We present a simple, general technique for reducing the sample complexity of matrix and tensor decomposition algorithms applied to distributions. We use the technique to give a polynomialtime algorithm for standard ICA with sample complexity nearly linear in the dimension, thereby improving substantially on previous bounds. The analysis is based on properties of random polynomials, namely the s...

The behaviour of group sequential tests in the two-sample problem is investigated if one replaces the classical non-robust estimators in the t-test statistic by modern robust estimators of location and scale. Hampel's 3-part redescending M-estimator 25A used in the Princeton study and the robust scale estimators length of the shortest half proposed by Rousseeuw & Leroy and Q proposed by Roussee...

Ask experts what would be an important reduction in amount consumed. Need some idea of the SD of a within-child difference in consumption from a four hour period in one day to a four hour period in another day. Could do a pilot study with say 10 children measured [without any intervention] on two different days and get the SD of the 10 differences. Then use sample size formula for 1 sample t-te...

The idea of perturbation independent decay (PID) has appeared in the context of survival-probability studies, and lately has emerged in the context of quantum irreversibility studies. In both cases the PID reflects the Lyapunov instability of the underlying semiclassical dynamics, and it can be distinguished from the Wigner-type decay that holds in the perturbative regime. The theory of the sur...

"In this paper we examine the living arrangements of older unmarried women--that is, single, divorced, or widowed women--in The Netherlands....[The] paper analyzes the distribution of [such] women across several types of living arrangements, including an institutionalized category ('residential homes'). The factors influencing this distribution that are examined include indices of functional l...

Many Six Sigma practitioners use “Student’s” independent two-sample t-test when investigating differences in means. This type of test is based upon drawing random samples from two independent normal (Gaussian) distributions. Often, however, the assumption of normality and/or random sampling is violated. This article discusses when and why the two-sample t-test may be considered robust to these ...