Individual prediction of automobile bodily injury claims liabilities

[spa] La mayoría de siniestros con daños corporales se liquidan mediante negociación, llegando a juicio menos del 5% de los casos. Una estrategia de negociación bien definida es, por tanto, fundamental para las compañías aseguradoras. En este artículo asumimos que la compensación monetaria concedida en juicio es la máxima cuantía que debería ser ofrecida por el asegurador en el proceso de negociación. Usando una base de datos real, implementamos un modelo log-lineal para estimar la máxima oferta de negociación. Perturbaciones no-esféricas son detectadas. Correlación ocurre cuando más de una siniestro se liquida en la misma sentencia judicial. Heterocedasticidad por grupos se debe a la influencia de la valoración del forense en la indemnización final.

Ajustes de funções de distribuição de probabilidade à radiação solar global no Estado do Rio Grande do Sul

O objetivo deste trabalho foi verificar o ajuste das séries de dados de radiação solar global média decendial, de 22 municípios do Estado do Rio Grande do Sul, às funções de distribuições de probabilidade normal, log-normal, gama, gumbel e weibull. Aplicou-se o teste de aderência de Kolmogorov-Smirnov, nas 792 séries de dados (22 municípios x 36 decêndios) de radiação solar global média decendial, para verificar o ajuste dos dados às distribuições normal, log-normal, gama, gumbel e weibull, totalizando 3.960 testes. Os dados decendiais de radiação solar global média se ajustam às funções de distribuições de probabilidade normal, log-normal, gama, gumbel e weibull, e apresentam melhor ajuste à função de distribuição de probabilidade normal.

Regiões homogêneas e funções de distribuição de probabilidade da precipitação pluvial no Estado de Táchira, Venezuela

O objetivo deste trabalho foi determinar regiões homogêneas baseadas na sazonalidade da precipitação pluvial mensal e a distribuição de probabilidade que melhor se ajusta à precipitação dessas regiões no Estado de Táchira, Venezuela. Utilizaram-se valores da precipitação mensal de 25 estações climatológicas, que apresentam séries entre 24 e 62 anos. Aplicou-se o método de Ward no agrupamento dos meses com precipitação pluvial mensal similar e também no das localidades com precipitação similar (regiões homogêneas). Avaliaram-se os ajustes das funções de densidade exponencial, gama, Gumbel, normal, log-normal a três parâmetros, e Weibull aos dados observados de precipitação mensal. A variação sazonal da precipitação no Estado de Táchira apresenta três períodos estatisticamente definidos como: seco, transição e úmido. Os períodos seco e úmido apresentam quatro regiões homogêneas de precipitação mensal similar e o de transição três. No período seco, a distribuição de probabilidade recomendada para as estimativas mensais é a exponencial, com exceção da região homogênea com os maiores valores de precipitação pluvial do período, onde a gama se sobressai. No período chuvoso, em todas as regiões homogêneas, a distribuição normal predomina, com exceção de agosto, em que a gama prevalece. Já nos meses de transição, destacam-se as distribuições gama, em abril, e normal, em novembro.

Comparação de modelos matemáticos não-lineares empregados na análise de desempenho de sistemas de irrigação

Modelos matemáticos não-lineares utilizados na análise de desempenho de sistemas de irrigação foram comparados visando a indicar o que se ajusta melhor aos dados observados em perfis de distribuição da água aplicada na irrigação. Foram considerados quatro modelos de probabilidade (Normal, Log-normal, Gama e Beta) e dois modelos potenciais (modelos Silva e Karmeli), aplicados a 91 casos de avaliação de desempenho da irrigação. A comparação entre as curvas de freqüência acumulada da soma de quadrados dos erros, obtida do ajuste de cada modelo aos dados, revelou que o modelo Silva é estatisticamente o melhor entre os modelos testados.

Análise bayesiana univariada e bivariada para a conversão alimentar de suínos da raça Piau

O objetivo deste trabalho foi apresentar modelagens alternativas, uni e bivariadas, para avaliação da conversão alimentar (CA) de suínos da raça Piau, com uso de inferência bayesiana. Os efeitos de sexo e genótipo sobre a CA dos animais foram avaliados por meio de procedimentos de simulação de Monte Carlo via cadeias de Markov (MCMC) e de integração aproximada aninhada de Laplace (INLA). O modelo univariado foi avaliado com diferentes distribuições para o erro - normal (gaussiana), t de Student, gama, log-normal e skew-normal -, enquanto, para o modelo bivariado, considerou-se o erro normal. A distribuição skew-normal foi o modelo mais parcimonioso para inferir sobre a resposta direta (univariada) da CA aos efeitos de sexo e genótipo, os quais não foram significativos. O modelo bivariado foi capaz de identificar diferenças significativas no ganho de peso e no consumo de ração em níveis de significância não detectados pelo modelo univariado. Além disso, ele também foi capaz de detectar diferenças entre sexos, quando agrupados por genótipos NN (machos, 2,73±0,04; fêmeas, 2,68±0,04) e Nn (machos, 2,70±0,07; fêmeas, 2,64±0,07), e revelou maior acurácia e precisão nas inferências nutricionais. Em ambas as abordagens, o método bayesiano mostra-se flexível e eficiente para a avaliação do desempenho nutricional dos animais.

