Parameter recovery for a skew-normal IRT model under a Bayesian approach: hierarchical framework, prior and kernel sensitivity and sample size

Item response theory (IRT) comprises a set of statistical models which are useful in many fields, especially when there is an interest in studying latent variables (or latent traits). Usually such latent traits are assumed to be random variables and a convenient distribution is assigned to them. A very common choice for such a distribution has been the standard normal. Recently, Azevedo et al. [Bayesian inference for a skew-normal IRT model under the centred parameterization, Comput. Stat. Data Anal. 55 (2011), pp. 353-365] proposed a skew-normal distribution under the centred parameterization (SNCP) as had been studied in [R. B. Arellano-Valle and A. Azzalini, The centred parametrization for the multivariate skew-normal distribution, J. Multivariate Anal. 99(7) (2008), pp. 1362-1382], to model the latent trait distribution. This approach allows one to represent any asymmetric behaviour concerning the latent trait distribution. Also, they developed a Metropolis-Hastings within the Gibbs sampling (MHWGS) algorithm based on the density of the SNCP. They showed that the algorithm recovers all parameters properly. Their results indicated that, in the presence of asymmetry, the proposed model and the estimation algorithm perform better than the usual model and estimation methods. Our main goal in this paper is to propose another type of MHWGS algorithm based on a stochastic representation (hierarchical structure) of the SNCP studied in [N. Henze, A probabilistic representation of the skew-normal distribution, Scand. J. Statist. 13 (1986), pp. 271-275]. Our algorithm has only one Metropolis-Hastings step, in opposition to the algorithm developed by Azevedo et al., which has two such steps. This not only makes the implementation easier but also reduces the number of proposal densities to be used, which can be a problem in the implementation of MHWGS algorithms, as can be seen in [R.J. Patz and B.W. Junker, A straightforward approach to Markov Chain Monte Carlo methods for item response models, J. Educ. Behav. Stat. 24(2) (1999), pp. 146-178; R. J. Patz and B. W. Junker, The applications and extensions of MCMC in IRT: Multiple item types, missing data, and rated responses, J. Educ. Behav. Stat. 24(4) (1999), pp. 342-366; A. Gelman, G.O. Roberts, and W.R. Gilks, Efficient Metropolis jumping rules, Bayesian Stat. 5 (1996), pp. 599-607]. Moreover, we consider a modified beta prior (which generalizes the one considered in [3]) and a Jeffreys prior for the asymmetry parameter. Furthermore, we study the sensitivity of such priors as well as the use of different kernel densities for this parameter. Finally, we assess the impact of the number of examinees, number of items and the asymmetry level on the parameter recovery. Results of the simulation study indicated that our approach performed equally as well as that in [3], in terms of parameter recovery, mainly using the Jeffreys prior. Also, they indicated that the asymmetry level has the highest impact on parameter recovery, even though it is relatively small. A real data analysis is considered jointly with the development of model fitting assessment tools. The results are compared with the ones obtained by Azevedo et al. The results indicate that using the hierarchical approach allows us to implement MCMC algorithms more easily, it facilitates diagnosis of the convergence and also it can be very useful to fit more complex skew IRT models.

Is Drosera meristocaulis a pygmy sundew? Evidence of a long-distance dispersal between Western Australia and northern South America

South America and Oceania possess numerous floristic similarities, often confirmed by morphological and molecular data. The carnivorous Drosera meristocaulis (Droseraceae), endemic to the Neblina highlands of northern South America, was known to share morphological characters with the pygmy sundews of Drosera sect. Bryastrum, which are endemic to Australia and New Zealand. The inclusion of D. meristocaulis in a molecular phylogenetic analysis may clarify its systematic position and offer an opportunity to investigate character evolution in Droseraceae and phylogeographic patterns between South America and Oceania. was included in a molecular phylogenetic analysis of Droseraceae, using nuclear internal transcribed spacer (ITS) and plastid rbcL and rps16 sequence data. Pollen of D. meristocaulis was studied using light microscopy and scanning electron microscopy techniques, and the karyotype was inferred from root tip meristem. The phylogenetic inferences (maximum parsimony, maximum likelihood and Bayesian approaches) substantiate with high statistical support the inclusion of sect. Meristocaulis and its single species, D. meristocaulis, within the Australian Drosera clade, sister to a group comprising species of sect. Bryastrum. A chromosome number of 2n approx. 3236 supports the phylogenetic position within the Australian clade. The undivided styles, conspicuous large setuous stipules, a cryptocotylar (hypogaeous) germination pattern and pollen tetrads with aperture of intermediate type 78 are key morphological traits shared between D. meristocaulis and pygmy sundews of sect. Bryastrum from Australia and New Zealand. The multidisciplinary approach adopted in this study (using morphological, palynological, cytotaxonomic and molecular phylogenetic data) enabled us to elucidate the relationships of the thus far unplaced taxon D. meristocaulis. Long-distance dispersal between southwestern Oceania and northern South America is the most likely scenario to explain the phylogeographic pattern revealed.

