Home About us Contact
|
Home About us Contact | ||
|
|
||
Inference Methods (inference + methods)
Selected AbstractsInference Methods for the Conditional Logistic Regression Model with Longitudinal DataBIOMETRICAL JOURNAL, Issue 1 2008Radu V. Craiu No abstract is available for this article. [source] A LIKELIHOOD FRAMEWORK FOR INFERRING THE EVOLUTION OF GEOGRAPHIC RANGE ON PHYLOGENETIC TREESEVOLUTION, Issue 11 2005Richard H. Ree Abstract At a time when historical biogeography appears to be again expanding its scope after a period of focusing primarily on discerning area relationships using cladograms, new inference methods are needed to bring more kinds of data to bear on questions about the geographic history of lineages. Here we describe a likelihood framework for inferring the evolution of geographic range on phylogenies that models lineage dispersal and local extinction in a set of discrete areas as stochastic events in continuous time. Unlike existing methods for estimating ancestral areas, such as dispersal-vicariance analysis, this approach incorporates information on the timing of both lineage divergences and the availability of connections between areas (dispersal routes). Monte Carlo methods are used to estimate branch-specific transition probabilities for geographic ranges, enabling the likelihood of the data (observed species distributions) to be evaluated for a given phylogeny and parameterized paleogeographic model. We demonstrate how the method can be used to address two biogeographic questions: What were the ancestral geographic ranges on a phylogenetic tree? How were those ancestral ranges affected by speciation and inherited by the daughter lineages at cladogenesis events? For illustration we use hypothetical examples and an analysis of a Northern Hemisphere plant clade (Cercis), comparing and contrasting inferences to those obtained from dispersal-vicariance analysis. Although the particular model we implement is somewhat simplistic, the framework itself is flexible and could readily be modified to incorporate additional sources of information and also be extended to address other aspects of historical biogeography. [source] Hybrid identification of fuzzy rule-based modelsINTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, Issue 1 2002Sung-Kwun Oh In this study, we propose a hybrid identification algorithm for a class of fuzzy rule-based systems. The rule-based fuzzy modeling concerns structure optimization and parameter identification using the fuzzy inference methods and hybrid structure combined with two methods of optimization theories for nonlinear systems. Two types of inference methods of a fuzzy model concern a simplified and linear type of inference. The proposed hybrid optimal identification algorithm is carried out using a combination of genetic algorithms and an improved complex method. The genetic algorithms determine initial parameters of the membership function of the premise part of the fuzzy rules. In the sequel, the improved complex method (being in essence a powerful auto-tuning algorithm) leads to fine-tuning of the parameters of the respective membership functions. An aggregate performance index with a weighting factor is proposed in order to achieve a balance between performance of the fuzzy model obtained for the training and testing data. Numerical examples are included to evaluate the performance of the proposed model. They are also contrasted with the performance of the fuzzy models existing in the literature. © 2002 John Wiley & Sons, Inc. [source] Nonparametric Varying-Coefficient Models for the Analysis of Longitudinal DataINTERNATIONAL STATISTICAL REVIEW, Issue 3 2002Colin O. Wu Summary Longitudinal methods have been widely used in biomedicine and epidemiology to study the patterns of time-varying variables, such as disease progression or trends of health status. Data sets of longitudinal studies usually involve repeatedly measured outcomes and covariates on a set of randomly chosen subjects over time. An important goal of statistical analyses is to evaluate the effects of the covariates, which may or may not depend on time, on the outcomes of interest. Because fully parametric models may be subject to model misspecification and completely unstructured nonparametric models may suffer from the drawbacks of "curse of dimensionality", the varying-coefficient models are a class of structural nonparametric models which are particularly useful in longitudinal analyses. In this article, we present several important nonparametric estimation and inference methods for this class of models, demonstrate the advantages, limitations and practical implementations of these methods in different longitudinal settings, and discuss some potential directions of further research in this area. Applications of these methods are illustrated through two epidemiological examples. Résumé Modèles non-paramétriques à coefficients variables pour l'analyse de données longitudinales Les méthodes longitudinales ont été largement utilisées en biomédecine et en épidémiologie pour étudier les modèles de variables variant dans le temps, du type progression de maladie ou tendances détat de santé. Les ensembles de données d'études longitudinales comprennent généralement des ésultats de mesures répétées et des covariables sur un ensemble de sujets choisis au hasard dans le temps. Un objectif important des analyses statistiques consisteàévaluer les effets des covariables, qui peuvent ou non dépendre du temps, sur les résultats d'intérêt. Du fait que des modèles entièrement paramétriques peuvent faire l'objet d'erreur de spécification de modèle et que des modèles non-paramétriques totalement non-structurés peuvent souffrir des inconvénients de la «malédiction de dimensionnalité», les modèles à coefficients variables sont une classe de modèles structurels non-paramétriques particulièrement utiles dans les analyses longitudinales. Dans cet article, on présente plusieurs estimations non-paramétriques importantes, ainsi que des méthodes d'inférence pour cette classe de modéles, on démontre les avantages, limites et mises en ,uvre pratiques de ces méthodes dans différents contextes longitudinaux et l'on traite de certaines directions possibles pour de plus amples recherches dans ce domaine. Des applications de ces méthodes sont illustrées à travers deux exemples épidémiologiques. [source] R×C ecological inference: bounds, correlations, flexibility and transparency of assumptionsJOURNAL OF THE ROYAL STATISTICAL SOCIETY: SERIES A (STATISTICS IN SOCIETY), Issue 1 2009D. James Greiner Summary., Despite its