Celso Rômulo Barbosa Cabral

Multivariate mixture modeling using skew-normal independent distributions

In this paper we consider a flexible class of models, with elements that are finite mixtures of multivariate skew-normal independent distributions. A general EM-type algorithm is employed for iteratively computing parameter estimates and this is discussed with emphasis on finite mixtures of skew-normal, skew-t, skew-slash and skew-contaminated normal distributions. Further, a general information-based method for approximating the asymptotic covariance matrix of the estimates is also presented. The accuracy of the associated estimates and the efficiency of some information criteria are evaluated via simulation studies. Results obtained from the analysis of artificial and real data sets are reported illustrating the usefulness of the proposed methodology. The proposed EM-type algorithm and methods are implemented in the R package mixsmsn.

Robust mixture modeling based on scale mixtures of skew-normal distributions

A flexible class of probability distributions, convenient for modeling data with skewness behavior, discrepant observations and population heterogeneity is presented. The elements of this family are convex linear combinations of densities that are scale mixtures of skew-normal distributions. An EM-type algorithm for maximum likelihood estimation is developed and the observed information matrix is obtained. These procedures are discussed with emphasis on finite mixtures of skew-normal, skew-t, skew-slash and skew contaminated normal distributions. In order to examine the performance of the proposed methods, some simulation studies are presented to show the advantage of this flexible class in clustering heterogeneous data and that the maximum likelihood estimates based on the EM-type algorithm do provide good asymptotic properties. A real data set is analyzed, illustrating the usefulness of the proposed methodology.

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.

High-Resolution Anoscopy in the Diagnosis of Anal Cancer Precursor Lesions in Renal Graft Recipients

BackgroundRenal graft recipients are one of the population groups known to be at high risk of developing anal cancer. This study investigated the presence of subclinical anal squamous intraepithelial lesions and the diagnostic ability of high-resolution anoscopy in detecting these lesions in renal graft recipients followed-up in Manaus.MethodsIn a cross-sectional study, 50 renal graft recipients were interviewed and submitted to high-resolution anoscopy with biopsies of acetowhite lesions or of the anal transition zone mucosa when acetowhitening was absent. Considering the histopathological reports of the examined anal specimens as the gold standard, the diagnostic validation and precision measures of high-resolution anoscopy were calculated as well as the prevalence of anal squamous intraepithelial lesions in the studied population.ResultsIn 42 renal graft recipients with satisfactory histopathological readings, prevalence of anal squamous intraepithelial lesions or condyloma acuminatum (ASIL-ACU) was 23.81%. Sensitivity of high-resolution anoscopy was 100%; specificity, 65.63%; positive predictive value, 47.62%; negative predictive value, 100%; and kappa coefficient, 0.48.ConclusionsWith a prevalence of 23.81% of subclinical ASIL-ACU lesions, the studied renal graft recipients had all these lesions detected by high-resolution anoscopy, notwithstanding most anal transition zone acetowhitened biopsied areas did not reveal histopathological aspects of anal cancer precursor lesions or condyloma acuminatum. Therefore, greater experience with the diagnostic tool was felt necessary to enhance its positive predictive value, specificity and diagnostic precision.Renal graft recipients are one of the population groups known to be at high risk of developing anal cancer. This study investigated the presence of subclinical anal squamous intraepithelial lesions and the diagnostic ability of high-resolution anoscopy in detecting these lesions in renal graft recipients followed-up in Manaus. In a cross-sectional study, 50 renal graft recipients were interviewed and submitted to high-resolution anoscopy with biopsies of acetowhite lesions or of the anal transition zone mucosa when acetowhitening was absent. Considering the histopathological reports of the examined anal specimens as the gold standard, the diagnostic validation and precision measures of high-resolution anoscopy were calculated as well as the prevalence of anal squamous intraepithelial lesions in the studied population. In 42 renal graft recipients with satisfactory histopathological readings, prevalence of anal squamous intraepithelial lesions or condyloma acuminatum (ASIL-ACU) was 23.81%. Sensitivity of high-resolution anoscopy was 100%; specificity, 65.63%; positive predictive value, 47.62%; negative predictive value, 100%; and kappa coefficient, 0.48. With a prevalence of 23.81% of subclinical ASIL-ACU lesions, the studied renal graft recipients had all these lesions detected by high-resolution anoscopy, notwithstanding most anal transition zone acetowhitened biopsied areas did not reveal histopathological aspects of anal cancer precursor lesions or condyloma acuminatum. Therefore, greater experience with the diagnostic tool was felt necessary to enhance its positive predictive value, specificity and diagnostic precision.

