Suchergebnisse

"Since the advent of heteroskedasticity-robust standard errors, several papers have proposed adjustments to the original White formulation. We replicate earlier findings that each of these adjusted estimators performs quite poorly in finite samples. We propose a class of alternative heteroskedasticity-robust tests of linear hypotheses based on an Edgeworth expansions of the test statistic distribution. Our preferred test outperforms existing methods in both size and power for low, moderate, and severe levels of heteroskedasticity"--National Bureau of Economic Research web site

Since 1970 the United States government has spent over half a billion dollars on social experiments intended to assess the effect of potential tax policies, health insurance plans, housing subsidies, and other programs. Was it worth it? Was anything learned from these experiments that could not have been learned by other, and cheaper, means? Could the experiments have been better designed or analyzed? These are some of the questions addressed by the contributors to this volume, the result of a conference on social experimentation sponsored in 1981 by the National Bureau of Economic Research. T