Cointegration: Bayesian Significance Test

To estimate causal relationships, time series econometricians must be aware of spurious correlation, a problem first mentioned by Yule (1926). To deal with this problem, one can work either with differenced series or multivariate models: VAR (VEC or VECM) models. These models usually include at least one cointegration relation. Although the Bayesian literature on VAR/VEC is quite advanced, Bauwens et al. (1999) highlighted that "the topic of selecting the cointegrating rank has not yet given very useful and convincing results". The present article applies the Full Bayesian Significance Test (FBST), especially designed to deal with sharp hypotheses, to cointegration rank selection tests in VECM time series models. It shows the FBST implementation using both simulated and available (in the literature) data sets. As illustration, standard non informative priors are used.

Statistical Information: A Bayesian Perspective

We explore the meaning of information about quantities of interest. Our approach is divided in two scenarios: the analysis of observations and the planning of an experiment. First, we review the Sufficiency, Conditionality and Likelihood principles and how they relate to trivial experiments. Next, we review Blackwell Sufficiency and show that sampling without replacement is Blackwell Sufficient for sampling with replacement. Finally, we unify the two scenarios presenting an extension of the relationship between Blackwell Equivalence and the Likelihood Principle.

Multiple Quaternary Refugia in the Eastern Guiana Shield Revealed by Comparative Phylogeography of 12 Frog Species

The Guiana Shield (GS) is one of the most pristine regions of Amazonia and biologically one of the richest areas on Earth. How and when this massive diversity arose remains the subject of considerable debate. The prevailing hypothesis of Quaternary glacial refugia suggests that a part of the eastern GS, among other areas in Amazonia, served as stable forested refugia during periods of aridity. However, the recently proposed disturbance-vicariance hypothesis proposes that fluctuations in temperature on orbital timescales, with some associated aridity, have driven Neotropical diversification. The expectations of the temporal and spatial organization of biodiversity differ between these two hypotheses. Here, we compare the genetic structure of 12 leaf-litter inhabiting frog species from the GS lowlands using a combination of mitochondrial and nuclear sequences in an integrative analytical approach that includes phylogenetic reconstructions, molecular dating, and Geographic Information System methods. This comparative and integrated approach overcomes the well-known limitations of phylogeographic inference based on single species and single loci. All of the focal species exhibit distinct phylogeographic patterns highlighting taxon-specific historical distributions, ecological tolerances to climatic disturbance, and dispersal abilities. Nevertheless, all but one species exhibit a history of fragmentation/isolation within the eastern GS during the Quaternary with spatial and temporal concordance among species. The signature of isolation in northern French Guiana (FG) during the early Pleistocene is particularly clear. Approximate Bayesian Computation supports the synchrony of the divergence between northern FG and other GS lineages. Substructure observed throughout the GS suggests further Quaternary fragmentation and a role for rivers. Our findings support fragmentation of moist tropical forest in the eastern GS during this period when the refuge hypothesis would have the region serving as a contiguous wet-forest refuge.

