Addressing missing covariates for the regression analysis of competing risks: Prognostic modelling for triaging patients diagnosed with prostate cancer.

Competing risks arise in medical research when subjects are exposed to various types or causes of death. Data from large cohort studies usually exhibit subsets of regressors that are missing for some study subjects. Furthermore, such studies often give rise to censored data. In this article, a carefully formulated likelihood-based technique for the regression analysis of right-censored competing risks data when two of the covariates are discrete and partially missing is developed. The approach envisaged here comprises two models: one describes the covariate effects on both long-term incidence and conditional latencies for each cause of death, whilst the other deals with the observation process by which the covariates are missing. The former is formulated with a well-established mixture model and the latter is characterised by copula-based bivariate probability functions for both the missing covariates and the missing data mechanism. The resulting formulation lends itself to the empirical assessment of non-ignorability by performing sensitivity analyses using models with and without a non-ignorable component. The methods are illustrated on a 20-year follow-up involving a prostate cancer cohort from the National Cancer Institutes Surveillance, Epidemiology, and End Results program.

Microcultures of lactic acid bacteria: characterization and selection of strains, optimization of nutrients and gallic acid concentration.

Eighteen lactic acid bacteria (LAB) strains, isolated from coffee pulp silages were characterized according to both growth and gallic acid (GA) consumption. Prussian blue method was adapted to 96-well microplates to quantify GA in LAB microcultures. Normalized data of growth and GA consumption were used to characterize strains into four phenotypes. A number of 5 LAB strains showed more than 60% of tolerance to GA at 2 g/l; whereas at 10 g/l GA growth inhibition was detected to a different extent depending on each strain, although GA consumption was observed in seven studied strains (>60%). Lactobacillus plantarum L-08 was selected for further studies based on its capacity to degrade GA at 10 g/l (97%). MRS broth and GA concentrations were varied to study the effect on growth of LAB. Cell density and growth rate were optimized by response surface methodology and kinetic analysis. Maximum growth was attained after 7.5 h of cultivation, with a dilution factor of 1-1/2 and a GA concentration between 0.625 and 2.5 g/l. Results indicated that the main factor affecting LAB growth was GA concentration. The main contribution of this study was to propose a novel adaptation of a methodology to characterize and select LAB strains with detoxifying potential of simple phenolics based on GA consumption and tolerance. In addition, the methodology presented in this study integrated the well-known RSM with an experimental design based on successive dilutions.

Selección para contenido de proteína y rendimiento de grano en trigo irradiado recurrentemente / Selection for grain protein content and yield in recurrently irradiated wheat

Con el objetivo de seleccionar para tamaño y peso de grano líneas de trigo (Triticum aestivum L.) de alto contenido de proteína y rendimiento de grano, a partir de compuestos genéticos irradiados provenientes de la variedad Salamanca, se seleccionaron espigas de donde, en los siguientes ciclos, se seleccionaron 637 plantas donde el contenido de proteína del grano fue analizado. De éstas se seleccionaron 29 de alta proteína y 23 de alto rendimiento de grano. La distribución de frecuencias del contenido de proteína en las 637 plantas tendió a la normal, con media de 13,6 por ciento, (10,9-16,8 por ciento; varianza de 1,0). La evaluación de líneas mostró que con irradiación recurrente y selección para tamaño y peso de grano se incrementó el contenido de proteína y rendimiento de grano. La línea con mayor proteína superó en 19,8 por ciento a Salamanca y en 21,8 por ciento a Romoga; la de mayor rendimiento superó a estas variedades en 45,3 y 35,8 por ciento, respectivamente. Las líneas L44 y L46 tuvieron los mayores incrementos en proteína (10,3 y 9,5 por ciento) y rendimiento de grano (31,8 y 24,8 por ciento) con respecto a Salamanca, mientras que en relación a Romoga, los respectivos incrementos fueron de 12,1 y 11,2 por ciento para proteína, y de 23,1 y 16,7 por ciento para rendimiento. Las líneas superaron a las variedades en volumen y peso de grano, pero en densidad del grano, número de tallos por planta y espiguillas por espiga, solo las líneas de alto rendimiento superaron a estas variedades.

A flexible class of parametric transition regression models based on copulas: application to poliomyelitis incidence.

This paper presents an extension of a general parametric class of transitional models of order p. In these models, the conditional distribution of the current observation, given the present and past history, is a mixture of conditional distributions, each of them corresponding to the current observation, given each one of the p-lagged observations. Such conditional distributions are constructed using bivariate copula models which allow for a rich range of dependence suitable to model non-Gaussian time series. Fixed and time varying covariates can be included in the models. These models have the advantage of straightforward construction and estimation for the analysis of time series and more general longitudinal data. A poliomyelitis incidence data set is used to illustrate the proposed methods, contrary to other researches' conclusions whose methods are mainly based on linear models, we find significant evidence of a decreasing trend in polio infection after accounting for seasonality.