Influence diagnostics for Student-t censored linear regression models

In this paper, we extend the censored linear regression model with normal errors to Student-t errors. A simple EM-type algorithm for iteratively computing maximum-likelihood estimates of the parameters is presented. To examine the performance of the proposed model, case-deletion and local influence techniques are developed to show its robust aspect against outlying and influential observations. This is done by the analysis of the sensitivity of the EM estimates under some usual perturbation schemes in the model or data and by inspecting some proposed diagnostic graphics. The efficacy of the method is verified through the analysis of simulated data sets and modelling a real data set first analysed under normal errors. The proposed algorithm and methods are implemented in the R package CensRegMod.

Needlescopic versus laparoscopic cholecystectomy: a prospective study of 60 patients

PURPOSE To test the hypothesis that needlescopic cholecystectomies (NC) offer superior outcomes in comparison to common laparoscopic cholecystectomies (LC). METHODS Sixty consecutive patients with gallbladder disease undergoing either LC or NC were evaluated with respect to differences in operative time, frequency of per-operative incidents, post-operative pain, late postoperative symptoms, length of scars and level of postoperative satisfaction. RESULTS Mean operative time was similar in both groups. Most of the patients, irrespective of the technique, informed mild postoperative pain. NC patients had lower levels of pain on the 7th postoperative day (PO7) (p<0.01) and decreased need for additional analgesia. Less frequency of epigastric wound pain was observed in NC patients until PO4 (p<0.01). Aesthetic result was far superior after NC (total length of scars less than half after LC). No differences regarding postoperative satisfaction with the operation were observed between the studied groups. CONCLUSIONS Both techniques were safe and effective, presenting similar operative times and low levels of postoperative pain. Downsizing the ports to 2-3 mm was associated with significantly less frequency of postoperative pain only in the epigastric wound until PO4. Aesthetic outcome of NC was significantly superior to LC, although this advantage did not influence patient level of satisfaction.

Bayesian analysis of censored linear regression models with scale mixtures of normal distributions

As is the case of many studies, the data collected are limited and an exact value is recorded only if it falls within an interval range. Hence, the responses can be either left, interval or right censored. Linear (and nonlinear) regression models are routinely used to analyze these types of data and are based on normality assumptions for the errors terms. However, those analyzes might not provide robust inference when the normality assumptions are questionable. In this article, we develop a Bayesian framework for censored linear regression models by replacing the Gaussian assumptions for the random errors with scale mixtures of normal (SMN) distributions. The SMN is an attractive class of symmetric heavy-tailed densities that includes the normal, Student-t, Pearson type VII, slash and the contaminated normal distributions, as special cases. Using a Bayesian paradigm, an efficient Markov chain Monte Carlo algorithm is introduced to carry out posterior inference. A new hierarchical prior distribution is suggested for the degrees of freedom parameter in the Student-t distribution. The likelihood function is utilized to compute not only some Bayesian model selection measures but also to develop Bayesian case-deletion influence diagnostics based on the q-divergence measure. The proposed Bayesian methods are implemented in the R package BayesCR. The newly developed procedures are illustrated with applications using real and simulated data.

