Determining Process Death Based on Censored Activity Data

This article addresses the problem of estimating the time of apparent death in a binary stochastic process. We show that, when only censored data are available, a fitted logistic regression model may estimate the time of death incorrectly. We improve this estimation by utilizing discrete-event simulation to produce simulated complete time series data. The proposed methodology may be applied to situations where time of death cannot be formally determined and has to be estimated based on prolonged inactivity. As an illustration, we use observed monthly activity patterns from 300 real Open Source Software development projects sampled from Sourceforge.net.     

The Joint Distribution of the Sum and the Maximum of IID Exponential Random Variables

The authors establish the joint distribution of the sum X and the maximum Y of IID exponential random variables. They derive exact formuli describing the random vector (X, Y), including its joint PDF, CDF, and other characteristics; marginal and conditional distributions; moments and related parameters; and stochastic representations leading to further properties of infinite divisibility and self-decomposability. The authors also discuss parameter estimation and include an example from climatology that illustrates the modeling potential of this new bivariate model.     

Depth Measures for Multivariate Functional Data

In this article, we address the problem of mining and analyzing multivariate functional data. That is, data where each observation is a set of possibly correlated functions. Complex data of this kind is more and more common in many research fields, particularly in the biomedical context. In this work, we propose and apply a new concept of depth measure for multivariate functional data. With this new depth measure it is possible to generalize robust statistics, such as the median, to the multivariate functional framework, which in turn allows the application of outlier detection, boxplots construction, and nonparametric tests also in this more general framework. We present an application to Electrocardiographic (ECG) signals.     

The collected works of john w. tukey

We describe novel, analytical, data-analysis, and Monte-Carlo-simulation studies of strongly heteroscedastic data of both small and wide range.Many different types of heteroscedasticity and fixed or variable weighting are incorporated through error-variance models.Attention is given to parameter bias determinations, evaluations of their significances, and to new ways to correct for bias.The error-variance models allow for both additive and independent power-law errors, and the power exponent is shown to be able to be well determined for typical physicalsciences data by the rapidly-converging, general-purpose, extended-least-squares program we use.The fitting and error-variance models are applied to both low-and high-heteroscedasticity situations, including single-response data from radioactive decay.Monte-Carlo simulations of data with similar parameters are used to evaluate the analytical models developed and the various minimization methods em-ployed, such as extended and generalized least squares.Logarithmic and inversion transformations are investigated in detail, and it is shown analytically and by simulations that exponential data with constant percentage errors can be logarithmically transformed to allow a simple parameter-bias-removal procedure.A more-general bias-reduction approach combining direct and inversion fitting is also developed.Distributions of fitting-model and error-variance-model parameters are shown to be typically non-normal, thus invalidating the usual estimates of parameter bias and precision.Errors in conventional confidence-interval estimates are quantified by comparison with accurate simulation results.     

Measuring Kurtosis by Right and Left Inequality Orders

The question of how to measure kurtosis in both symmetric and asymmetric distributions is addressed using the kurtosis diagram of Zenga (2006 Zenga , M. ( 2006 ). Kurtosis . In : Kotz , S. , Read , C. B. , Balakrishnan , N. , Vidakovic , B. , eds. Encyclopedia of Statistical Sciences. 2nd ed . New York : John Wiley and Sons . [Google Scholar]). Kurtosis is related to inequality at either side of the median, and we establish a hierarchy of kurtosis orderings in which the kurtosis diagram stands at the weakest level. A sufficient condition for constructing kurtosis measures compatible with such ordering is provided. The merits of the proposed approach in both clarifying and formalizing the idea of kurtosis are evaluated and examples are discussed throughout.     

Improving the admissibility screen: evaluating test statistics on the basis of p-values rather than power

The admissibility of testing procedures is examined when the loss function used is an increasing function of the p-value rather than the standard 0–1 loss. It is shown that the class of admissible procedures using the new approach is a subset of the class of admissible procedures using the 0–1 loss.     

A bivariate normal example where the locally most powerful and distantly most powerful test statistics are beaten everywhere from a median p-value standpoint

In the bivariate normal, n=2 case, when testing H₀:μ_x=μ_y=0,σ² _x=σ² _y=1, ρ=0 vs. H₁:μ_x=μ_y=0,σ² _x=σ² _y=1, 0<ρ<1, it is shown that the median p-values given by the locally most powerful test and the distantly most powerful test are both beaten everywhere by the median of a third test.     

Some characterizations of discrete distributions based on weak records

Let X ₁, X ₂,... be iid random variables (rv's) with the support on nonnegative integers and let (W _n , n≥0) denote the corresponding sequence of weak record values. We obtain new characterization of geometric and some other discrete distributions based on different forms of partial independence of rv's W _n and W _n+r —W _n for some fixed n≥0 and r≥1. We also prove that rv's W ₀ and W _n+1 —W _n have identical distribution if and only if (iff) the underlying distribution is geometric.     

Adaptive sampling without replacement of clusters

In a common form of adaptive cluster sampling, an initial sample of units is selected by random sampling without replacement and, whenever the observed value of the unit is sufficiently high, its neighboring units are added to the sample, with the process of adding neighbors repeated if any of the added units are also high valued. In this way, an initial selection of a high-valued unit results in the addition of the entire network of surrounding high-valued units and some low-valued “edge” units where sampling stops. Repeat selections can occur when more than one initially selected unit is in the same network or when an edge unit is shared by more than one added network. Adaptive sampling without replacement of networks avoids some of this repeat selection by sequentially selecting initial sample units only from the part of the population not already in any selected network. The design proposed in this paper carries this step further by selecting initial units only from the population, exclusive of any previously selected networks or edge units.