Problematic Internet use is associated with substance use in young adolescents.

AIM: This study examined whether problematic Internet use was associated with substance use among young adolescents and assessed whether this association accounted for the use of tobacco, alcohol, cannabis and other drugs. METHODS: Using the Internet Addiction Test, we divided a representative sample of 3067 adolescents in Switzerland (mean age 14 years) into regular and problematic Internet users. We performed a bivariate analysis and two logistic regression models, to analyse substances separately and simultaneously, and developed a log-linear model to define the associations between significant variables. RESULTS: Problematic Internet users were more likely to be female, to use substances, to come from nonintact families, to report poor emotional well-being and to be below average students. The first model showed significant associations between problematic users and each substance, with adjusted odds ratios of 2.05 for tobacco, 1.72 for alcohol, 1.94 for cannabis and 2.73 for other drugs. Only smoking remained significant in the second model, with an adjusted odds ratio of 1.71. CONCLUSION: Problematic Internet use is associated with other risky behaviours and may be an important early predictor of adolescent substance use. Therefore, it should be included in the psychosocial screening of adolescents.

Parent-adolescent relationship in youths with a chronic condition.

BACKGROUND: Suffering from a chronic disease or disability (CDD) during adolescence can be a burden for both the adolescents and their parents. The aim of the present study is to assess how living with a CDD during adolescence, the quality of parent-adolescent relationship (PAR) and the adolescent's psychosocial development interact with each other. METHODS: Using the Swiss Multicenter Adolescent Survey on Health 2002 (SMASH02) database, we compared adolescents aged 16-20 years with a CDD (n = 760) with their healthy peers (n = 6493) on sociodemographics, adolescents' general and psychosocial health, interparental relationship and PAR. RESULTS: Bivariate analyses showed that adolescents with a CDD had a poorer psychosocial health and a more difficult relationship with their parents. The log-linear model indirectly linked CDD and poor PAR through four variables: two of the adolescents' psychosocial health variables (suicide attempt and sensation seeking), the need for help regarding difficulties with parents and a highly educated mother that acted as a protective factor, allowing for a better parent-adolescent with a CDD relationship. CONCLUSION: It is essential for health professionals taking care of adolescents with a CDD to distinguish between issues in relation with the CDD from other psychosocial difficulties, in order to help these adolescents and their parents deal with them appropriately and thus maintain a healthy PAR.

A nonparametric method for the measurement of size diversity with emphasis on data standardization

The most suitable method for estimation of size diversity is investigated. Size diversity is computed on the basis of the Shannon diversity expression adapted for continuous variables, such as size. It takes the form of an integral involving the probability density function (pdf) of the size of the individuals. Different approaches for the estimation of pdf are compared: parametric methods, assuming that data come from a determinate family of pdfs, and nonparametric methods, where pdf is estimated using some kind of local evaluation. Exponential, generalized Pareto, normal, and log-normal distributions have been used to generate simulated samples using estimated parameters from real samples. Nonparametric methods include discrete computation of data histograms based on size intervals and continuous kernel estimation of pdf. Kernel approach gives accurate estimation of size diversity, whilst parametric methods are only useful when the reference distribution have similar shape to the real one. Special attention is given for data standardization. The division of data by the sample geometric mean is proposedas the most suitable standardization method, which shows additional advantages: the same size diversity value is obtained when using original size or log-transformed data, and size measurements with different dimensionality (longitudes, areas, volumes or biomasses) may be immediately compared with the simple addition of ln k where kis the dimensionality (1, 2, or 3, respectively). Thus, the kernel estimation, after data standardization by division of sample geometric mean, arises as the most reliable and generalizable method of size diversity evaluation

Forecasting the maximum compensation offer in the automobile BI claims negotiation process

Most motor bodily injury (BI) claims are settled by negotiation, with fewer than 5% of cases going to court. A well-defined negotiation strategy is thus very useful for insurance companies. In this paper we assume that the monetary compensation awarded in court is the upper amount to be offered by the insurer in the negotiation process. Using a real database, a log-linear model is implemented to estimate the maximal offer. Non-spherical disturbances are detected. Correlation occurs when various claims are settled in the same judicial verdict. Group wise heteroscedasticity is due to the influence of the forensic valuation on the final compensation amount. An alternative approximation based on generalized inference theory is applied to estimate confidence intervals on variance components, since classical interval estimates may be unreliable for datasets with unbalanced structures.