Multivariate measurement error models using finite mixtures of skew-Student t distributions

In regression models, the classical assumption of normal distribution of the random observational errors is often violated, masking some important features of the variability present in the data. Some practical actions to solve the problem, like transformation of variables to achieve normality, are often of doubtful utility. In this work we present a proposal to deal with this issue in the context of the simple linear regression model when both the response and the explanatory variable are observed with error. In such models, the experimenter observes a surrogate variable instead of the covariate of interest. We extend the classical normal model by jointly modeling the unobserved covariate and the random errors by a finite mixture of a skewed version of the Student t distribution. This approach allows us to model data with great flexibility, accommodating skewness, heavy tails and multi-modality. We develop a simple EM-type algorithm to perform maximum likelihood inference of the parameters of the proposed model, and compare the efficiency of our method with some competitors through the analysis of some artificial and real data.

Citologia anal como método de rastreamento para a detecção precoce do câncer anal: esfregaços com algodão hidrófilo são mesmo insatisfatórios?

PURPOSE To test the ability of analpaps performed with cotton swab smears to produce satisfactory cytologic readings as compared to traditional sampling materials. METHODS 318 consecutive patients were examined at the Ambulatório Araújo Lima of Hospital Universitario Getúlio Vargas in the Anal Cancer Prevention Week and were sampled for the performance of analpap. 180 of these patients were randomly sorted to be sampled by either one of the following materials: cytologic brush, dacron swab or cotton swab. The ability of cotton in producing satisfactory anal cytologic readings as compared to dacron and cytologic brush was analised. RESULTS There was no statistical difference among the materials employed in the ability to produce satisfactory citological readings in analpaps. (p > 0.05) CONCLUSION Our results showed that cotton swabs were as efficient as dacron swabs or cytologic brushes in the ability to produce satisfactory analpap readings.

Anal cancer precursor lesions in HIV-positive and HIV-negative patients seen at a tertiary health institution in Brazil

PURPOSE To investigate the prevalence of anal squamous intraepithelial lesions (ASIL) or anal cancer in patients attended at the Tropical Medicine Foundation of Amazonas. METHODS 344 patients consecutively attended at the institution, in 2007/2008, were distributed in the following strata according to presence/abscense of at risk conditions for anal cancer: Group 1 - HIV-positive men-who-have-sex-with-men (101); Group 2 - HIV-positive females (49); Group 3 - patients without any at risk condition for anal cancer (53); Group 4 - HIV-positive heterosexual men (38); Group 5 - HIV-negative patients, without anoreceptive sexual habits, but with other at risk conditions for anal cancer (45); Group 6 - HIV-negative men-who-have-sex-with-men (26); and Group 7 - HIV-negative anoreceptive females (32). The histopathological results of biopsies guided by high-resolution anoscopy were analyzed by frequentist and bayesian statistics in order to calculate the point-prevalence of ASIL/cancer and observe any eventual preponderance of one group over the other. RESULTS The point-prevalence of ASIL for all the patients studied was 93/344 (27%), the difference between HIV-positive and negative patients being statistically significant (38.3% versus 13.5%; p < 0.0001). The prevalence of ASIL for each one of the groups studied was: Group 1 = 49.5%, Group 2 = 28.6%, Group 3 = 3.8%, Group 4 = 21.1%, Group 5 = 11.1%, Group 6 = 30.8% and Group 7 = 18.8%. Standard residual analysis demonstrated that ASIL was significantly prevalent in patients of Group 1 and high-grade ASIL in patients of Group 2. The odds for ASIL of Group 1 was significantly higher in comparison to Groups 2, 3, 4, 5 and 7 (p < 0.03). The odds for ASIL of Groups 2, 4 and 6 were significantly higher in comparison to Group 3 (p < 0.03). CONCLUSIONS In the patients studied, ASIL (low and/or high-grade) tended to be significantly more prevalent in HIV-positive patients. Nonetheless, HIV-negative anoreceptive patients also presented great probability to have anal cancer precursor lesions, mainly those of the male gender.