potential pitfalls, ecological inference is an unavoidable part of some quantitative settings, including US voting rights litigation. In such applications, the analyst will typically encounter two-way tables with more than two rows and columns. Although several ecological inference methods are currently available for 2×2 tables, there are fewer options for analysing general R×C tables, and virtually none that model counts as opposed to fractions. We propose a count R×C method that respects the bounds deterministically, that allows for complex relationships between internal cell quantities, that is easily extensible and that results from transparent assumptions. We study the method via simulation, and then apply it to an example that is drawn from the state of Texas relevant to recent redistricting litigation there. [source] Subsampling in testing autocovariance for periodically correlated time seriesJOURNAL OF TIME SERIES ANALYSIS, Issue 6 2008Ukasz Lenart Abstract., The main purpose of this article was to describe the asymptotic properties of subsampling procedure applied to nonstationary, periodically correlated time series. We present the conditions under which the subsampling version for the estimator of Fourier coefficient of autocovariance function is consistent. Our result provides new tools in statistical inference methods for nonstationary, periodically correlated time series. For example, it enables to construct consistent subsampling test which successfully distinguishes the period of the series. [source] Species discovery in marine planktonic invertebrates through global molecular screeningMOLECULAR ECOLOGY, Issue 5 2010ERICA GOETZE Abstract Species discovery through large-scale sampling of mitochondrial diversity, as advocated under DNA barcoding, has been widely criticized. Two of the primary weaknesses of this approach, the use of a single gene marker for species delineation and the possible co-amplification of nuclear pseudogenes, can be circumvented through incorporation of multiple data sources. Here I show that for taxonomic groups with poorly characterized systematics, large-scale genetic screening using a mitochondrial DNA marker can be a very effective approach to species discovery. Global sampling (120 locations) of 1295 individuals of 22 described species of eucalanid copepods identified 15 novel evolutionarily significant units (ESUs) within this marine holoplanktonic family. Species limits were tested under reciprocal monophyly at the mitochondrial (mt) gene 16S rRNA, and 13 of 15 lineages were reciprocally monophyletic under three phylogenetic inference methods. Five of these mitochondrial ESUs also received moderate support for reciprocal monophyly at the independently-inherited nuclear gene, internal transcribed spacer 2 (ITS2). Additional support for the utility of mt DNA as a proxy for species boundaries in this taxon is discussed, including results from related morphological and biogeographic studies. Minimal overlap of intra-ESU and inter-ESU 16S rRNA genetic distances was observed, suggesting that this mt marker performs well for species discovery via molecular screening. Sampling coverage required for the discovery of new ESUs was found to be in the range of >50 individuals/species, well above the sampling intensity of most current DNA Barcoding studies. Large-scale genetic screening can provide critical first data on the presence of cryptic species, and should be used as an approach to generate systematic hypotheses in groups with incomplete taxonomies. [source] Internal algorithm variability and among-algorithm discordance in statistical haplotype reconstructionMOLECULAR ECOLOGY, Issue 8 2009ZU-SHI HUANG The potential effectiveness of statistical haplotype inference makes it an area of active exploration over the last decade. There are several complications of statistical inference, including: the same algorithm can produce different solutions for the same data set, which reflects the internal algorithm variability; different algorithms can give different solutions for the same data set, reflecting the discordance among algorithms; and the algorithms per se are unable to evaluate the reliability of the solutions even if they are unique, this being a general limitation of all inference methods. With the aim of increasing the confidence of statistical inference results, consensus strategy appears to be an effective means to deal with these problems. Several authors have explored this with different emphases. Here we discuss two recent studies examining the internal algorithm variability and among-algorithm discordance, respectively, and evaluate the different outcomes of these analyses, in light of Orzack (2009) comment. Until other, better methods are developed, a combination of these two approaches should provide a practical way to increase the confidence of statistical haplotyping results. [source] Laying the foundations for a new classification of Agaonidae (Hymenoptera: Chalcidoidea), a multilocus phylogenetic approachCLADISTICS, Issue 4 2010Astrid Cruaud A phylogeny of the Agaonidae (Chalcidoidea) in their restricted sense, pollinators of Ficus species (Moraceae), is estimated using 4182 nucleotides from six genes, obtained from 101 species representing 19 of the 20 recognized genera, and four outgroups. Data analysed by parsimony and Bayesian inference methods demonstrate that Agaonidae are monophyletic and that the previous classification is not supported. Agaonidae are partitioned into four groups: (i) Tetrapus, (ii) Ceratosolen + Kradibia, (iii) some Blastophaga + Wiebesia species, and (iv) all genera associated with monoecious figs and a few Blastophaga and Wiebesia. The latter group is subdivided into subgroups: (i) Pleistodontes, (ii) Blastophaga psenes and neocaledonian Dolichoris, (iii) some Blastophaga and Wiebesia species, and (iv) Platyscapa, all afrotropical genera and all genera associated with section Conosycea. Eleven genera were recovered as monophyletic, six were para- or polyphyletic, and two cannot be tested with our data set. Based on our phylogeny we propose a new classification for the Agaonidae. Two new subfamilies are proposed: Tetrapusiinae for the genus Tetrapus, and Kradibiinae for Ceratosolen + Kradibia. Liporrhopalum is synonymized with Kradibia and the subgenus Valisia of Blastophaga is elevated to generic rank. These changes resulted in 36 new combinations. Finally, we discuss the hypothesis of co-speciation between the pollinators and their host species by comparing the two phylogenies. ,© The Willi Hennig Society 2009. [source] | |||||||||||||