We consider the decision problem of making causal conclusions from observational data. Typically, using standard matched pairs techniques, there is a source of uncertainty that is not usually quantified, namely the uncertainty due to the choice of the experimenter: two different reasonable experimenters can easily have opposite results. In this work we present an alternative to the standard non...

Recent work on nonparametric identification of average partial effects (APEs) from panel data require restrictions on individual or time heterogeneity. Identifying assumptions under the “generalized first-differencing” category, such as time homogeneity (Chernozhukov, Fernandez-Val, Hahn, and Newey, 2013), have testable equality restrictions on the distribution of the outcome variable. This pap...

G08CDF also returns the standardized statistic Z 1⁄4 ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi n1 þ n2 n1n2 r D, where D may be Dn1;n2 , D þ n1;n2 or D n1;n2 depending on the choice of the alternative hypothesis. The distribution of this statistic converges asymptotically to a distribution given by Smirnov as n1 and n2 increase; see Feller (1948), Kendall and Stuart (1973), Kim and Jenri...

German Works Councils and Productivity: First Evidence from a Nonparametric Test This paper presents the first nonparametric test whether German works councils go hand in hand with higher labor productivity or not. It distinguishes between establishments that are covered by collective bargaining or not. Results from a Kolmogorov-Smirnov test for first order stochastic dominance tend to indicate...

We present a systematic study of the dynamical scaling process leading to the establishment of the Kolmogorov-Zakharov (KZ) spectrum in weak three-wave turbulence. In the finite-capacity case, in which the transient spectrum reaches infinite frequency in finite time, the dynamical scaling exponent is anomalous in the sense that it cannot be determined from dimensional considerations. As a conse...

Nonparametric two-sample or homogeneity testing is a decision theoretic problem that involves identifying differences between two random variables without making parametric assumptions about their underlying distributions. The literature is old and rich, with a wide variety of statistics having being designed and analyzed, both for the unidimensional and the multivariate setting. In this short ...

The problems of application of nonparametric Kolmogorov, Cramer-von MisesSmirnov, Anderson-Darling goodness-of-fit tests for discrete, grouped and censored data have been considered in this paper. The use of these tests for grouped and censored data as well as samples of discrete random variables is based on Smirnov transformation. The convergence of statistic distributions to the corresponding...

Testing the equality of percentiles (quantiles) between populations is an effective method for robust, nonparametric comparison, especially when the distributions are asymmetric or irregularly shaped. Unlike global nonparametric tests for homogeneity such as the Kolmogorv-Smirnov test, testing the equality of a set of percentiles (i.e., a percentile profile) yields an estimate of the location a...

Extended Abstract. Suppose n i.i.d. observations, X1, …, Xn, are available from the unknown distribution F(.), goodness-of-fit tests refer to tests such as H0 : F(x) = F0(x) against H1 : F(x) $neq$ F0(x). Some nonparametric tests such as the Kolmogorov--Smirnov test, the Cramer-Von Mises test, the Anderson-Darling test and the Watson test have been suggested by comparing empirical ...