Bayesian inference for a skew-normal IRT model under the centred parameterization

Item response theory (IRT) comprises a set of statistical models which are useful in many fields, especially when there is interest in studying latent variables. These latent variables are directly considered in the Item Response Models (IRM) and they are usually called latent traits. A usual assumption for parameter estimation of the IRM, considering one group of examinees, is to assume that the latent traits are random variables which follow a standard normal distribution. However, many works suggest that this assumption does not apply in many cases. Furthermore, when this assumption does not hold, the parameter estimates tend to be biased and misleading inference can be obtained. Therefore, it is important to model the distribution of the latent traits properly. In this paper we present an alternative latent traits modeling based on the so-called skew-normal distribution; see Genton (2004). We used the centred parameterization, which was proposed by Azzalini (1985). This approach ensures the model identifiability as pointed out by Azevedo et al. (2009b). Also, a Metropolis Hastings within Gibbs sampling (MHWGS) algorithm was built for parameter estimation by using an augmented data approach. A simulation study was performed in order to assess the parameter recovery in the proposed model and the estimation method, and the effect of the asymmetry level of the latent traits distribution on the parameter estimation. Also, a comparison of our approach with other estimation methods (which consider the assumption of symmetric normality for the latent traits distribution) was considered. The results indicated that our proposed algorithm recovers properly all parameters. Specifically, the greater the asymmetry level, the better the performance of our approach compared with other approaches, mainly in the presence of small sample sizes (number of examinees). Furthermore, we analyzed a real data set which presents indication of asymmetry concerning the latent traits distribution. The results obtained by using our approach confirmed the presence of strong negative asymmetry of the latent traits distribution. (C) 2010 Elsevier B.V. All rights reserved.

On the Skew-Normal-Cauchy Distribution

In this article, we study further properties of a skew normal distribution, called the skew-normal-Cauchy (SNC) distribution by Nadarajah and Kotz (2003). A stochastic representation is obtained which allows alternative derivations for moments, moments generating function, and skewness and kurtosis coefficients. Issues related to singularity of the Fisher information matrix are investigated.

Multivariate measurement error models based on scale mixtures of the skew-normal distribution

Scale mixtures of the skew-normal (SMSN) distribution is a class of asymmetric thick-tailed distributions that includes the skew-normal (SN) distribution as a special case. The main advantage of these classes of distributions is that they are easy to simulate and have a nice hierarchical representation facilitating easy implementation of the expectation-maximization algorithm for the maximum-likelihood estimation. In this paper, we assume an SMSN distribution for the unobserved value of the covariates and a symmetric scale mixtures of the normal distribution for the error term of the model. This provides a robust alternative to parameter estimation in multivariate measurement error models. Specific distributions examined include univariate and multivariate versions of the SN, skew-t, skew-slash and skew-contaminated normal distributions. The results and methods are applied to a real data set.

On the skew-normal calibration model

In this article, we present the EM-algorithm for performing maximum likelihood estimation of an asymmetric linear calibration model with the assumption of skew-normally distributed error. A simulation study is conducted for evaluating the performance of the calibration estimator with interpolation and extrapolation situations. As one application in a real data set, we fitted the model studied in a dimensional measurement method used for calculating the testicular volume through a caliper and its calibration by using ultrasonography as the standard method. By applying this methodology, we do not need to transform the variables to have symmetrical errors. Another interesting aspect of the approach is that the developed transformation to make the information matrix nonsingular, when the skewness parameter is near zero, leaves the parameter of interest unchanged. Model fitting is implemented and the best choice between the usual calibration model and the model proposed in this article was evaluated by developing the Akaike information criterion, Schwarz`s Bayesian information criterion and Hannan-Quinn criterion.

Analysis of Ki-67 and Bcl-2 protein expression in normal colorectal mucosa of women with breast cancer

The aim of this study was to evaluate Ki-67 and Bcl-2 protein expression in the normal colorectal mucosa adjacent to adenomatous polyps in women with breast cancer. A cross-sectional, controlled study was conducted in 35 women with and without breast cancer who had adenomatous colorectal polyps. The patients were divided into two groups: Group A (a control group of women without breast cancer, n = 18) and Group B (a study group of women with breast cancer, n = 17). A sample of normal colonic mucosa was collected at a distance of 5 cm from the polypoid lesion to evaluate immunchistochemical expression of the Ki-67 and Bcl-2 proteins. Student`s t-test and the chi-square test were used to analyse Ki-67 and Bcl-2 expression, respectively. Statistical significance was established at p < 0.05. The mean percentage of Ki-67-stained nuclei in Groups A and B was 25.12 +/- 2.08 and 41.50 +/- 1.85, respectively (p < 0.001), whereas the percentage of cases with cells expressing Bcl-2 in Groups A and B was 17.6% and 82.4%, respectively (p < 0.003). In the present study, greater proliferative activity and greater expression of the antiapoptotic protein Bcl-2 was found in the normal colorectal mucosa of women with breast cancer. (C) 2009 Elsevier Ltd. All rights reserved.