Isotype distribution of anticardiolipin antibodies in systemic lupus erythematosus prospective analysis of a series of 100 patients

A prospective study of IgG and IgM isotypes of anticardiolipin antibodies (aCL) in a series of 100 patients with systemic lupus erythematosus was carried out. To determine the normal range of both isotype titres a group of 100 normal control serum samples was studied and a log-normal distribution of IgG and IgM isotypes was found. The IgG anticardiolipin antibody serum was regarded as positive if a binding index greater than 2.85 (SD 3.77) was detected and a binding index greater than 4.07 (3.90) was defined as positive for IgM anticardiolipin antibody. Twenty four patients were positive for IgG aCL, 20 for IgM aCL, and 36 for IgG or IgM aCL, or both. IgG aCL were found to have a significant association with thrombosis and thrombocytopenia, and IgM aCL with haemolytic anaemia and neutropenia. Specificity and predictive value for these clinical manifestations increased at moderate and high anticardiolipin antibody titres. In addition, a significant association was found between aCL and the presence of lupus anticoagulant. Identification of these differences in the anticardiolipin antibody isotype associations may improve the clinical usefulness of these tests, and this study confirms the good specificity and predictive value of the anticardiolipin antibody titre for these clinical manifestations.

Diversidade e índice sucessional de uma vegetação de cerrado sensu stricto na Universidade Estadual de Goiás-UEG, campus de Anápolis

A composição vegetal, estrutura, diversidade, estádio sucessional e distribuição de espécies do cerrado do campus da UEG com 6 ha, foram inventariados usando 30 parcelas com 100 m² cada. A partir de dbs superior ou igual a 5 cm foram amostrados 515 indivíduos, representados por 20 famílias, 28 gêneros e 46 espécies. As famílias de maior riqueza foram Leguminosae, Vochysiaceae e Malpighiaceae. As espécies Qualea grandiflora, Byrsonima crassa, Erytroxylum tortuosum, Qualea parviflora e Miconia ferruginata apresentaram os maiores VIs. A diversidade da área (H¢ = 1,353) é menor que valores descritos para Cerrado, o que pode ser conseqüência tanto da abundância de espécies como Q. grandiflora e B. crasssa quanto de interferências antrópicas no local, incluindo queimadas. O valor do índice sucessional (IS = 2,3) indica uma comunidade em estágio intermediário de sucessão, já que seu valor oscila de 1 a 3 . A comunidade ajustou-se apenas ao modelo log-normal, o que, de acordo com a literatura, pode ser influência da proporção da abundância de espécies dominantes, intermediárias e raras.

Sorption of fomesafen in Brazilian soils

The study of the dynamics of a herbicide in the soil focus on the interactions with environmental components to obtain agronomic efficiency, ensuring selectivity to the culture and risk reduction of environmental impact. This study evaluated the sorption process of fomesafen in the Brazilian soils Ultisol, Cambisol, and Organosol. Besides soil, washed sand was used as an inert material for determination of the sorption ratio of fomesafen in the soil. The bioassay method was applied, using Sorghum vulgare plants as bio-indicator of herbicide presence. Plant poisoning evaluation and harvest for dry matter determination were carried out 21 days after sorghum sowing. To calculate C50, the nonlinear log-logistic model was applied and sorption ratios of the herbicide were obtained in different soils. The decreasing sorption ratio of formesafen in the soils was: Organosol > Ultisol > Cambisol. It was concluded that the contents of organic matter and clay in the soils were the attributes that most influenced fomesafen sorption.

Construction of 2D transparent micromodels in polyester resin with porosity similar to carrots

Microscopic visualization, especially in transparent micromodels, can provide valuable information to understand the transport phenomena at pore scale in different process occurring in porous materials (food, timber, soils, etc.). Micromodels studies focus mainly on the observation of multi-phase flow, which presents a greater proximity to reality. The aim of this study was to study the process of flexography and its application in the manufacture of polyester resin transparent micromodels and its application to carrots. Materials used to implement a flexo station for micromodels construction were thermoregulated water bath, exposure chamber to UV light, photosensitive substance (photopolymer), RTV silicone polyester resin, and glass plates. In this paper, data on size distribution of a particular kind of carrot we used, and a transparent micromodel with square cross-section as well as a Log-normal pore size distribution with pore radii ranging from 10 to 110 µm (average of 22 µm and micromodel size of 10 × 10 cm) were built. Finally, it stresses that it has successfully implemented the protocol processing 2D polyester resin transparent micromodels.

Possible solution of some essential zero problems in compositional data analysis

One of the tantalising remaining problems in compositional data analysis lies in how to deal with data sets in which there are components which are essential zeros. By an essential zero we mean a component which is truly zero, not something recorded as zero simply because the experimental design or the measuring instrument has not been sufficiently sensitive to detect a trace of the part. Such essential zeros occur in many compositional situations, such as household budget patterns, time budgets, palaeontological zonation studies, ecological abundance studies. Devices such as nonzero replacement and amalgamation are almost invariably ad hoc and unsuccessful in such situations. From consideration of such examples it seems sensible to build up a model in two stages, the first determining where the zeros will occur and the second how the unit available is distributed among the non-zero parts. In this paper we suggest two such models, an independent binomial conditional logistic normal model and a hierarchical dependent binomial conditional logistic normal model. The compositional data in such modelling consist of an incidence matrix and a conditional compositional matrix. Interesting statistical problems arise, such as the question of estimability of parameters, the nature of the computational process for the estimation of both the incidence and compositional parameters caused by the complexity of the subcompositional structure, the formation of meaningful hypotheses, and the devising of suitable testing methodology within a lattice of such essential zero-compositional hypotheses. The methodology is illustrated by application to both simulated and real compositional data