Superiority comparisons of heterogeneous linear estimators

In this paper conditions for strong and weak superiority of a heterogeneous linear estimator over another are derived. The general results are applied to some special cases: in particular, two restricted least squares estimators are compared using the superiority conditions obtained. The weak superiority criterion is used as a basis in forming a generalization of an optimal se-quence of tests (Anderson, 1962) for searching for the best estimator when the alternative linear restrictions form a nested se-quence of hypotheses. An application of this is the determination of the correct length of lag and appropriate degree of polynomial in the estimation of polynomial distributed lag models.     

Invertibility of non-linear time series models

Sufficient conditions for invertibility of non-linear time series models are available in the literature only for a few special cases. In this paper a practical and general method for checking invertibility is presented. Briefly stated, it consists of feeding independent and identically distributed innovations into the non-linear model and then observing whether the model blows up or not. Using this idea invertibility conditions are derived for several recently proposed non-linear moving average models. Finally, the method is applied to a number of bilinear models fitted to economic time series.     

THE COLOR OF THE UNDERGRADUATE EXPERIENCE AND THE OCCUPATIONAL ATTAINMENT OF BLACKS AND WHITES: Evidence from Longitudinal Data

This study examines the impact of attendance at colleges with higher black enrollment on occupational attainment. The unique multipopulation LISREL models focus on blacks and whites, specify income and occupational self-direction as distinct dimensions of labor market accomplishment, and adjust for the possible confounding influence of college selectivity and precollege self-appraisals. Data from the NLS-72, augmented by selectivity and black enrollment data from other sources, are utilized. Findings largely support the hypothesis of within-race parity in occupational attainment. Black enrollment exerts nonsignificant effects on income among blacks and occupational self-direction in both races and slightly enhances income among whites.     

Estimation of the variance of an adaptive estimator by bootstrapping

In this paper we propose a bootstrap-based method to estimate the standard error of adaptive estimators. We apply it in the standard problem of location estimation discussed in Randies and Hogg (1973) and in Hogg and Lenth (1984). Our adaptive estimator is based on a choice between the mean the 35% trimmed mean and the median. Finally, we carry out a simulation study to see how well the proposed method performs in small and moderate sample sizes.     

De copulis non est disputandum

Normal distribution of residuals is a traditional assumption in multivariate models. It is, however, not very often consistent with real data. Copulae allow for an extension of dependency models to nonellipticity and for separation of margins from the dependency. This paper provides a survey of copulae where different copula classes, estimation and simulation techniques and goodness-of-fit tests are considered. In the empirical section we apply different copulae to the static and dynamic Value-at-Risk of portfolio returns and Profit-and-Loss function.     

Monotony relations between distribution functions and their application to experimental design

In a linear regression model an estimator of the unknown coefficients is considered which, in special cases, includes the least squares estimator. In the ease of stable symmetric error distribution and by means of a certain monotony relation between distribution functions optimality of this estimator is proved and the designing problem is investigated. A robustness property of optimal designs against the designing criterion and some conclusions are given concerning the least squares estimator in the case of G- and C-optimality.     

Healthy mind in healthy body? A review of sensorimotor–cognitive interdependencies in old age

We review four broad lines of research on couplings between sensorimotor and cognitive aging, with an emphasis on methodological concerns. First, correlational cross-sectional and longitudinal data indicate increasing associations between sensorimotor and cognitive aspects of behavior with advancing age. Second, older adults show greater performance decrements than young adults when sensorimotor and cognitive tasks or task components need to be performed concurrently rather than in isolation. Third, aerobic fitness interventions produce positive transfer effects on cognition that are particularly pronounced for tasks with high demands on attention and executive control. Fourth, neuroscience findings from animal models and humans have identified aging-sensitive structural and functional circuitries that support cognitive functions and are enhanced by higher levels of sensorimotor functioning. We conclude that sensorimotor and cognitive aging are causally related and functionally interdependent and that age-associated increments in cognitive resource demands of sensorimotor functioning are malleable by experience.     

Effects of fragmentation and trampling on carabid beetle assemblages in urban woodlands in Helsinki, Finland

We studied the effects of fragmentation (edge effects and patch size) and trampling (path cover) on carabid beetle assemblages in urban woodland patches in Helsinki, Finland. We expected that (1) open habitat and generalist species would benefit and forest species would suffer from increased woodland fragmentation, and (2) most carabid species would respond negatively to increased levels of trampling. A total of 2088 carabid individuals representing 37 species were collected. A cluster analysis distinguished sites in the interior of large woodland patches, with low or moderate path cover, from the other sites. The other sites did not cluster meaningfully, suggesting increased variation in the carabid fauna with increasing human impact. All species and ecological species-groups decreased with increasing distance from the edge toward the woodland interior and with increasing patch size. This pattern is in accordance with our expectation for open habitat and generalist species but opposite to what we expected for forest species. The reason for these surprising results may be that (1) the species we collected are not true forest interior species, (2) urban woodland edges are optimal habitats for many forest carabids, or (3) edges are actually sub-optimal, and high catches simply reflect increased activity of beetles moving away from the edge. Trampling did not have an overall negative effect on carabids as hypothesized. Species associated with moist forest habitat responded as predicted: they decreased in abundance with increasing path cover. Furthermore, open habitat species decreased with increasing path cover but more straightforward than we had predicted. Model elaboration, by dropping the highly trampled sites from the analyses, suggested that our data of high trampling may be too scarce: the results without these sites were more in accordance with our predictions than with the full dataset.