Local Influence Analysis for Skew-Normal Linear Mixed Models

In this article, we consider local influence analysis for the skew-normal linear mixed model (SN-LMM). As the observed data log-likelihood associated with the SN-LMM is intractable, Cook`s well-known approach cannot be applied to obtain measures of local influence. Instead, we develop local influence measures following the approach of Zhu and Lee (2001). This approach is based on the use of an EM-type algorithm and is measurement invariant under reparametrizations. Four specific perturbation schemes are discussed. Results obtained for a simulated data set and a real data set are reported, illustrating the usefulness of the proposed methodology.

The log-bimodal-skew-normal model. A geochemical application

The main objective of this paper is to study a logarithm extension of the bimodal skew normal model introduced by Elal-Olivero et al. [1]. The model can then be seen as an alternative to the log-normal model typically used for fitting positive data. We study some basic properties such as the distribution function and moments, and discuss maximum likelihood for parameter estimation. We report results of an application to a real data set related to nickel concentration in soil samples. Model fitting comparison with several alternative models indicates that the model proposed presents the best fit and so it can be quite useful in real applications for chemical data on substance concentration. Copyright (C) 2011 John Wiley & Sons, Ltd.

Bayesian density estimation using Skew Student-t-Normal mixtures

We present a Bayesian approach for modeling heterogeneous data and estimate multimodal densities using mixtures of Skew Student-t-Normal distributions [Gomez, H.W., Venegas, O., Bolfarine, H., 2007. Skew-symmetric distributions generated by the distribution function of the normal distribution. Environmetrics 18, 395-407]. A stochastic representation that is useful for implementing a MCMC-type algorithm and results about existence of posterior moments are obtained. Marginal likelihood approximations are obtained, in order to compare mixture models with different number of component densities. Data sets concerning the Gross Domestic Product per capita (Human Development Report) and body mass index (National Health and Nutrition Examination Survey), previously studied in the related literature, are analyzed. (c) 2008 Elsevier B.V. All rights reserved.

Skew-normal linear calibration: a Bayesian perspective

In this paper, we present a Bayesian approach for estimation in the skew-normal calibration model, as well as the conditional posterior distributions which are useful for implementing the Gibbs sampler. Data transformation is thus avoided by using the methodology proposed. Model fitting is implemented by proposing the asymmetric deviance information criterion, ADIC, a modification of the ordinary DIC. We also report an application of the model studied by using a real data set, related to the relationship between the resistance and the elasticity of a sample of concrete beams. Copyright (C) 2008 John Wiley & Sons, Ltd.

A non-normal topology generated by a two-point selection

We construct a two-point selection f : [P](2) -> P, where P is the set of the irrational numbers, such that the space (P, tau(f)) is not normal and it is not collectionwise Hausdorff either. Here, tau(f) denotes the topology generated by the two-point selection f. This example answers a question posed by V. Gutev and T. Nogura. We also show that if f :[X](2) -> X is a two-point selection such that the topology tau(f) has countable pseudocharacter, then tau(f) is a Tychonoff topology. (C) 2008 Elsevier B.V. All rights reserved.

Bias correction in a multivariate normal regression model with general parameterization

This paper derives the second-order biases Of maximum likelihood estimates from a multivariate normal model where the mean vector and the covariance matrix have parameters in common. We show that the second order bias can always be obtained by means of ordinary weighted least-squares regressions. We conduct simulation studies which indicate that the bias correction scheme yields nearly unbiased estimators. (C) 2009 Elsevier B.V. All rights reserved.

