Sampling, WLS, and Mixed Models

Mixed models may be defined with or without reference to sampling, and can be used to predict realized random effects, as when estimating the latent values of study subjects measured with response error. When the model is specified without reference to sampling, a simple mixed model includes two random variables, one stemming from an exchangeable distribution of latent values of study subjects and the other, from the study subjects` response error distributions. Positive probabilities are assigned to both potentially realizable responses and artificial responses that are not potentially realizable, resulting in artificial latent values. In contrast, finite population mixed models represent the two-stage process of sampling subjects and measuring their responses, where positive probabilities are only assigned to potentially realizable responses. A comparison of the estimators over the same potentially realizable responses indicates that the optimal linear mixed model estimator (the usual best linear unbiased predictor, BLUP) is often (but not always) more accurate than the comparable finite population mixed model estimator (the FPMM BLUP). We examine a simple example and provide the basis for a broader discussion of the role of conditioning, sampling, and model assumptions in developing inference.

Predicting random effects with an expanded finite population mixed model

Prediction of random effects is an important problem with expanding applications. In the simplest context, the problem corresponds to prediction of the latent value (the mean) of a realized cluster selected via two-stage sampling. Recently, Stanek and Singer [Predicting random effects from finite population clustered samples with response error. J. Amer. Statist. Assoc. 99, 119-130] developed best linear unbiased predictors (BLUP) under a finite population mixed model that outperform BLUPs from mixed models and superpopulation models. Their setup, however, does not allow for unequally sized clusters. To overcome this drawback, we consider an expanded finite population mixed model based on a larger set of random variables that span a higher dimensional space than those typically applied to such problems. We show that BLUPs for linear combinations of the realized cluster means derived under such a model have considerably smaller mean squared error (MSE) than those obtained from mixed models, superpopulation models, and finite population mixed models. We motivate our general approach by an example developed for two-stage cluster sampling and show that it faithfully captures the stochastic aspects of sampling in the problem. We also consider simulation studies to illustrate the increased accuracy of the BLUP obtained under the expanded finite population mixed model. (C) 2007 Elsevier B.V. All rights reserved.

Design of associative memories using cellular neural networks

Cellular neural networks (CNNs) have locally connected neurons. This characteristic makes CNNs adequate for hardware implementation and, consequently, for their employment on a variety of applications as real-time image processing and construction of efficient associative memories. Adjustments of CNN parameters is a complex problem involved in the configuration of CNN for associative memories. This paper reviews methods of associative memory design based on CNNs, and provides comparative performance analysis of these approaches.

Improved likelihood inference in beta regression

We consider the issue of performing accurate small-sample likelihood-based inference in beta regression models, which are useful for modelling continuous proportions that are affected by independent variables. We derive small-sample adjustments to the likelihood ratio statistic in this class of models. The adjusted statistics can be easily implemented from standard statistical software. We present Monte Carlo simulations showing that inference based on the adjusted statistics we propose is much more reliable than that based on the usual likelihood ratio statistic. A real data example is presented.

Glycosaminoglycan distribution in the rat uterine cervix during the estrous cycle

OBJECTIVE: To analyze the amount of glycosaminoglycans in the uterine cervix during each phase of the rat estrous cycle. DESIGN: Based on vaginal smears, forty female, regularly cycling rats were divided into four groups (n = 10 for each group): GI - proestrous, GII - estrous, GIII - metaestrous and GIV - diestrous. Animals were sacrificed at each phase of the cycle, and the cervix was immediately removed and submitted to biochemical extraction and determination of sulfated glycosaminoglycans and hyaluronic acid. The results were analyzed by ANOVA followed by the Bonferroni post-hoc test. RESULTS: The uterine cervix had the highest amount of total sulfated glycosaminoglycans and dermatan sulfate during the estrous phase (8.90 ± 0.55 mg/g of cetonic extract, p<0.001; and 8.86 ± 0.57 mg/g of cetonic extract, p<0.001). In addition, there was more heparan sulfate at the cervix during the proestrous phase (0.185 ± 0.03 mg/g of cetonic extract) than during any other phase (p<0.001). There were no significant changes in the concentration of hyaluronic acid in the uterine cervix during the estrous cycle. CONCLUSION: Our data suggest that the amount of total sulfated glycosaminoglycans may be influenced by hormonal fluctuations related to the estrous cycle, with dermatan sulfate and heparan sulfate being the glycosaminoglycans most sensitive to hormonal change.