Bayesian analysis of random regression models using B-splines to model test-day milk yield of Holstein cattle in Brazil

The objective of this paper is to model variations in test-day milk yields of first lactations of Holstein cows by RR using B-spline functions and Bayesian inference in order to fit adequate and parsimonious models for the estimation of genetic parameters. They used 152,145 test day milk yield records from 7317 first lactations of Holstein cows. The model established in this study was additive, permanent environmental and residual random effects. In addition, contemporary group and linear and quadratic effects of the age of cow at calving were included as fixed effects. Authors modeled the average lactation curve of the population with a fourth-order orthogonal Legendre polynomial. They concluded that a cubic B-spline with seven random regression coefficients for both the additive genetic and permanent environment effects was to be the best according to residual mean square and residual variance estimates. Moreover they urged a lower order model (quadratic B-spline with seven random regression coefficients for both random effects) could be adopted because it yielded practically the same genetic parameter estimates with parsimony. (C) 2012 Elsevier B.V. All rights reserved.

From Amazonia to the Atlantic forest: Molecular phylogeny of Phyzelaphryninae frogs reveals unexpected diversity and a striking biogeographic pattern emphasizing conservation challenges

Documenting the Neotropical amphibian diversity has become a major challenge facing the threat of global climate change and the pace of environmental alteration. Recent molecular phylogenetic studies have revealed that the actual number of species in South American tropical forests is largely underestimated, but also that many lineages are millions of years old. The genera Phyzelaphryne (1 sp.) and Adelophryne (6 spp.), which compose the subfamily Phyzelaphryninae, include poorly documented, secretive, and minute frogs with an unusual distribution pattern that encompasses the biotic disjunction between Amazonia and the Atlantic forest. We generated >5.8 kb sequence data from six markers for all seven nominal species of the subfamily as well as for newly discovered populations in order to (1) test the monophyly of Phyzelaphryninae, Adelophryne and Phyzelaphryne, (2) estimate species diversity within the subfamily, and (3) investigate their historical biogeography and diversification. Phylogenetic reconstruction confirmed the monophyly of each group and revealed deep subdivisions within Adelophryne and Phyzelaphryne, with three major clades in Adelophryne located in northern Amazonia, northern Atlantic forest and southern Atlantic forest. Our results suggest that the actual number of species in Phyzelaphryninae is, at least, twice the currently recognized species diversity, with almost every geographically isolated population representing an anciently divergent candidate species. Such results highlight the challenges for conservation, especially in the northern Atlantic forest where it is still degraded at a fast pace. Molecular dating revealed that Phyzelaphryninae originated in Amazonia and dispersed during early Miocene to the Atlantic forest. The two Atlantic forest clades of Adelophryne started to diversify some 7 Ma minimum, while the northern Amazonian Adelophryne diversified much earlier, some 13 Ma minimum. This striking biogeographic pattern coincides with major events that have shaped the face of the South American continent, as we know it today. (C) 2012 Elsevier Inc. All rights reserved.

Phylogenetic analysis of complete genome sequences of hepatitis B virus from an Afro-Colombian community: presence of HBV F3/A1 recombinant strain

Background: Hepatitis B virus (HBV) infection is one of the most prevalent viral infections in humans and represents a serious public health problem. In Colombia, our group reported recently the presence of subgenotypes F3, A2 and genotype G in Bogota. The aim of this study was to characterize the HBV genotypes circulating in Quibdo, the largest Afro-descendant community in Colombia. Sixty HBsAg-positive samples were studied. A fragment of 1306 bp (S/POL) was amplified by nested PCR. Positive samples to S/POL fragment were submitted to PCR amplification of the HBV complete genome. Findings: The distribution of HBV genotypes was: A1 (52.17%), E (39.13%), D3 (4.3%) and F3/A1 (4.3%). An HBV recombinant strain subgenotype F3/A1 was found for the first time. Conclusions: This study is the first analysis of complete HBV genome sequences from Afro-Colombian population. It was found an important presence of HBV/A1 and HBV/E genotypes. A new recombinant strain of HBV genotype F3/A1 was reported in this population. This fact may be correlated with the introduction of these genotypes in the times of slavery.