Base Excision Repair Activities Differ in Human Lung Cancer Cells and Corresponding Normal Controls

Oxidative damage to DNA is thought to play a role in carcinogenesis by causing Mutations, and indeed accumulation of oxidized DNA bases has been observed in samples obtained from tumors but not from surrounding tissue within the same patient. Base excision repair (BER) is the main pathway for the repair of oxidized modifications both in nuclear and mitochondrial, DNA. In order to ascertain whether diminished BER capacity might account for increased levels of oxidative DNA damage in cancer cells, the activities of BER enzymes in three different lung cancer cell lines and their non-cancerous counterparts were measured using oligonucleotide substrates with single DNA lesions to assess specific BER enzymes. The activities of four BER enzymes, OGG1, NTH1, UDG and APE1, were compared in mitochondrial and nuclear extracts. For each specific lesion, the repair activities were similar among the three cell lines used. However, the specific activities and cancer versus control comparison differed significantly between the nuclear and mitochondrial compartments. OGG1 activity, as measured by 8-oxodA incision, was upregulated in cancer cell mitochondria but down-regulated in the nucleus when compared to control cells. Similarly, NTH1 activity was also up-regulated in mitochondrial extracts from cancer cells but did not change significantly in the nucleus. Together, these results support the idea that alterations in BER capacity are associated with carcinogenesis.

Förlossningsupplevelse hos kvinnor med normal graviditet och graviditetsdiabetes

Bakgrund: Forskning har visat att förlossningsupplevelsen har betydelse för kvinnansframtida inställning till barnafödande. Forskningsresultat har huvudsakligen presenterats för normala graviditeter eller där urvalet varit blandat (normala och komplicerade graviditeter). Begränsad forskning finns om hur komplicerad graviditet kan påverka förlossningsupplevelsen.Syfte: Att jämföra förlossningsupplevelse bland kvinnor som haft normal graviditet respektive graviditetsdiabetes samt studera sambandsfaktorer för förlossningsupplevelsen.Metod: Studien är en retrospektiv kohortstudie där data insamlats med hjälp av enkäter. Deltagarna (n=444) är slumpmässigt valda bland kvinnor i Sverige med normal graviditet och kvinnor med graviditetsdiabetes. Kvinnor som fött tvillingar och som inte angivit barnetsfödelsevikt exkluderades från fördjupningsstudien, vilket innebar att data för 429 kvinnor, 326 med normal graviditet och 103 med graviditetsdiabetes ingick. Parametriska och ickeparametriska analyser har genomförts för att analysera materialet.Resultat: Nästan två tredjedelar av kvinnorna (62,9%) hade en positiv förlossningsupplevelse. Kvinnor med graviditetsdiabetes hade oftare en negativ förlossningsupplevelse jämfört med kvinnor med normal graviditet. Nöjdhet med smärtlindringen visade ettsignifikant samband med förlossningsupplevelsen, de som var nöjda med smärtlindringen var mer nöjda med sin förlossningsupplevelse.Slutsats: Gravida kvinnor med komplicerad graviditet i form av graviditetsdiabetes har signifikant sämre förlossningsupplevelse jämfört med kvinnor som haft en normal graviditet.

Lifestyle and health status in a sample of Swedish women four years after pregnancy : a comparison of women with a history of normal pregnancy and women with a history of gestational diabetes mellitus

Background: Despite the recommendations to continue the regime of healthy food and physical activity (PA) postpartum for women with previous gestational diabetes mellitus (GDM), the scientific evidence reveals that these recommendations may not be complied to. This study compared lifestyle and health status in women whose pregnancy was complicated by GDM with women who had a normal pregnancy and delivery. Methods: The inclusion criteria were women with GDM (ICD-10: O24.4 A and O24.4B) and women with uncomplicated pregnancy and delivery in 2005 (ICD-10: O80.0). A random sample of women fulfilling the criteria (n = 882) were identified from the Swedish Medical Birth Register. A questionnaire was sent by mail to eligible women approximately four years after the pregnancy. A total of 444 women (50.8%) agreed to participate, 111 diagnosed with GDM in their pregnancy and 333 with normal pregnancy/ delivery. Results: Women with previous GDM were significantly older, reported higher body weight and less PA before the index pregnancy. No major differences between the groups were noticed regarding lifestyle at the follow-up. Overall, few participants fulfilled the national recommendations of PA and diet. At the follow-up, 19 participants had developed diabetes, all with previous GDM. Women with previous GDM reported significantly poorer self-rated health (SRH), higher level of sick-leave and more often using medication on regular basis. However, a history of GDM or having overt diabetes mellitus showed no association with poorer SRH in the multivariate analysis. Irregular eating habits, no regular PA, overweight/obesity, and regular use of medication were associated with poorer SRH in all participants. Conclusions: Suboptimal levels of PA, and fruit and vegetable consumption were found in a sample of women with a history of GDM as well as for women with normal pregnancy approximately four years after index pregnancy. Women with previous GDM seem to increase their PA after childbirth, but still they perform their PA at lower intensity than women with a history of normal pregnancy. Having GDM at index pregnancy or being diagnosed with overt diabetes mellitus at follow-up did not demonstrate associations with poorer SRH four years after delivery.