Inference with Few Heterogeneous Clusters

Abstract Suppose estimating a model on each of a small number of potentially heterogeneous clusters yields approximately independent, unbiased, and Gaussian parameter estimators. We make two contributions in this setup. First, we show how to compare a scalar parameter of interest between treatment and control units using a two-sample t-statistic, extending previous results for the one-sample t-statistic. Second, we develop a test for the appropriate level of clustering; it tests the null hypothesis that clustered standard errors from a much finer partition are correct. We illustrate the approach by revisiting empirical studies involving clustered, time series, and spatially correlated data.

[1]  Andrew V. Carter,et al.  Asymptotic Behavior of a t-Test Robust to Cluster Heterogeneity , 2017, Review of Economics and Statistics.

[2]  Joseph P. Romano,et al.  Randomization Tests Under an Approximate Symmetry Assumption , 2017 .

[3]  James G. MacKinnon,et al.  Wild Bootstrap Inference for Wildly Different Cluster Sizes , 2017 .

[4]  Michal Kolesár,et al.  Robust Standard Errors in Small Samples: Some Practical Advice , 2012, Review of Economics and Statistics.

[5]  Joseph P. Romano,et al.  Supplement to \Randomization Tests under an Approximate Symmetry Assumption" , 2015 .

[6]  Matthew D. Webb Reworking wild bootstrap‐based inference for clustered errors , 2014, Canadian Journal of Economics/Revue canadienne d'économique.

[7]  Ulrich K. Müller HAC Corrections for Strongly Autocorrelated Time Series , 2014 .

[8]  Yixiao Sun Let’s fix it: Fixed-bb asymptotics versus small-bb asymptotics in heteroskedasticity and autocorrelation robust inference , 2014 .

[9]  Yixiao Sun A Heteroskedasticity and Autocorrelation Robust F Test Using an Orthonormal Series Variance Estimator , 2013 .

[10]  Timothy G. Conley,et al.  Inference with dependent data using cluster covariance estimators , 2011 .

[11]  Guillaume Fréchette,et al.  The Evolution of Cooperation in Infinitely Repeated Games: Experimental Evidence , 2011 .

[12]  D. McKenzie,et al.  Does Management Matter? Evidence from India , 2011 .

[13]  Yixiao Sun Let's Fix it: Fixed-b Asymptotics Versus Small-b Asymptotics in Heteroscedasticity and Autocorrelation Robust Inference , 2010 .

[14]  Richard K. Crump,et al.  Nonparametric Tests for Treatment Effect Heterogeneity , 2006, The Review of Economics and Statistics.

[15]  Alan M. Taylor,et al.  Financial Stability, the Trilemma, and International Reserves , 2008 .

[16]  C. Hansen Asymptotic properties of a robust variance matrix estimator for panel data when T is large , 2007 .

[17]  Ulrich K. Müller A theory of robust long-run variance estimation , 2007 .

[18]  Stephen G. Donald,et al.  Inference with Difference-in-Differences and Other Panel Data , 2007, The Review of Economics and Statistics.

[19]  Ulrich K. Müller,et al.  t-Statistic Based Correlation and Heterogeneity Robust Inference , 2007 .

[20]  G. Székely,et al.  Student’s t-test for Gaussian scale mixtures , 2006 .

[21]  J. Stock,et al.  Heteroskedasticity-Robust Standard Errors for Fixed Effects Panel Data Regression , 2006 .

[22]  P. Phillips,et al.  Optimal Bandwidth Selection in Heteroskedasticity-Autocorrelation Robust Testing , 2005 .

[23]  Nicholas M. Kiefer,et al.  A NEW ASYMPTOTIC THEORY FOR HETEROSKEDASTICITY-AUTOCORRELATION ROBUST TESTS , 2005, Econometric Theory.

[24]  Nicholas M. Kiefer,et al.  HETEROSKEDASTICITY-AUTOCORRELATION ROBUST TESTING USING BANDWIDTH EQUAL TO SAMPLE SIZE , 2002, Econometric Theory.

[25]  Asymptotic behaviour of the sample autocovariance and autocorrelation function of the AR(1) process with ARCH(1) errors , 2001 .

[26]  E. Duflo,et al.  How Much Should We Trust Differences-in-Differences Estimates? , 2001 .

[27]  R. Cont Empirical properties of asset returns: stylized facts and statistical issues , 2001 .

[28]  T. Mikosch,et al.  Limit theory for the sample autocorrelations and extremes of a GARCH (1,1) process , 2000 .

[29]  Richard A. Davis,et al.  The sample autocorrelations of heavy-tailed processes with applications to ARCH , 1998 .

[30]  Nonhomogeneous samples in the Behrens-Fisher problem , 1998 .

[31]  N. K. Bakirov Comparison Theorems for Distribution Functions of Quadratic Forms of Gaussian Vectors , 1996 .

[32]  M. Hallin,et al.  Improved Eaton bounds for linear combinations of bounded random variables , 1993 .

[33]  Jean-Marie Dufour,et al.  Nonuniform Bounds for Nonparametric t-Tests , 1991, Econometric Theory.

[34]  N. K. Bakirov Extrema of the Distributions of Quadratic Forms of Gaussian Variables , 1990 .

[35]  N. K. Bakirov An extremal property of the student distribution , 1989 .

[36]  Yoav Benjamini,et al.  Is the t Test Really Conservative When the Parent Distribution is Long-Tailed? , 1983 .

[37]  Donald B. Keim SIZE-RELATED ANOMALIES AND STOCK RETURN SEASONALITY Further Empirical Evidence , 1983 .

[38]  W. Hamilton,et al.  The evolution of cooperation. , 1984, Science.

[39]  J. Hausman Specification tests in econometrics , 1978 .

[40]  R. Oaxaca Another Look at Tests of Equality between Sets of Coefficients in Two Linear Regressions , 1974 .

[41]  D. Brillinger Estimation of the mean of a stationary time series by sampling , 1973, Journal of Applied Probability.

[42]  E. Fama,et al.  Risk, Return, and Equilibrium: Empirical Tests , 1973, Journal of Political Economy.

[43]  B. Efron Student's t-Test under Symmetry Conditions , 1969 .

[44]  Morton B. Brown,et al.  Bounds on the Distribution Functions of the Behrens-Fisher Statistic , 1966 .

[45]  L. J. Savage,et al.  The nonexistence of certain statistical procedures in nonparametric problems , 1956 .