Prediction in Multilevel Logistic Regression

The purpose of this article is to present a new method to predict the response variable of an observation in a new cluster for a multilevel logistic regression. The central idea is based on the empirical best estimator for the random effect. Two estimation methods for multilevel model are compared: penalized quasi-likelihood and Gauss-Hermite quadrature. The performance measures for the prediction of the probability for a new cluster observation of the multilevel logistic model in comparison with the usual logistic model are examined through simulations and an application.

A new class of survival regression models with heavy-tailed errors: robustness and diagnostics

Birnbaum-Saunders models have largely been applied in material fatigue studies and reliability analyses to relate the total time until failure with some type of cumulative damage. In many problems related to the medical field, such as chronic cardiac diseases and different types of cancer, a cumulative damage caused by several risk factors might cause some degradation that leads to a fatigue process. In these cases, BS models can be suitable for describing the propagation lifetime. However, since the cumulative damage is assumed to be normally distributed in the BS distribution, the parameter estimates from this model can be sensitive to outlying observations. In order to attenuate this influence, we present in this paper BS models, in which a Student-t distribution is assumed to explain the cumulative damage. In particular, we show that the maximum likelihood estimates of the Student-t log-BS models attribute smaller weights to outlying observations, which produce robust parameter estimates. Also, some inferential results are presented. In addition, based on local influence and deviance component and martingale-type residuals, a diagnostics analysis is derived. Finally, a motivating example from the medical field is analyzed using log-BS regression models. Since the parameter estimates appear to be very sensitive to outlying and influential observations, the Student-t log-BS regression model should attenuate such influences. The model checking methodologies developed in this paper are used to compare the fitted models.

The influence of ARIMA-GARCH parameters in feed forward neural networks prediction

The objective of this article is to find out the influence of the parameters of the ARIMA-GARCH models in the prediction of artificial neural networks (ANN) of the feed forward type, trained with the Levenberg-Marquardt algorithm, through Monte Carlo simulations. The paper presents a study of the relationship between ANN performance and ARIMA-GARCH model parameters, i.e. the fact that depending on the stationarity and other parameters of the time series, the ANN structure should be selected differently. Neural networks have been widely used to predict time series and their capacity for dealing with non-linearities is a normally outstanding advantage. However, the values of the parameters of the models of generalized autoregressive conditional heteroscedasticity have an influence on ANN prediction performance. The combination of the values of the GARCH parameters with the ARIMA autoregressive terms also implies in ANN performance variation. Combining the parameters of the ARIMA-GARCH models and changing the ANN`s topologies, we used the Theil inequality coefficient to measure the prediction of the feed forward ANN.

Prediction of the economic activity from the short and long-term interest rate differential: new evidences in Chile and the United States of America cases

The purpose of this work is to verify the stability of the relationship between real activity and interest rate spread. The test is based on Chen (1988) and Osorio and Galea (2006). The analysis is applied to Chile and the United States, from 1980 to 1999. In general, in both cases the relationship was statistically significant in early 80s, but a break point is found in both countries during that decades, suggesting that the relationship depends on the monetary rule follow by the Central Bank.

PREDICTION OF METAL CATION TOXICITY TO THE BIOLUMINESCENT FUNGUS GERRONEMA VIRIDILUCENS

A correlation between the physicochemical properties of mono- [Li(I), K(I), Na(I)] and divalent [Cd(II), Cu(II), Mn(II), Ni(II), Co(II), Zn(II), Mg(II), Ca(II)] metal cations and their toxicity (evaluated by the free ion median effective concentration. EC50(F)) to the naturally bioluminescent fungus Gerronema viridilucens has been studied using the quantitative ion character activity relationship (QICAR) approach. Among the 11 ionic parameters used in the current study, a univariate model based on the covalent index (X(m)(2)r) proved to be the most adequate for prediction of fungal metal toxicity evaluated by the logarithm of free ion median effective concentration (log EC50(F)): log EC50(F) = 4.243 (+/-0.243) -1.268 (+/-0.125).X(m)(2)r (adj-R(2) = 0.9113, Alkaike information criterion [AIC] = 60.42). Additional two- and three-variable models were also tested and proved less suitable to fit the experimental data. These results indicate that covalent bonding is a good indicator of metal inherent toxicity to bioluminescent fungi. Furthermore, the toxicity of additional metal ions [Ag(I), Cs(I), Sr(II), Ba(II), Fe(II), Hg(II), and Pb(II)] to G. viridilucens was predicted, and Pb was found to be the most toxic metal to this bioluminescent fungus (EC50(F)): Pb(II) > Ag(I) > Hg(I) > Cd(II) > Cu(II) > Co(II) Ni(II) > Mn(II) > Fe(II) approximate to Zn(II) > Mg(II) approximate to Ba(II) approximate to Cs(I) > Li(I) > K(I) approximate to Na(I) approximate to Sr(II)> Ca(II). Environ. Toxicol. Chem. 2010;29:2177-2181. (C) 2010 SETAC

Artificial Neural Networks and the Study of the Psychoactivity of Cannabinoid Compounds

Cannabinoid compounds have widely been employed because of its medicinal and psychotropic properties. These compounds are isolated from Cannabis sativa (or marijuana) and are used in several medical treatments, such as glaucoma, nausea associated to chemotherapy, pain and many other situations. More recently, its use as appetite stimulant has been indicated in patients with cachexia or AIDS. In this work, the influence of several molecular descriptors on the psychoactivity of 50 cannabinoid compounds is analyzed aiming one obtain a model able to predict the psychoactivity of new cannabinoids. For this purpose, initially, the selection of descriptors was carried out using the Fisher`s weight, the correlation matrix among the calculated variables and principal component analysis. From these analyses, the following descriptors have been considered more relevant: E(LUMO) (energy of the lowest unoccupied molecular orbital), Log P (logarithm of the partition coefficient), VC4 (volume of the substituent at the C4 position) and LP1 (Lovasz-Pelikan index, a molecular branching index). To follow, two neural network models were used to construct a more adequate model for classifying new cannabinoid compounds. The first model employed was multi-layer perceptrons, with algorithm back-propagation, and the second model used was the Kohonen network. The results obtained from both networks were compared and showed that both techniques presented a high percentage of correctness to discriminate psychoactive and psychoinactive compounds. However, the Kohonen network was superior to multi-layer perceptrons.