Mudanças no âmbito da testagem anti-HIV no Brasil entre 1998 e 2005

OBJETIVO: Analisar mudanças na realização de teste anti-HIV, as razões alegadas entre as pessoas que foram ou não testadas e o recebimento de aconselhamento. MÉTODOS: Estudos transversais conduzidos com homens e mulheres de 16 a 65 anos, com amostras representativas do Brasil urbano em 1998 (n=3.600) e 2005 (n=5.040). Características sociodemográficas, sexuais, reprodutivas e de experiências de vida e saúde foram consideradas na análise. A avaliação das possíveis diferenças nas distribuições das variáveis baseou-se nos testes qui-quadrado de Pearson e F design-based (±<5%). RESULTADOS: Em 1998, 20,2% dos entrevistados haviam realizado o teste e 33,6% em 2005. Foram testadas 60% das mulheres na faixa 25-34 anos, mas as que iniciaram a vida sexual antes dos 16 anos e reportaram quatro ou mais parceiros sexuais nos cinco anos anteriores à entrevista foram menos testadas. Não se observou aumento significativo da testagem entre homens, exceto para os de 55-65 anos, renda per capita entre 1-3 e 5-10 salários mínimos, aposentados, protestantes históricos e adeptos de cultos afro-brasileiros, moradores da região Norte/Nordeste e os que declararam parceria homo/bissexual ou não tiveram relações sexuais nos cinco anos anteriores à entrevista. Não aumentou a freqüência de testagem entre pessoas auto-avaliadas como sob alto risco para o HIV. Entre as mulheres, a freqüência de testagem pré-natal aumentou e a testagem por trabalho diminuiu entre os homens. Em 2005, metade dos testados não recebeu orientação antes ou após o teste. CONCLUSÕES: Houve expansão desigual na testagem, atingindo principalmente mulheres em idade reprodutiva, adultas e pessoas com melhores condições sociais. A testagem parece estar aumentando no País sem a devida atenção à decisão autônoma das pessoas e sem o provimento de maior e melhor oferta de aconselhamento

The Preparation of Ternary Solid Dispersions of an Herbal Drug via Spray Drying of Liquid Feed

The present study aimed the preparation and characterization of ternary solid dispersions by direct spray drying of a liquid suspension containing curcumin, a solubility enhancer and a drying aid. The experiments followed a Box-Behnken design in order to evaluate the influence of temperature, ratio of curcumin: lipidic carrier, and the collodial silicon dioxide content on the characteristics of the microparticulated solid dispersions. The angle of repose, Hausner factor, Carr index, water activity, and solubility were used to characterize solid dispersions. The results show that water activity, Hausner factor, and Carr index varied in an acceptable range for pharmaceutical purposes. The condition that maximizes solubility was determined using an exploratory design based on a surface response analysis and allowed a 3200-fold increase in curcumin solubility. Ternary solid dispersion showed a 90% curcumin release after 10min during a dissolution test. The results show that the spray drying of a liquid feed is an attractive and promising alternative to obtain enhanced solubility drug ternary solid dispersions.

Stereologic investigation of the posterior part of the hippocampus in schizophrenia

Structural magnetic resonance imaging and postmortem studies showed volume loss in the hippocampus in schizophrenia. The noted tissue reduction in the posterior section suggests that some cellular subfractions within this structure might be reduced in schizophrenia. To address this, we investigated numbers and densities of neurons, oligodendrocytes and astrocytes in the posterior hippocampal subregions in postmortem brains from ten patients with schizophrenia and ten matched controls using design-based stereology performed on Nissl-stained sections. Compared to the controls, the patients with schizophrenia showed a significant decrease in the mean number of oligodendrocytes in the left and right CA4. This is the first finding of reduced numbers of oligodendrocytes in CA4 of the posterior part of the hippocampus in schizophrenia. Our results are in line with earlier findings in the literature concerning decreased numbers of oligodendrocytes in the prefrontal cortex in schizophrenia. Our results may indicate disturbed connectivity of the CA4 of the posterior part of the hippocampus in schizophrenia and, thus, contribute to the growing number of studies showing the involvement of posterior hippocampal pathology in the pathophysiology of schizophrenia.

Stereological and allometric studies on neurons and axo-dendritic synapses in the superior cervical ganglia of rats, capybaras and horses

The superior cervical ganglion (SCG) in mammals varies in structure according to developmental age, body size, gender, lateral asymmetry, the size and nuclear content of neurons and the complexity and synaptic coverage of their dendritic trees. In small and medium-sized mammals, neuron number and size increase from birth to adulthood and, in phylogenetic studies, vary with body size. However, recent studies on larger animals suggest that body weight does not, in general, accurately predict neuron number. We have applied design-based stereological tools at the light-microscopic level to assess the volumetric composition of ganglia and to estimate the numbers and sizes of neurons in SCGs from rats, capybaras and horses. Using transmission electron microscopy, we have obtained design-based estimates of the surface coverage of dendrites by postsynaptic apposition zones and model-based estimates of the numbers and sizes of synaptophysin-labelled axo-dendritic synaptic disks. Linear regression analysis of log-transformed data has been undertaken in order to establish the nature of the relationships between numbers and SCG volume (V(scg)). For SCGs (five per species), the allometric relationship for neuron number (N) is N=35,067xV (scg) (0.781) and that for synapses is N=20,095,000xV (scg) (1.328) , the former being a good predictor and the latter a poor predictor of synapse number. Our findings thus reveal the nature of SCG growth in terms of its main ingredients (neurons, neuropil, blood vessels) and show that larger mammals have SCG neurons exhibiting more complex arborizations and greater numbers of axo-dendritic synapses.

