Improved score tests in symmetric linear regression models

The class of symmetric linear regression models has the normal linear regression model as a special case and includes several models that assume that the errors follow a symmetric distribution with longer-than-normal tails. An important member of this class is the t linear regression model, which is commonly used as an alternative to the usual normal regression model when the data contain extreme or outlying observations. In this article, we develop second-order asymptotic theory for score tests in this class of models. We obtain Bartlett-corrected score statistics for testing hypotheses on the regression and the dispersion parameters. The corrected statistics have chi-squared distributions with errors of order O(n(-3/2)), n being the sample size. The corrections represent an improvement over the corresponding original Rao`s score statistics, which are chi-squared distributed up to errors of order O(n(-1)). Simulation results show that the corrected score tests perform much better than their uncorrected counterparts in samples of small or moderate size.

Small-Sample Corrections for Score Tests in Birnbaum-Saunders Regressions

In this article, we deal with the issue of performing accurate small-sample inference in the Birnbaum-Saunders regression model, which can be useful for modeling lifetime or reliability data. We derive a Bartlett-type correction for the score test and numerically compare the corrected test with the usual score test and some other competitors.

Three Bartlett-type corrections for score statistics in symmetric nonlinear regression models

We present simple matrix formulae for corrected score statistics in symmetric nonlinear regression models. The corrected score statistics follow more closely a chi (2) distribution than the classical score statistic. Our simulation results indicate that the corrected score tests display smaller size distortions than the original score test. We also compare the sizes and the powers of the corrected score tests with bootstrap-based score tests.

Domestic use of a disclosing solution for denture hygiene: a randomised trial

Objectives: The purpose of this study was to investigate the effect of the domestic use of a disclosing agent for denture hygiene. Materials and methods: Completely edentulous participants wearing maxillary dentures were randomly assigned to one of the three intervention groups: (1) Follow-up only (control; n = 12); (2) Oral and denture hygiene instructions (n = 10); (3) Instructions associated with the home use of a disclosing agent (1% neutral red; n = 10). Biofilm coverage area (%) over internal and external surfaces of the maxillary denture was assessed at baseline and after 14 and 90 days. Data were evaluated by generalised estimating equations based on score tests (alpha = 0.05). Results: The participants presented low changes for areas of biofilm coverage (14 days (%): internal: GI = 1.4 +/- 0.9; GII = 1.5 +/- 1.3; GIII = -0.4 +/- 0.9; external: GI = 1.4 +/- 1.5; GII = 1.5 +/- 1.4; GIII = -0.4 +/- 0.9; 90 days (%): internal: GI = 2.0 +/- 0.9; GII = 2.2 +/- 1.4; GIII = 0.3 +/- 1.0; external: GI = 2.1 +/- 1.4; GII = 2.2 +/- 1.5; GIII = 0.3 +/- 0.9). Changes were similar for the three groups (p = 0.293) and were not influenced by the test time (p = 0.218). Conclusion: It can be concluded that the home use of a disclosing agent for denture hygiene does not improve the removal of the biofilm, particularly for patients with adequate oral hygiene habits.

The Use of Smell Identification Tests in the Diagnosis of Parkinson`s Disease in Brazil

Smell identification tests may be of routine clinical value in the differential diagnosis of PD but are subject to cultural variation and have not been systematically evaluated in the Brazilian population. We have applied culturally adapted translations of the University of Pennsylvania 40-item smell identification test (UPSIT-40) and the 16-item identification test from Sniffin` Sticks (SS-16) to nondemented Brazilian PD patients and controls. Pearson`s correlation coefficient between the test scores was 0.76 (95% CI 0.70-0.81, n = 204, P < 0.001). To calculate reliability measures for each test we used the diagnosis (either PD or control) as outcome variable for separate logistic regression analyses using the score in the UPSIT-40 or the SS-16 as a covariate. The SS-16 specificity was 89.0% with a sensitivity of 81.1% (106 PD and 118 controls). The UPSIT-40 specificity was 83.5% and its sensitivity 82.1% (95 PD and 109 controls). Regression curves were used to associate an individual`s smell test score with the probability of belonging to the PD, as opposed to the control group. Our data provide support for the use of the UPSIT-40 and SS-16 to help distinguish early PD from controls. (c) 2008 Movement Disorder Society

Size and power properties of some tests in the Birnbaum-Saunders regression model

The Birnbaum-Saunders distribution has been used quite effectively to model times to failure for materials subject to fatigue and for modeling lifetime data. In this paper we obtain asymptotic expansions, up to order n(-1/2) and under a sequence of Pitman alternatives, for the non-null distribution functions of the likelihood ratio, Wald, score and gradient test statistics in the Birnbaum-Saunders regression model. The asymptotic distributions of all four statistics are obtained for testing a subset of regression parameters and for testing the shape parameter. Monte Carlo simulation is presented in order to compare the finite-sample performance of these tests. We also present two empirical applications. (C) 2010 Elsevier B.V. All rights reserved.

