Fast and robust estimators of variance components in the nested error model

Usual fitting methods for the nested error linear regression model are known to be very sensitive to the effect of even a single outlier. Robust approaches for the unbalanced nested error model with proved robustness and efficiency properties, such as M-estimators, are typically obtained through iterative algorithms. These algorithms are often computationally intensive and require robust estimates of the same parameters to start the algorithms, but so far no robust starting values have been proposed for this model. This paper proposes computationally fast robust estimators for the variance components under an unbalanced nested error model, based on a simple robustification of the fitting-of-constants method or Henderson method III. These estimators can be used as starting values for other iterative methods. Our simulations show that they are highly robust to various types of contamination of different magnitude.     

The Downfall of Gomułka

Marina Tsvetaeva’s 1934 “Chërt” (The Devil) forms a central part of the cycle of autobiographical prose she wrote in emigration. This article assembles clues to the hidden origins of the Devil she describes in prose about her grandfathers, some of it censored in pre-1990 editions of her works. Tsvetaeva’s Devil is not simply metaphysical: it has the unusual appearance of a Great Dane. Though she goes on to trace its appearances in the literature and culture of her childhood, some of its physical features (eyes, nose, colour and posture) link it with other people in her life. The vivid details of the Devil suggest relationships, though peculiarly mediated ones, to members of her own family, especially her maternal grandfather, Aleksandr Danilovich Mein. The poet describes herself using Pushkin’s poem “Utoplennik” to camouflage her own sense of self from her mother. Much of the rest of “The Devil” describes her recognition of the Devil in varying symbolic or even phonetic guises, tracing how the poet stayed faithful to him even after he ceased to appear visibly, how she found and read his symbols in surrounding reality—e.g., card games, toys, rituals for finding lost objects—and in unexpected, otherwise respectable, parts of society, including her own grandfather. As always, Tsvetaeva creates a story that affirms her identity as a poet and illustrates the work she had to do to achieve that identity.     

The Estimation of Food Expenditures From Household Budget Data in the Presence of Bulk Purchases

The aim of this article is the estimation of annual food expenditures with limited information about bulk purchases with data from a Spanish household-budget survey for 1990—1991. Three alternatives are compared. The first, currently used for official purposes, does not use all the information. The second uses all the available information in a rough way. The third assumes a formal model for the unknown frequency of purchases. The three alternatives are compared by a regression model that should be homogeneous with respect to the dummy variables that represent the partial information of the groups and should show a distinct pattern of outliers under each alternative. Finally, we study the effect of the official and the best alternative on food inflation and inequality measures. We find that they lead to similar inflation rates but to different inequality estimates.     

Over the Colombian Rainbow

This poststructural narrative research intends to contribute a better understanding of some lesbian, gay, bisexual, and transgendered (LGBT) people's meanings, interactions, and reflections through the analysis of Colombian government's master narratives and LGBT advocates’ counter-narratives. A better understanding between the Colombian government and LGBT activists is needed in order to build bridges that allow the parties to construct pathways to new stories that legitimize them and will support solutions to their conflicts. The author argues that LGBT counter-narratives are repairing the damaged identities of LGBT in Colombia, even though they have not become master narratives.     

A basis approach to goodness-of-fit testing in recurrent event models

A class of tests for the hypothesis that the baseline hazard function in Cox's proportional hazards model and for a general recurrent event model belongs to a parametric family C identical with {lambda(0)(.; xi): xi in Xi} is proposed. Finite properties of the tests are examined via simulations, while asymptotic properties of the tests under a contiguous sequence of local alternatives are studied theoretically. An application of the tests to the general recurrent event model, which is an extended minimal repair model admitting covariates, is demonstrated. In addition, two real data sets are used to illustrate the applicability of the proposed tests.     

Clustering time series by linear dependency

Statistics and Computing - We present a new way to find clusters in large vectors of time series by using a measure of similarity between two time series, the generalized cross correlation. This...     

Sojourning With the Homogeneous Poisson Process

In this pedagogical article, distributional properties, some surprising, pertaining to the homogeneous Poisson process (HPP), when observed over a possibly random window, are presented. Properties of the gap-time that covered the termination time and the correlations among gap-times of the observed events are obtained. Inference procedures, such as estimation and model validation, based on event occurrence data over the observation window, are also presented. We envision that through the results in this article, a better appreciation of the subtleties involved in the modeling and analysis of recurrent events data will ensue, since the HPP is arguably one of the simplest among recurrent event models. In addition, the use of the theorem of total probability, Bayes’ theorem, the iterated rules of expectation, variance and covariance, and the renewal equation could be illustrative when teaching distribution theory, mathematical statistics, and stochastic processes at both the undergraduate and graduate levels. This article is targeted toward both instructors and students.     

Total least squares and bootstrapping with applications in calibration

The solution to the errors-in-variables problem computed through total least squares is highly nonlinear. Because of this, many statistical procedures for constructing confidence intervals and testing hypotheses cannot be applied. One possible solution to this dilemma is bootstrapping. A nonparametric bootstrap technique could fail. Here, the proper nonparametric bootstrap procedure is provided and its correctness is proved. On the other hand, a residual bootstrap is not valid and suitable in this case. The results are illustrated through a simulation study. An application of this approach to calibration data is presented.     

Priority Topics in the Study of Environmental Risk in Developing Countries: Report on a Workshop Held at the East–West Center, August, 1988

The rapid industrialization occurring in developing regions of the world brings not only economic benefits, but changes in the types and severity of health and environmental problems that each region experiences. As the industrialized world moves toward the use of risk assessment methodologies to aid in problem evaluation and regulatory and policy decision analysis, it seems inevitable that these methodologies will be applied globally. The changes brought about by rapid industrialization, however, must be viewed within the context of societies that are still struggling with the more traditional and basic environmental problems associated with urban and rural poverty. The urgency of development and the lack of adequate resources for characterizing health and environmental changes, often present under these circumstances, offer special challenges to the application of risk assessment methodologies.