Family Distribution (family + distribution)

Distribution by Scientific Domains

Selected Abstracts

A unified framework for transmission-disequilibrium test analysis of discrete and continuous traits

Ying Liu
Abstract This paper presents a unified framework for transmission-disequilibrium tests for discrete and continuous traits. A conditional score test is derived that maximizes power to detect small effects for any exponential family distribution, which includes binary and normal distributions, and distributions that are skewed or have non-normal kurtosis. The specific distributional form need not be specified, and the method applies to sibships of arbitrary size. Formulas for the distribution of the test statistic are given for models including complex genetic effects (additive, dominant, and recessive gene action), covariates, multiple gene models including gene-gene interactions or heterogeneity, and gene-environment interactions. We develop refinements of our method for trait-based sampling designs and multiple siblings that can have dramatic effects on power. Genet. Epidemiol. 22:26,40, 2002. © 2002 Wiley-Liss, Inc. [source]

Floristic inventory and diversity assessment of a lowland African Montane Rainforest at Korup, Cameroon and implications for conservation

Innocent Ndoh Mbue
Abstract Twenty modified-Whittaker plots were stratified at different sampling locations from February to May of 2008 in the central zone of Korup National Park, Cameroon. Our interest was to assess floristic diversity and investigate their relationship with environmental variables. Diversity profiles and rank abundance,curves were used for diversity analysis while canonical correspondence analysis and species,response curves were used to investigate the relationships between the response and explanatory variables. Of the 66 families identified, the Rubiaceae (999 species) were the most abundant. The Sterculiaceae (basal area = 10.482 m2 ha,1) were the dominant family, while the co-dominant families included the Ebenaceae (basal area = 9.092 m2 ha,1) and the Euphorbiaceae (basal area = 8.168 m2 ha,1). Soil variables explained 54.3% of total variation in family distribution. Canonical axes were related to different environmental gradients: axis1 was related to increasing canopy cover (r = 0.6951); axis 2, increasing Magnesium (r = 0.8465) and effective cation exchange capacity (r = 0.5899); axis 3, increasing effective cation exchange capacity (r = 0.5536); while axis 4, increasing Phosphorus concentration (r = 0.5232). Our results demonstrate the advantage which diversity profiles have over single or combination of indices, and the importance of using a combination of methodologies in diversity analysis. Résumé De février à mai 2008, vingt parcelles de Whittaker modifié ont été stratifiées à différents sites d'échantillonnage dans la zone centrale du Parc National de Korup, au Cameroun. Nous voulions évaluer la diversité floristique et étudier son lien avec diverses variables environnementales. Nous avons employé des profils de diversité et des courbes de rangs d'abondance pour l'analyse de la diversité, tandis que nous utilisions une analyse canonique des correspondances et des courbes de réponse des espèces pour étudier les relations entre les réponses et les variables explicatives. Sur les 66 familles identifiées, les Rubiacées (999 espèces) étaient les plus abondantes. Les Sterculiacées (surface basale = 10,482 m2 ha,1) étaient la famille dominante et, parmi les familles co-dominantes, il y avait les Ebénacées (surface basale = 9,092 m2 ha,1) et les Euphorbiacées (surface basale = 8,168 m2 ha,1). Des variables du sol expliquaient 54,3% de la variation totale de la distribution des familles. Les axes canoniques ont été liés aux différents gradients environnementaux; l'axe 1 était liéà une couverture croissante de la canopée (r = 0,6951); l'axe 2 à une augmentation du magnésium (r = 0,8465) et à la capacité réelle d'échange de cations (r = 0,5899); l'axe 3 à une capacité réelle croissante d'échanges de cations (r = 0,5536); et l'axe 4 à une concentration croissante en phosphore (r = 0,5532). Nos résultats montrent l'avantage que les profils de diversité ont sur des indices uniques ou combinés et l'importance d'utiliser une combinaison de méthodologies dans une analyse de diversité. [source]

Generalized Additive Modeling with Implicit Variable Selection by Likelihood-Based Boosting

BIOMETRICS, Issue 4 2006
Gerhard Tutz
Summary The use of generalized additive models in statistical data analysis suffers from the restriction to few explanatory variables and the problems of selection of smoothing parameters. Generalized additive model boosting circumvents these problems by means of stagewise fitting of weak learners. A fitting procedure is derived which works for all simple exponential family distributions, including binomial, Poisson, and normal response variables. The procedure combines the selection of variables and the determination of the appropriate amount of smoothing. Penalized regression splines and the newly introduced penalized stumps are considered as weak learners. Estimates of standard deviations and stopping criteria, which are notorious problems in iterative procedures, are based on an approximate hat matrix. The method is shown to be a strong competitor to common procedures for the fitting of generalized additive models. In particular, in high-dimensional settings with many nuisance predictor variables it performs very well. [source]

Bayesian Covariance Selection in Generalized Linear Mixed Models

BIOMETRICS, Issue 2 2006
Bo Cai
Summary The generalized linear mixed model (GLMM), which extends the generalized linear model (GLM) to incorporate random effects characterizing heterogeneity among subjects, is widely used in analyzing correlated and longitudinal data. Although there is often interest in identifying the subset of predictors that have random effects, random effects selection can be challenging, particularly when outcome distributions are nonnormal. This article proposes a fully Bayesian approach to the problem of simultaneous selection of fixed and random effects in GLMMs. Integrating out the random effects induces a covariance structure on the multivariate outcome data, and an important problem that we also consider is that of covariance selection. Our approach relies on variable selection-type mixture priors for the components in a special Cholesky decomposition of the random effects covariance. A stochastic search MCMC algorithm is developed, which relies on Gibbs sampling, with Taylor series expansions used to approximate intractable integrals. Simulated data examples are presented for different exponential family distributions, and the approach is applied to discrete survival data from a time-to-pregnancy study. [source]