Local power of some tests in exponential family nonlinear models

In this paper we obtain asymptotic expansions up to order n(-1/2) for the nonnull distribution functions of the likelihood ratio, Wald, score and gradient test statistics in exponential family nonlinear models (Cordeiro and Paula, 1989), under a sequence of Pitman alternatives. The asymptotic distributions of all four statistics are obtained for testing a subset of regression parameters and for testing the dispersion parameter, thus generalising the results given in Cordeiro et al. (1994) and Ferrari et al. (1997). We also present Monte Carlo simulations in order to compare the finite-sample performance of these tests. (C) 2010 Elsevier B.V. All rights reserved.

Validation of an experimental polyurethane model for biomechanical studies on implant supported prosthesis - tension tests

OBJECTIVES: The complexity and heterogeneity of human bone, as well as ethical issues, frequently hinder the development of clinical trials. The purpose of this in vitro study was to determine the modulus of elasticity of a polyurethane isotropic experimental model via tension tests, comparing the results to those reported in the literature for mandibular bone, in order to validate the use of such a model in lieu of mandibular bone in biomechanical studies. MATERIAL AND METHODS: Forty-five polyurethane test specimens were divided into 3 groups of 15 specimens each, according to the ratio (A/B) of polyurethane reagents (PU-1: 1/0.5, PU-2: 1/1, PU-3: 1/1.5). RESULTS: Tension tests were performed in each experimental group and the modulus of elasticity values found were 192.98 MPa (SD=57.20) for PU-1, 347.90 MPa (SD=109.54) for PU-2 and 304.64 MPa (SD=25.48) for PU-3. CONCLUSION: The concentration of choice for building the experimental model was 1/1.

Validation of an experimental polyurethane model for biomechanical studies on implant-supported prosthesis: compression tests

OBJECTIVES: The complexity and heterogeneity of human bone, as well as ethical issues, most always hinder the performance of clinical trials. Thus, in vitro studies become an important source of information for the understanding of biomechanical events on implant-supported prostheses, although study results cannot be considered reliable unless validation studies are conducted. The purpose of this work was to validate an artificial experimental model based on its modulus of elasticity, to simulate the performance of human bone in vivo in biomechanical studies of implant-supported prostheses. MATERIAL AND METHODS: In this study, fast-curing polyurethane (F16 polyurethane, Axson) was used to build 40 specimens that were divided into five groups. The following reagent ratios (part A/part B) were used: Group A (0.5/1.0), Group B (0.8/1.0), Group C (1.0/1.0), Group D (1.2/1.0), and Group E (1.5/1.0). A universal testing machine (Kratos model K - 2000 MP) was used to measure modulus of elasticity values by compression. RESULTS: Mean modulus of elasticity values were: Group A - 389.72 MPa, Group B - 529.19 MPa, Group C - 571.11 MPa, Group D - 470.35 MPa, Group E - 437.36 MPa. CONCLUSION: The best mechanical characteristics and modulus of elasticity value comparable to that of human trabecular bone were obtained when A/B ratio was 1:1.

Evaluating resin-enamel bonds by microshear and microtensile bond strength tests: effects of composite resin

OBJECTIVES: The aims of this study were to evaluate the effect of resin composite (Filtek Z250 and Filtek Flow Z350) and adhesive system [(Solobond Plus, Futurabond NR (VOCO) and Adper Single Bond (3M ESPE)] on the microtensile (μTBS) and microshear bond strength (μSBS) tests on enamel, and to correlate the bond strength means between them. MATERIAL AND METHODS: Thirty-six extracted human molars were sectioned to obtain two tooth halves: one for μTBS and the other one for μSBS. Adhesive systems and resin composites were applied to the enamel ground surfaces and light-cured. After storage (37(0)C/24 h) specimens were stressed (0.5 mm/min). Fracture modes were analyzed under scanning electron microscopy. The data were analyzed using two-way ANOVA and Tukey's test (α=0.05). RESULTS: The correlation between tests was estimated with Pearson's product-moment correlation statistics (α =0.05). For both tests only the main factor resin composite was statistically significant (p<0.05). The correlation test detected a positive (r=0.91) and significant (p=0.01) correlation between the tests. CONCLUSIONS: The results were more influenced by the resin type than by the adhesives. Both microbond tests seem to be positive and linearly correlated and can therefore lead to similar conclusions.

