARE INVOLVED
• ON THE COMPARISON OF SEVERAL MEAN VALUES: AN ALTERNATIVE APPROACH
• A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for Heteroskedasticity
• Longitudinal data analysis using generalized linear models
• Bootstrap-Based Improvements for Inference with Clustered Errors

Cited by

• Affective Polarization in Comparative and Longitudinal Perspective
• Cash and the Economy: Evidence from India’s Demonetization*
• A Modified Randomization Test for the Level of Clustering
• A More Robust t-Test
• Common Auditors and Private Bank Loans*
• Understanding and misunderstanding randomized controlled trials
• Wild Bootstrap for Instrumental Variables Regressions with Weak and Few Clusters
• The Behrens-Fisher Problem with Covariates and Baseline Adjustments
• Randomization inference for difference-in-differences with few treated clusters
• Kin-based institutions and state capacity
• Internet use and physical and mental health in old age during the COVID-19 pandemic: Evidence from partners in SHARE
• Robust Inference Under Heteroskedasticity via the Hadamard Estimator
• Look up and ahead: How climate scenarios affect European sovereign credit risk
• Dyadic Clustering in International Relations
• Uncertainty Quantification For Low-Rank Matrix Completion With Heterogeneous and Sub-Exponential Noise
• Fast cluster bootstrap methods for linear regression models
• Kin networks and quality of government: a regional analysis

Related

• Robust Inference in Panel Data Models: Some Effects of Heteroskedasticity and Leveraged Data in Small Samples
• Using Heteroscedasticity Consistent Standard Errors in the Linear Regression Model
• Unlocking the Regression Space
• The Small Sample Behavior of Some Statistics Which Test the Equality of Several Means
• Weak Instruments, First-Stage Heteroskedasticity, the Robust F-Test and a GMM Estimator with the Weight Matrix Based on First-Stage Residuals