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.

Molecular determinants of caste differentiation in the highly eusocial honeybee Apis mellifera

Abstract Background In honeybees, differential feeding of female larvae promotes the occurrence of two different phenotypes, a queen and a worker, from identical genotypes, through incremental alterations, which affect general growth, and character state alterations that result in the presence or absence of specific structures. Although previous studies revealed a link between incremental alterations and differential expression of physiometabolic genes, the molecular changes accompanying character state alterations remain unknown. Results By using cDNA microarray analyses of >6,000 Apis mellifera ESTs, we found 240 differentially expressed genes (DEGs) between developing queens and workers. Many genes recorded as up-regulated in prospective workers appear to be unique to A. mellifera, suggesting that the workers' developmental pathway involves the participation of novel genes. Workers up-regulate more developmental genes than queens, whereas queens up-regulate a greater proportion of physiometabolic genes, including genes coding for metabolic enzymes and genes whose products are known to regulate the rate of mass-transforming processes and the general growth of the organism (e.g., tor). Many DEGs are likely to be involved in processes favoring the development of caste-biased structures, like brain, legs and ovaries, as well as genes that code for cytoskeleton constituents. Treatment of developing worker larvae with juvenile hormone (JH) revealed 52 JH responsive genes, specifically during the critical period of caste development. Using Gibbs sampling and Expectation Maximization algorithms, we discovered eight overrepresented cis-elements from four gene groups. Graph theory and complex networks concepts were adopted to attain powerful graphical representations of the interrelation between cis-elements and genes and objectively quantify the degree of relationship between these entities. Conclusion We suggest that clusters of functionally related DEGs are co-regulated during caste development in honeybees. This network of interactions is activated by nutrition-driven stimuli in early larval stages. Our data are consistent with the hypothesis that JH is a key component of the developmental determination of queen-like characters. Finally, we propose a conceptual model of caste differentiation in A. mellifera based on gene-regulatory networks.

Occurrence and behavior of butyltins in intertidal and shallow subtidal surface sediments of an estuarine beach under different sampling conditions

Contamination by butyltin compounds (BTs) has been reported in estuarine environments worldwide, with serious impacts on the biota of these areas. Considering that BTs can be degraded by varying environmental conditions such as incident light and salinity, the short-term variations in such factors may lead to inaccurate estimates of BTs concentrations in nature. Therefore, the present study aimed to evaluate the possibility that measurements of BTs in estuarine sediments are influenced by different sampling conditions, including period of the day (day or night), tidal zone (intertidal or subtidal), and tides (high or low). The study area is located on the Brazilian southeastern coast, Sao Vicente Estuary, at Pescadores Beach, where BT contamination was previously detected. Three replicate samples of surface sediment were collected randomly in each combination of period of the day, tidal zone, and tide condition, from three subareas along the beach, totaling 72 samples. BTs were analyzed by GC-PFPD using a tin filter and a VF-5 column, by means of a validated method. The concentrations of tributyltin (TBT), dibutyltin (DBT), and monobutyltin (MBT) ranged from undetectable to 161 ng Sn g(-1) (d.w.). In most samples (71%), only MBT was quantifiable, whereas TBTs were measured in only 14, suggesting either an old contamination or rapid degradation processes. DBT was found in 27 samples, but could be quantified in only one. MBT concentrations did not differ significantly with time of day, zones, or tide conditions. DBT and TBT could not be compared under all these environmental conditions, because only a few samples were above the quantification limit. Pooled samples of TBT did not reveal any difference between day and night. These results indicated that, in assessing contamination by butyltin compounds, surface-sediment samples can be collected in any environmental conditions. However, the wide variation of BTs concentrations in the study area, i.e., over a very small geographic scale, illustrates the need for representative hierarchical and composite sampling designs that are compatible with the multiscalar temporal and spatial variability common to most marine systems. The use of such sampling designs will be necessary for future attempts to quantitatively evaluate and monitor the occurrence and impact of these compounds in nature

Investigating Smart Sampling as a population initialization method for Differential Evolution in continuous problems