Relationship between oral health and its impact on quality of life among adolescents

The aim of this study was to assess oral health status and its relationship with quality of life. A household population, cross-sectional study was carried out; participants were between 15 and 17 years of age (n = 247) and were examined by two calibrated dentists. Socio-economic status was classified according to ANEP-ABIPEME criteria. Clinical examinations to observe DMFT, CPI and Dean indices were performed as per WHO criteria. The Significant Caries Index (SiC) was used to evaluate polarization of the occurrence of caries among participants of the tercile with higher DMF-T. The OHIP instrument was used to measure quality of life. The Spearman and Mann-Whitney tests were used for assessing correlations (5% significance level). Examinations were carried out in 117 (47.37%) females and in 130 (52.63%) males. Of the examined participants, 45.75% were classified as belonging to socio-economic class C. Caries occurrence was observed in 218 subjects (88.26%); the mean DMFT was 5.40. The SiC index was 9.97. Almost half (47.77%) of the participants examined did not present sextants affected by periodontal disease. Of the participants examined, 80.16% presented absence of fluorosis. The mean OHIP was 3.95. The following correlations were observed: a positive and statistically significant correlation between the highest score in the OHIP and decayed teeth; a positive correlation with threshold significance between OHIP and DMFT; an inverse correlation between intact teeth and OHIP; and a positive and non statistically significant correlation between SiC and OHIP (correlation coefficient = 0.13, p = 0.245). Association between the mean OHIP and the terciles was not significant (p = 0.146); there were also no associations between periodontal condition and OHIP nor were there associations between the presence of fluorosis and mean OHIP.

Estressores em Unidade de Terapia Intensiva: versão brasileira do The Environmental Stressor Questionnaire

Este estudo teve como objetivo realizar a adaptação cultural do The Environmental Stressor Questionnaire - (ESQ) para a língua portuguesa do Brasil e verificar sua confiabilidade e validade. Foram empregadas as etapas metodológicas recomendadas pela literatura para adaptação cultural. A versão brasileira do ESQ foi aplicada a 106 pacientes de Unidade de Terapia Intensiva (UTI) de dois hospitais, público e privado, do interior do Estado de São Paulo. A confiabilidade foi avaliada quanto à consistência interna e estabilidade (teste e reteste); a validade convergente foi verificada por meio da correlação entre o ESQ e questão genérica sobre estresse em UTI. A confiabilidade foi satisfatória com Alfa de Crombach=0,94 e Coeficiente de Correlação Intraclasse=0,861 (IC95% 0,723; 0,933). Constatou-se correlação entre o escore total do ESQ e a questão genérica sobre estresse (r=0,70), confirmando a validade convergente. A versão brasileira do ESQ mostrou-se uma ferramenta confiável e válida para avaliação de estressores em UTI.