A Bayesian destructive weighted Poisson cure rate model and an application to a cutaneous melanoma data

In this article, we propose a new Bayesian flexible cure rate survival model, which generalises the stochastic model of Klebanov et al. [Klebanov LB, Rachev ST and Yakovlev AY. A stochastic-model of radiation carcinogenesis - latent time distributions and their properties. Math Biosci 1993; 113: 51-75], and has much in common with the destructive model formulated by Rodrigues et al. [Rodrigues J, de Castro M, Balakrishnan N and Cancho VG. Destructive weighted Poisson cure rate models. Technical Report, Universidade Federal de Sao Carlos, Sao Carlos-SP. Brazil, 2009 (accepted in Lifetime Data Analysis)]. In our approach, the accumulated number of lesions or altered cells follows a compound weighted Poisson distribution. This model is more flexible than the promotion time cure model in terms of dispersion. Moreover, it possesses an interesting and realistic interpretation of the biological mechanism of the occurrence of the event of interest as it includes a destructive process of tumour cells after an initial treatment or the capacity of an individual exposed to irradiation to repair altered cells that results in cancer induction. In other words, what is recorded is only the damaged portion of the original number of altered cells not eliminated by the treatment or repaired by the repair system of an individual. Markov Chain Monte Carlo (MCMC) methods are then used to develop Bayesian inference for the proposed model. Also, some discussions on the model selection and an illustration with a cutaneous melanoma data set analysed by Rodrigues et al. [Rodrigues J, de Castro M, Balakrishnan N and Cancho VG. Destructive weighted Poisson cure rate models. Technical Report, Universidade Federal de Sao Carlos, Sao Carlos-SP. Brazil, 2009 (accepted in Lifetime Data Analysis)] are presented.

Phylogeography of the neotropical Anopheles triannulatus complex (Diptera: Culicidae) supports deep structure and complex patterns

Abstract Background The molecular phylogenetic relationships and population structure of the species of the Anopheles triannulatus complex: Anopheles triannulatus s.s., Anopheles halophylus and the putative species Anopheles triannulatus C were investigated. Methods The mitochondrial COI gene, the nuclear white gene and rDNA ITS2 of samples that include the known geographic distribution of these taxa were analyzed. Phylogenetic analyses were performed using Bayesian inference, Maximum parsimony and Maximum likelihood approaches. Results Each data set analyzed septely yielded a different topology but none provided evidence for the seption of An. halophylus and An. triannulatus C, consistent with the hypothesis that the two are undergoing incipient speciation. The phylogenetic analyses of the white gene found three main clades, whereas the statistical parsimony network detected only a single metapopulation of Anopheles triannulatus s.l. Seven COI lineages were detected by phylogenetic and network analysis. In contrast, the network, but not the phylogenetic analyses, strongly supported three ITS2 groups. Combined data analyses provided the best resolution of the trees, with two major clades, Amazonian (clade I) and trans-Andean + Amazon Delta (clade II). Clade I consists of multiple subclades: An. halophylus + An. triannulatus C; trans-Andean Venezuela; central Amazonia + central Bolivia; Atlantic coastal lowland; and Amazon delta. Clade II includes three subclades: Panama; cis-Andean Colombia; and cis-Venezuela. The Amazon delta specimens are in both clades, likely indicating local sympatry. Spatial and molecular variance analyses detected nine groups, corroborating some of subclades obtained in the combined data analysis. Conclusion Combination of the three molecular markers provided the best resolution for differentiation within An. triannulatus s.s. and An. halophylus and C. The latest two species seem to be very closely related and the analyses performed were not conclusive regarding species differentiation. Further studies including new molecular markers would be desirable to solve this species status question. Besides, results of the study indicate a trans-Andean origin for An. triannulatus s.l. The potential implications for malaria epidemiology remain to be investigated.

Molecular phylogeny, morphology and their implications for the taxonomy of Eriocaulaceae

The pantropical family Eriocaulaceae includes ten genera and c. 1,400 species, with diversity concentrated in the New World. The last complete revision of the family was published more than 100 years ago, and until recently the generic and infrageneric relationships were poorly resolved. However, a multi-disciplinary approach over the last 30 years, using morphological and anatomical characters, has been supplemented with additional data from palynology, chemistry, embryology, population genetics, cytology and, more recently, molecular phylogenetic studies. This led to a reassessment of phylogenetic relationships within the family. In this paper we present new data for the ITS and trnL-F regions, analysed separately and in combination, using maximum parsimony and Bayesian inference. The data confirm previous results, and show that many characters traditionally used for differentiating and circumscribing the genera within the family are homoplasious. A new generic key with characters from various sources and reflecting the current taxonomic changes is presented.