38 resultados para multilinear regressions


Relevância:

10.00% 10.00%

Publicador:

Resumo:

Time-lagged responses of biological variables to landscape modifications are widely recognized, but rarely considered in ecological studies. In order to test for the existence of time-lags in the response of trees, small mammals, birds and frogs to changes in fragment area and connectivity, we studied a fragmented and highly dynamic landscape in the Atlantic forest region. We also investigated the biological correlates associated with differential responses among taxonomic groups. Species richness and abundance for four taxonomic groups were measured in 21 secondary forest fragments during the same period (2000-2002), following a standardized protocol. Data analyses were based on power regressions and model selection procedures. The model inputs included present (2000) and past (1962, 1981) fragment areas and connectivity, as well as observed changes in these parameters. Although past landscape structure was particularly relevant for trees, all taxonomic groups (except small mammals) were affected by landscape dynamics, exhibiting a time-lagged response. Furthermore, fragment area was more important for species groups with lower dispersal capacity, while species with higher dispersal ability had stronger responses to connectivity measures. Although these secondary forest fragments still maintain a large fraction of their original biodiversity, the delay in biological response combined with high rates of deforestation and fast forest regeneration imply in a reduction in the average age of the forest. This also indicates that future species losses are likely, especially those that are more strictly-forest dwellers. Conservation actions should be implemented to reduce species extinction, to maintain old-growth forests and to favour the regeneration process. Our results demonstrate that landscape history can strongly affect the present distribution pattern of species in fragmented landscapes, and should be considered in conservation planning. (C) 2009 Elsevier Ltd. All rights reserved.

Relevância:

10.00% 10.00%

Publicador:

Resumo:

Quadratic alternative superalgebras are introduced and their super-identities and central functions on one odd generator are described. As a corollary, all multilinear skew-symmetric identities and central polynomials of octonions are classified. (C) 2008 Elsevier B.V. All rights reserved.

Relevância:

10.00% 10.00%

Publicador:

Resumo:

We simplify the results of Bremner and Hentzel [J. Algebra 231 (2000) 387-405] on polynomial identities of degree 9 in two variables satisfied by the ternary cyclic sum [a, b, c] abc + bca + cab in every totally associative ternary algebra. We also obtain new identities of degree 9 in three variables which do not follow from the identities in two variables. Our results depend on (i) the LLL algorithm for lattice basis reduction, and (ii) linearization operators in the group algebra of the symmetric group which permit efficient computation of the representation matrices for a non-linear identity. Our computational methods can be applied to polynomial identities for other algebraic structures.

Relevância:

10.00% 10.00%

Publicador:

Resumo:

We describe the characters of simple modules and composition factors of costandard modules for S(2 vertical bar 1) in positive characteristics and verify a conjecture of La Scala-Zubkov regarding polynomial superinvariants for GL(2 vertical bar 1).

Relevância:

10.00% 10.00%

Publicador:

Resumo:

We discuss an algebraic theory for generalized Jordan chains and partial signatures, that are invariants associated to sequences of symmetric bilinear forms on a vector space. We introduce an intrinsic notion of partial signatures in the Lagrangian Grassmannian of a symplectic space that does not use local coordinates, and we give a formula for the Maslov index of arbitrary real analytic paths in terms of partial signatures.

Relevância:

10.00% 10.00%

Publicador:

Resumo:

We introduce, for the first time, a new class of Birnbaum-Saunders nonlinear regression models potentially useful in lifetime data analysis. The class generalizes the regression model described by Rieck and Nedelman [Rieck, J.R., Nedelman, J.R., 1991. A log-linear model for the Birnbaum-Saunders distribution. Technometrics 33, 51-60]. We discuss maximum-likelihood estimation for the parameters of the model, and derive closed-form expressions for the second-order biases of these estimates. Our formulae are easily computed as ordinary linear regressions and are then used to define bias corrected maximum-likelihood estimates. Some simulation results show that the bias correction scheme yields nearly unbiased estimates without increasing the mean squared errors. Two empirical applications are analysed and discussed. Crown Copyright (C) 2009 Published by Elsevier B.V. All rights reserved.

Relevância:

10.00% 10.00%

Publicador:

Resumo:

This paper derives the second-order biases Of maximum likelihood estimates from a multivariate normal model where the mean vector and the covariance matrix have parameters in common. We show that the second order bias can always be obtained by means of ordinary weighted least-squares regressions. We conduct simulation studies which indicate that the bias correction scheme yields nearly unbiased estimators. (C) 2009 Elsevier B.V. All rights reserved.

Relevância:

10.00% 10.00%

Publicador:

Resumo:

Rhipicephalus (Boophilus) microplus is an important cattle pest in Uruguay, and the law regulates its control. It is resistant to organophosphates, synthetic pyrethroids and, as recently discovered, to fipronil. Resistance to macrocyclic lactones (MLs) and amitraz have not been documented; however, veterinarians and farmers have reported treatment failures. The objective of the present work was to study the susceptibility of cattle tick strains from different Uruguayan counties to ivermectin (IVM) and fipronil by using the Larval Immersion Test (LIT). The Mozo strain was used as the susceptible reference strain. From 2007 to 2009, twenty-eight tick populations were collected from different cattle farms with and without history of IVM or fipronil use. A probit analysis estimated dose-mortality regressions, lethal concentrations (LC), and confidence intervals. The resistance ratio (RR) was determined at the LC(50) and LC(90) estimates. To classify a tick population in relation to resistance, three categories based on a statistical analysis of LC and RR between field populations and Mozo strains were defined: susceptible (no differences), incipient resistance (differences and RR(50) < 2) and resistant (differences and RR(50) >= 2). Eighteen field populations were tested with IVM and five of them presented a RR(50) range between 1.35 and 1.98 and the LC(50/90), which is statistically different from the Mozo strain (incipient resistance). However, the RR(90) increases >= 2 in four of the populations, confirming that tick resistance to IVM is emergent. The low RR values obtained could be a result of a low frequency of treatments with IVM. Twenty-seven tick populations were tested with fipronil and six were diagnosed as resistant according to the LIT. Cross-resistance was not observed between fipronil and IVM on these tick populations. The current study presents different R. (B.) microplus populations with an incipient resistance to IVM, and indicates that the fipronil tick resistance is restricted to certain areas in Uruguay. (c) 2011 Elsevier B.V. All rights reserved.