Characterization of aqueous silver nitrate solutions for leakage tests

OBJECTIVE: To determine the pH over a period of 168 h and the ionic silver content in various concentrations and post-preparation times of aqueous silver nitrate solutions. Also, the possible effects of these factors on microleakage test in adhesive/resin restorations in primary and permanent teeth were evaluated. MATERIAL AND METHODS: A digital pHmeter was used for measuring the pH of the solutions prepared with three types of water (purified, deionized or distilled) and three brands of silver nitrate salt (Merck, Synth or Cennabras) at 0, 1, 2, 24, 48, 72, 96 and 168 h after preparation, and storage in transparent or dark bottles. Ionic silver was assayed according to the post-preparation times (2, 24, 48, 72, 96, 168 h) and concentrations (1, 5, 25, 50%) of solutions by atomic emission spectrometry. For each sample of each condition, three readings were obtained for calculating the mean value. Class V cavities were prepared with enamel margins on primary and permanent teeth and restored with the adhesive systems OptiBond FL or OptiBond SOLO Plus SE and the composite resin Filtek Z-250. After nail polish coverage, the permanent teeth were immersed in 25% or 50% AgNO3 solution and the primary teeth in 5% or 50% AgNO3 solutions for microleakage evaluation. ANOVA and the Tukey's test were used for data analyses (α=5%). RESULTS: The mean pH of the solutions ranged from neutral to alkaline (7.9±2.2 to 11.8±0.9). Mean ionic silver content differed depending on the concentration of the solution (4.75±0.5 to 293±15.3 ppm). In the microleakage test, significant difference was only observed for the adhesive system factor (p=0.000). CONCLUSIONS: Under the tested experimental conditions and based on the obtained results, it may be concluded that the aqueous AgNO3 solutions: have neutral/alkaline pH and service life of up to 168 h; the level of ionic silver is proportional to the concentration of the solution; even at 5% concentration, the solutions were capable of indicating loss of marginal seal in the composite restorations; the 3-step conventional adhesive system had better performance regarding microleakage in enamel on primary and permanent teeth.

Validade e confiabilidade da versão brasileira do Índice de Capacidade para o Trabalho

OBJETIVO: Avaliar a validade e a confiabilidade da versão brasileira de índice de capacidade para o trabalho. MÉTODOS:Estudo transversal com amostra de 475 trabalhadores de empresa do setor elétrico no estado de São Paulo (dez municípios em Campinas e região), realizado em 2005. Foram avaliados os seguintes aspectos da versão brasileira do Índice de Capacidade para o Trabalho: validade de construto, por meio de análise fatorial confirmatória e da capacidade discriminante; validade de critério, correlacionado o escore do índice com medidas de saúde auto-referidas; e confiabilidade, por meio da análise da consistência interna utilizando o coeficiente alfa de Cronbach. RESULTADOS: A análise fatorial indicou três fatores do construto capacidade para o trabalho: questões relativas aos "recursos mentais" (20,6% da variância), à autopercepção da capacidade para o trabalho (18,9% da variância) e à presença de doenças e limitações decorrentes do estado de saúde (18,4% da variância). O índice discriminou os trabalhadores segundo nível de absenteísmo, identificando média estatisticamente significativa (p<0,001) entre aqueles com absenteísmo elevado (37,2 pontos) e baixo (42,3 pontos). A análise de critério mostrou correlação do índice com todas as dimensões do estado de saúde analisadas (p<0,0001). O índice apresentou boa confiabilidade com coeficiente alfa de Cronbach (0,72). CONCLUSÕES: A versão brasileira do Índice de Capacidade para o Trabalho mostrou propriedades psicométricas satisfatórias quanto à validade de construto, de critério e de confiabilidade, representando uma opção adequada para avaliação da capacidade para o trabalho em abordagens individuais e inquéritos populacionais.

Association between osteoporosis and rheumatoid arthritis in women: a cross-sectional study

CONTEXT AND OBJECTIVES: Osteoporosis has frequently been observed in patients with rheumatoid arthritis. The present study was undertaken in order to evaluate factors associated with osteoporosis among women with rheumatoid arthritis. DESIGN AND SETTING: Cross-sectional study, carried out in a public hospital in São Paulo. METHODS: The participants were 83 women with rheumatoid arthritis (53.7 ± 10.0 years old). Bone mineral density (BMD) and body composition were measured by dual energy X-ray absorptiometry. The patients were divided into three groups according to BMD: group 1, normal BMD (n = 24); group 2, osteopenia (n = 38); and group 3, osteoporosis (n = 21). Tests were performed to compare differences in means and correlations, with adjustments for age, duration of disease and cumulative corticosteroid. The relationships between clinical factors, physical activity score, dietary intake, body composition and biochemical parameters were analyzed using linear regression models. RESULTS: Mean calcium, vitamin D and omega-6 intakes were lower than the recommendations. Associations were found between BMD and age, disease duration, parathyroid hormone concentration and fat intake. The linear regression model showed that being older, with more years of disease and lower weight were negatively correlated with BMD [Total femur = 0.552 + 0.06 (weight) + 0.019 (total physical activity) - 0.05 (age) - 0.003 (disease duration); R² = 48.1; P < 0.001]. CONCLUSION: The present study indicates that nutritional factors and body composition are associated with bone mass in women with rheumatoid arthritis.