Recently, researches have shown that the performance of metaheuristics can be affected by population initialization. Opposition-based Differential Evolution (ODE), Quasi-Oppositional Differential Evolution (QODE), and Uniform-Quasi-Opposition Differential Evolution (UQODE) are three state-of-the-art methods that improve the performance of the Differential Evolution algorithm based on population initialization and different search strategies. In a different approach to achieve similar results, this paper presents a technique to discover promising regions in a continuous search-space of an optimization problem. Using machine-learning techniques, the algorithm named Smart Sampling (SS) finds regions with high possibility of containing a global optimum. Next, a metaheuristic can be initialized inside each region to find that optimum. SS and DE were combined (originating the SSDE algorithm) to evaluate our approach, and experiments were conducted in the same set of benchmark functions used by ODE, QODE and UQODE authors. Results have shown that the total number of function evaluations required by DE to reach the global optimum can be significantly reduced and that the success rate improves if SS is employed first. Such results are also in consonance with results from the literature, stating the importance of an adequate starting population. Moreover, SS presents better efficacy to find initial populations of superior quality when compared to the other three algorithms that employ oppositional learning. Finally and most important, the SS performance in finding promising regions is independent of the employed metaheuristic with which SS is combined, making SS suitable to improve the performance of a large variety of optimization techniques. (C) 2012 Elsevier Inc. All rights reserved.

Decisions on Temporal Sampling Protocol Influence the Detection of Ecological Patterns

Within-site variability in species detectability is a problem common to many biodiversity assessments and can strongly bias the results. Such variability can be caused by many factors, including simple counting inaccuracies, which can be solved by increasing sample size, or by temporal changes in species behavior, meaning that the way the temporal sampling protocol is designed is also very important. Here we use the example of mist-netted tropical birds to determine how design decisions in the temporal sampling protocol can alter the data collected and how these changes might affect the detection of ecological patterns, such as the species-area relationship (SAR). Using data from almost 3400 birds captured from 21,000 net-hours at 31 sites in the Brazilian Atlantic Forest, we found that the magnitude of ecological trends remained fairly stable, but the probability of detecting statistically significant ecological patterns varied depending on sampling effort, time of day and season in which sampling was conducted. For example, more species were detected in the wet season, but the SAR was strongest in the dry season. We found that the temporal distribution of sampling effort was more important than its total amount, discovering that similar ecological results could have been obtained with one-third of the total effort, as long as each site had been equally sampled over 2 yr. We discuss that projects with the same sampling effort and spatial design, but with different temporal sampling protocol are likely to report different ecological patterns, which may ultimately lead to inappropriate conservation strategies.

Use of passive diffusion sampling method for defining NO2 concentrations gradient in São Paulo, Brazil

Abstract Background Air pollution in São Paulo is constantly being measured by the State of Sao Paulo Environmental Agency, however there is no information on the variation between places with different traffic densities. This study was intended to identify a gradient of exposure to traffic-related air pollution within different areas in São Paulo to provide information for future epidemiological studies. Methods We measured NO2 using Palmes' diffusion tubes in 36 sites on streets chosen to be representative of different road types and traffic densities in São Paulo in two one-week periods (July and August 2000). In each study period, two tubes were installed in each site, and two additional tubes were installed in 10 control sites. Results Average NO2 concentrations were related to traffic density, observed on the spot, to number of vehicles counted, and to traffic density strata defined by the city Traffic Engineering Company (CET). Average NO2concentrations were 63μg/m3 and 49μg/m3 in the first and second periods, respectively. Dividing the sites by the observed traffic density, we found: heavy traffic (n = 17): 64μg/m3 (95% CI: 59μg/m3 – 68μg/m3); local traffic (n = 16): 48μg/m3 (95% CI: 44μg/m3 – 52μg/m3) (p < 0.001). Conclusion The differences in NO2 levels between heavy and local traffic sites are large enough to suggest the use of a more refined classification of exposure in epidemiological studies in the city. Number of vehicles counted, traffic density observed on the spot and traffic density strata defined by the CET might be used as a proxy for traffic exposure in São Paulo when more accurate measurements are not available.