Low-intensity Treadmill Exercise-related Changes in the Rat Stellate Ganglion Neurons

Stellate ganglion (SG) represents the main sympathetic input to the heart. This study aimed at investigating physical exercise-related changes in the quantitative aspects of SG neurons in treadmill-exercised Wistar rats. By applying state-of-the-art design-based stereology, the SG volume, total number of SG neurons, mean perikaryal volume of SG neurons, and the total volume of neurons in the whole SG have been examined. Arterial pressure and heart rate were also measured at the end of the exercise period. The present study showed that a low-intensity exercise training program caused a 12% decrease in the heart rate of trained rats. In contrast, there were no effects on systolic pressure, diastolic pressure, or mean arterial pressure. As to quantitative changes related to physical exercise, the main findings were a 21% increase in the fractional volume occupied by neurons in the SG, and an 83% increase in the mean perikaryal volume of SG neurons in treadmill-trained rats, which shows a remarkable neuron hypertrophy. It seems reasonable to infer that neuron hypertrophy may have been the result of a functional overload imposed on the SG neurons by initial posttraining sympathetic activation. From the novel stereological data we provide, further investigations are needed to shed light on the mechanistic aspect of neuron hypertrophy: what role does neuron hypertrophy play? Could neuron hypertrophy be assigned to the functional overload induced by physical exercise? (C) 2008 Wiley-Liss, Inc.

Hypertrophy and neuron loss: structural changes in sheep SCG induced by unilateral sympathectomy

Recently, superior cervical ganglionectomy has been performed to investigate a variety of scientific topics from regulation of intraocular pressure to suppression of lingual tumour growth. Despite these recent advances in our understanding of the functional mechanisms underlying superior cervical ganglion (SCG) growth and development after surgical ablation, there still exists a need for information concerning the quantitative nature of the relationships between the removed SCG and its remaining contralateral ganglion and between the remaining SCG and its modified innervation territory. To this end, using design-based stereological methods, we have investigated the structural changes induced by unilateral ganglionectomy in sheep at three distinct timepoints (2, 7 and 12 weeks) after surgery. The effects of time, and lateral (left-right) differences, were examined by two-way analyses of variance and paired t-tests. Following removal of the left SCG, the main findings were: (i) the remaining right SCG was bigger at shorter survival times, i.e. 74% at 2 weeks, 55% at 7 weeks and no increase by 12 weeks, (ii) by 7 weeks after surgery, the right SCG contained fewer neurons (no decrease at 2 weeks, 6% fewer by 7 weeks and 17% fewer by 12 weeks) and (iii) by 7 weeks, right SCG neurons were also larger and the magnitude of this increase grew substantially with time (no rise at 2 weeks, 77% by 7 weeks and 215% by 12 weeks). Interaction effects between time and ganglionectomy-induced changes were significant for SCG volume and mean perikaryal volume. These findings show that unilateral superior cervical ganglionectomy has profound effects on the contralateral ganglion. For future investigations, it would be interesting to examine the interaction between SCGs and their innervation targets after ganglionectomy. Is the ganglionectomy-induced imbalance between the sizes of innervation territories the milieu in which morphoquantitative changes, particularly changes in perikaryal volume and neuron number, occur? Mechanistically, how would those changes arise? Are there any grounds for believing in a ganglionectomy-triggered SCG cross-innervation and neuroplasticity? (C) 2011 ISDN. Published by Elsevier Ltd. All rights reserved.

The Developing Left Superior Cervical Ganglion of Pacas (Agouti Paca)

In this study the main question investigated was the number and size of both binucleate and mononucleate superior cervical ganglion (SCG) neurons and, whether post-natal development would affect these parameters. Twenty left SCGs from 20 male pacas were used. Four different ages were investigated, that is newborn (4 days), young (45 days), adult (2 years), and aged animals (7 years). By using design-based stereo-logical methods, that is the Cavalieri principle and a physical disector combined with serial sectioning, the total volume of ganglion and total number of mononucleate and binucleate neurons were estimated. Furthermore, the mean perikaryal (somal) volume of mononucleate and binucleate neurons was estimated using the vertical nucleator. The main findings of this study were a 154% increase in the SCG volume, a 95% increase in the total number of mononucleate SCG neurons and a 50% increase in the total volume of SCG neurons. In conclusion, apart from neuron number, different adaptive mechanisms may coexist in the autonomic nervous system to guarantee a functional homeostasis during ageing, which is not always associated with neuron losses. Anat Rec, 292:966-975, 2009. (C) 2009 Wiley-Liss, Inc.

