Dealing with separation or near-to-separation in the model for multinomial response with application to childhood health seeking behavior data from a complex survey.

Separation or monotone-likelihood can be observed in fitting process of a multinomial logistic model using maximum likelihood estimation (MLE) when sample size is small and/or one of the outcome categories is rare and/or there is one or more influential covariates, resulting in infinite or biased estimate of at least one regression coefficient of the model. This study investigated empirically to identify the optimal data condition to define both 'separation' and 'near-to-separation' (partial separation) and explored their consequences in MLE and provided a solution by applying a penalized likelihood approach, which has been proposed in the literature, by adding a Jeffreys prior-based penalty term to the original likelihood function to remove the first-order bias in the MLEs of the multinomial logit model via equivalent Poisson regression. Furthermore, the penalized estimating equation (PMLE) is extended to a weighted estimating equation allowing for survey-weight for analyzing data from a complex survey. The simulation study suggests that the PMLE outperforms the MLE by providing smaller amount of bias and mean squared of error and better coverage. The methods are applied to analyze data on choice of health facility for treatment of childhood diseases.

A multivariate Poisson regression model for count data.

We propose a new technique for the study of multivariate count data. The proposed model is applied to the study of the number of individuals several fossil species found in a set of geographical observation points. First, we are proposing a multivariate model based on the Poisson distributions, which allows positive and negative correlations between the components. We are extending the log-linear Poisson model in the multivariate case through the conditional distributions. For this model, we obtain the maximum likelihood estimates and compute several goodness of fit statistics. Finally we illustrate the application of the proposed method over data sets: various simulated data sets and a count data set of various fossil species.

Evaluation of the micropropagation potential of curauá pineapple hybrids for fiber production / Avaliação do potencial de micropropagação de híbridos do abacaxi curauá para a produção de fibras

Plant fiber is a renewable and biodegradable material that can be used effectively to reinforce various composites. Pineapple hybrids selected for their fiber quality are in the phase of agronomic validation in Brazil by the Embrapa Cassava and Fruits research unit. The selection of a hybrid for large-scale fiber production depends on obtaining a large number of seedlings. This study evaluated the morphogenetic response and propagation potential of eight hybrids of Ananas comosus var. erectifolius, for the purpose of producing high-quality seedlings on a large scale. Stem and crown buds were reduced and placed in MS nutritive medium supplemented with BAP at 0.5 mg L-1, NAA at 0.01 mg L-1 and Phytagel® at 2.5 g L-1. After 45 days, the number of oxidized, contaminated and surviving buds was determined. Swollen buds and plantlets were transferred to a multiplication medium containing MS sucrose, salts and vitamins. The propagation potential was evaluated based on the geometric growth rate among sub-cultures. The FIB-NEG hybrid presented the best results for the establishment phase (40.28%). The best propagative potential was obtained from crown buds with the highest values for FIB-EST (3.93), FIB-MIN (3.91) and FIB-BOY (3.91) hybrids.

A fibra vegetal é uma fonte renovável, biodegradável e de excelente desempenho como reforço em compósitos variados. Híbridos selecionados pela qualidade de suas fibras estão em fase de validação agronômica na Embrapa Mandioca e Fruticultura e sua adoção para produção de fibra em larga escala depende de um elevado número de mudas. Este trabalho teve como objetivo avaliar a resposta morfogenética e o potencial propagativo de oito híbridos de Ananas comosus var. erectifolius, com a finalidade de produzir mudas de qualidade em larga escala. Gemas do caule e coroa foram reduzidas, introduzidas em meio nutritivo MS suplementado com BAP a 0,5 mg L-1, ANA a 0,01 mg L-1 e Phytagel® a 2,5 g L-1. Aos 45 dias foram avaliados o número de gemas oxidadas, contaminadas e sobreviventes. Gemas intumescidas e plantas formadas foram transferidas para o meio de multiplicação contendo sacarose, sais e vitaminas MS. Avaliou-se o potencial propagativo a partir de uma taxa de crescimento geométrico entre subcultivos. O híbrido FIB-NEG (40.28%) apresentou os melhores resultados em porcentagem para a fase de estabelecimento. O melhor potencial propagativo foi obtido a partir de gemas de coroa, com os valores mais elevados registrados para os híbridos FIB-EST (3.93), FIB-MIN (3.91) e FIB-BOY (3.91).