A test for comparing conditional ROC curves with multidimensional covariates.

The comparison of Receiver Operating Characteristic (ROC) curves is frequently used in the literature to compare the discriminatory capability of different classification procedures based on diagnostic variables. The performance of these variables can be sometimes influenced by the presence of other covariates, and thus they should be taken into account when making the comparison. A new non-parametric test is proposed here for testing the equality of two or more dependent ROC curves conditioned to the value of a multidimensional covariate. Projections are used for transforming the problem into a one-dimensional approach easier to handle. Simulations are carried out to study the practical performance of the new methodology. The procedure is then used to analyse a real data set of patients with Pleural Effusion to compare the diagnostic capability of different markers.

Comparison of the epidemiological behavior of mastitis pathogens by applying time-series analysis in results of milk samples submitted for microbiological examination.

The objective of this study is to examine and compare the trends of mastitis pathogens in quarter milk samples (n = 240,232) submitted for microbiological examination at the Milk Analysis Laboratory (L.I.G.A.L.) at Galicia, Spain from June 2005 to September 2011. Autoregressive Integrated Moving Average (ARIMA) models and multivariate statistical techniques such as Cluster Analysis were used in order to detect seasonal trends and similarities between the series trends and to classify mastitis pathogens into relatively homogeneous groups. The decrease of bulk milk somatic cell counts achieved by the mastitis control program, developed in recent years in this region, is the result of the decrease in IMI caused by a limited number of mastitis pathogens. The obtained results reflect a greater complexity in the behavior of mastitis pathogens, unlike the traditional classification into contagious or environmental. Staphylococcus aureus showed a trend similar to Streptococcus dysgalactiae, a mastitis pathogen can behave in both a contagious and an environmental manner. Among the traditionally considered environmental mastitis pathogens, Strep. uberis showed a different behavior to Escherichia coli and Klebsiella pneumoniae. Coagulase-negative staphylococci (CNS) species and Streptococcus other than Strep. agalactiae showed differences in the trend model. Time-series analysis and multivariate statistical techniques, such as Cluster Analysis, could be powerful tools to assess the isolation trend of mastitis pathogens because of their ability to cope with stochastic dependence of consecutive data. Furthermore, they could be used to identify the epidemiological behavior of mastitis pathogens using the results of milk samples submitted for routine microbiological examination, by classifying them into relatively homogeneous groups.

Forest fire spatial pattern analysis in Galicia (NW Spain).

Knowledge of fire behaviour is of key importance in forest management. In the present study, we analysed the spatial structure of forest fire with spatial point pattern analysis and inference techniques recently developed in the Spatstat package of R. Wildfires have been the primary threat to Galician forests in recent years. The district of Fonsagrada-Ancares is one of the most seriously affected by fire in the region and, therefore, the central focus of the study. Our main goal was to determine the spatial distribution of ignition points to model and predict fire occurrence. These data are of great value in establishing enhanced fire prevention and fire fighting plans. We found that the spatial distribution of wildfires is not random and that fire occurrence may depend on ownership conflicts. We also found positive interaction between small and large fires and spatial independence between wildfires in consecutive years.

Artificial neural networks as a useful tool to predict the risk level of Betula pollen in the air.

An increasing percentage of the European population suffers from allergies to pollen. The study of the evolution of air pollen concentration supplies prior knowledge of the levels of pollen in the air, which can be useful for the prevention and treatment of allergic symptoms, and the management of medical resources. The symptoms of Betula pollinosis can be associated with certain levels of pollen in the air. The aim of this study was to predict the risk of the concentration of pollen exceeding a given level, using previous pollen and meteorological information, by applying neural network techniques. Neural networks are a widespread statistical tool useful for the study of problems associated with complex or poorly understood phenomena. The binary response variable associated with each level requires a careful selection of the neural network and the error function associated with the learning algorithm used during the training phase. The performance of the neural network with the validation set showed that the risk of the pollen level exceeding a certain threshold can be successfully forecasted using artificial neural networks. This prediction tool may be implemented to create an automatic system that forecasts the risk of suffering allergic symptoms.

Reporting delay: a review with a simulation study and application to Spanish AIDS data.

To correct for the effect of reporting delay on incidence data relating to AIDS, three methods of estimation have been analysed: Poisson log-linear; log-linear logistic mixed regression (log-logit), and truncation. The first two methods transform the data in a contingency table. The difference between them is the hypothesis of delay stationarity, which is only assumed by the former. A correction is proposed for the first method to improve its asymptotic properties. The truncation method is based on the product-limit estimator. A simulation study was carried out to examine the behaviour (means, variances and mean squared errors) of the three methods. All were applied to data from the National Commission on AIDS (Spain), showing an improvement in reporting efficiency.