A calibration approach based on Takagi-Sugeno fuzzy inference system for digital electronic compasses

Recently, the development of industrial processes brought on the outbreak of technologically complex systems. This development generated the necessity of research relative to the mathematical techniques that have the capacity to deal with project complexities and validation. Fuzzy models have been receiving particular attention in the area of nonlinear systems identification and analysis due to it is capacity to approximate nonlinear behavior and deal with uncertainty. A fuzzy rule-based model suitable for the approximation of many systems and functions is the Takagi-Sugeno (TS) fuzzy model. IS fuzzy models are nonlinear systems described by a set of if then rules which gives local linear representations of an underlying system. Such models can approximate a wide class of nonlinear systems. In this paper a performance analysis of a system based on IS fuzzy inference system for the calibration of electronic compass devices is considered. The contribution of the evaluated IS fuzzy inference system is to reduce the error obtained in data acquisition from a digital electronic compass. For the reliable operation of the TS fuzzy inference system, adequate error measurements must be taken. The error noise must be filtered before the application of the IS fuzzy inference system. The proposed method demonstrated an effectiveness of 57% at reducing the total error based on considered tests. (C) 2011 Elsevier Ltd. All rights reserved.

Design of 1D and 2D molecule-based magnets with the ligand 4,5-dimethyl-1,2-phenylenebis(oxamato)

Three new bimetallic oxamato-based magnets with the proligand 4,5-dimethyl-1,2-phenylenebis-(oxamato) (dmopba) were synthesized using water or dimethylsulfoxide (DMSO) as solvents. Single crystal X-ray diffraction provided structures for two of them: [MnCu(dmopba)(H(2)O)(3)]n center dot 4nH(2)O (1) and [MnCu(dmopba)(DMSO)(3)](n center dot)nDMSO (2). The crystalline structures for both 1 and 2 consist of linearly ordered oxamato-bridged Mn(II)Cu(II) bimetallic chains. The magnetic characterization revealed a typical behaviour of ferrimagnetic chains for 1 and 2. Least-squares fits of the experimental magnetic data performed in the 300-20 K temperature range led to J(MnCu) = -27.9 cm(-1), g(Cu) = 2.09 and g(Mn) = 1.98 for 1 and J(MnCu) = -30.5 cm(-1), g(Cu) = 2.09 and g(Mn) = 2.02 for 2 (H = -J(MnCu)Sigma S(Mn, i)(S(Cu, i) + S(Cu, i-1))). The two-dimensional ferrimagnetic system [Me(4)N](2n){Co(2)[Cu(dmopba)](3)}center dot 4nDMSO center dot nH(2)O (3) was prepared by reaction of Co(II) ions and an excess of [Cu(dmopba)](2-) in DMSO. The study of the temperature dependence of the magnetic susceptibility as well as the temperature and field dependences of the magnetization revealed a cluster glass-like behaviour for 3.

Haplotype distribution of five nuclear genes based on network genealogies and Bayesian inference indicates that Trypanosoma cruzi hybrid strains are polyphyletic

Chagas disease is still a major public health problem in Latin America. Its causative agent, Trypanosoma cruzi, can be typed into three major groups, T. cruzi I, T. cruzi II and hybrids. These groups each have specific genetic characteristics and epidemiological distributions. Several highly virulent strains are found in the hybrid group; their origin is still a matter of debate. The null hypothesis is that the hybrids are of polyphyletic origin, evolving independently from various hybridization events. The alternative hypothesis is that all extant hybrid strains originated from a single hybridization event. We sequenced both alleles of genes encoding EF-1 alpha, actin and SSU rDNA of 26 T. cruzi strains and DHFR-TS and TR of 12 strains. This information was used for network genealogy analysis and Bayesian phylogenies. We found T. cruzi I and T. cruzi II to be monophyletic and that all hybrids had different combinations of T. cruzi I and T. cruzi II haplotypes plus hybrid-specific haplotypes. Bootstrap values (networks) and posterior probabilities (Bayesian phylogenies) of clades supporting the monophyly of hybrids were far below the 95% confidence interval, indicating that the hybrid group is polyphyletic. We hypothesize that T. cruzi I and T. cruzi II are two different species and that the hybrids are extant representatives of independent events of genome hybridization, which sporadically have sufficient fitness to impact on the epidemiology of Chagas disease.