No abstract

The literature on GWAS (genome-wide association studies) data suggests that very large sample sizes (for example, 50,000 cases and 50,000 controls) may be required to detect significant associations of genomic regions for complex disorders such as Alzheimer's disease (AD). Because of the challenges of obtaining such large cohorts, we describe here a novel sequential strategy that combines pooling of DNA and bootstrapping (pbGWAS) in order to significantly increase the statistical power and exponentially reduce expenses. We applied this method to a very homogeneous sample of patients belonging to a unique and clinically well-characterized multigenerational pedigree with one of the most severe forms of early onset AD, carrying the PSEN1 p.Glu280Ala mutation (often referred to as E280A mutation), which originated as a consequence of a founder effect. In this cohort, we identified novel loci genome-wide significantly associated as modifiers of the age of onset of AD (CD44, rs187116, P = 1.29 × 10–12; NPHP1, rs10173717, P = 1.74 × 10–12; CADPS2, rs3757536, P = 1.54 × 10–10; GREM2, rs12129547, P = 1.69 × 10–13, among others) as well as other loci known to be associated with AD. Regions identified by pbGWAS were confirmed by subsequent individual genotyping. The pbGWAS methodology and the genes it targeted could provide important insights in determining the genetic causes of AD and other complex conditions.

Background: Depression is associated with Alzheimer’s disease (AD). Objective: To evaluate the association between depressive symptoms and age of onset of cognitive decline in autosomal dominant AD, and to determine possible factors associated to early depressive symptoms in this population. Methods: We conducted a retrospective study to identify depressive symptoms among 190 presenilin 1 (PSEN1) E280A mutation carriers, subjected to comprehensive clinical evaluations in up to a 20-year longitudinal follow-up. We controlled for the following potential confounders: APOE, sex, hypothyroidism, education, marital status, residence, tobacco, alcohol, and drug abuse. Results: PSEN1 E280A carriers with depressive symptoms before mild cognitive impairment (MCI) develop dementia faster than E280A carriers without depressive symptoms (Hazard Ratio, HR = 1.95; 95% CI, 1.15–3.31). Not having a stable partner accelerated the onset of MCI (HR = 1.60; 95 % CI, 1.03–2.47) and dementia (HR = 1.68; 95 % CI, 1.09–2.60). E280A carriers with controlled hypothyroidism had later age of onset of depressive symptoms (HR = 0.48; 95 % CI, 0.25–0.92), dementia (HR = 0.43; 95 % CI, 0.21–0.84), and death (HR = 0.35; 95 % CI, 0.13–0.95). APOE ɛ2 significantly affected AD progression in all stages. APOE polymorphisms were not associate to depressive symptoms. Women had a higher frequency and developed earlier depressive symptoms than men throughout the illness (HR = 1.63; 95 % CI, 1.14–2.32). Conclusion: Depressive symptoms accelerated progress and faster cognitive decline of autosomal dominant AD. Not having a stable partner and factors associated with early depressive symptoms (e.g., in females and individuals with untreated hypothyroidism), could impact prognosis, burden, and costs.

El objetivo de esta investigación fue analizar factores demográficos, socioeconómicos y académicos asociados con deserción y graduación, mediante un modelo de riesgos competitivos. Se incluyeron 639 estudiantes matriculados en 2009-2010, a quienes se les realizó seguimiento durante 14 periodos académicos. Los resultados mostraron que la probabilidad acumulada de deserción para el segundo periodo académico fue de 0.147. La probabilidad de graduarse en el tiempo estipulado por el programa fue del 0.187 y de 0.328 un año después. Para el periodo 14, el 49.0% de los estudiantes había obtenido su título y el 35.4% habían desertado. Variables socioeconómicas estuvieron asociadas a la probabilidad de deserción, mientras que ciertas condiciones demográficas se asociaron con la probabilidad de graduación. No obstante, las variables académicas tuvieron un efecto significativo en ambos desenlaces. Se concluye que las características asociadas a la deserción y la graduación se corresponden con aspectos que se pueden intervenir por las instituciones educativas para incrementar la permanencia y graduación.

Most survival analyzes are based on exact failure times and right censored observations, using methods widely known as the Kaplan-Meier (KM). When the data are interval censored is necessary to use the Turnbull's method to estimate the survival function, but in practice is often used the imputation of failure times in this kind of censorship through the midpoint of the interval, the right end of the interval or generating a random point within the interval using the uniform distribution. This paper studies through simulation the effect of three types of imputation on the estimates of the survival curve compared to the method developed by Turnbull. Different simulation scenarios based on the sample size and the time between visits were analyzed. In all scenarios simulation functions estimated using data imputation differ significantly from the true survival function S(t).Key words: Survival Analysis, Interval Censoring, Data Imputation. ResumenLa mayoría de los análisis de supervivencia se basan en tiempos de falla exactos y observaciones censuradas a la derecha, utilizándose métodos ampliamente difundidos como el método de Kaplan-Meier (KM). Cuando los datos presentan censura a intervalo es necesario utilizar el método de Turnbull para estimar la función de supervivencia, sin embargo en la práctica se usa con frecuencia la imputación del tiempo de falla en este tipo de censura a través del punto medio del intervalo (PM), el extremo derecho del intervalo (ED) o generando un punto aleatorio dentro del mismo a través de la distribución uniforme. Este trabajo estudia a través de simulación el efecto de los tres tipos de imputación sobre la estimación de la curva de supervivencia en comparación al método desarrollado por Turnbull. Se analizaron diferentes escenarios de simulación basados en el tamaño de muestra y el tiempo entre visitas. En todos los escenarios de simulación las funciones estimadas usando imputación de datos difieren significativamente de la verdadera función de supervivencia S(t).

This paper develops simultaneous condence bands using computer intensive methods based on resampling, for the expected discounted warranty costs in coherent systems under physical minimal repair, that is, when the system is observed at its components level and only the component that causes the fault is minimally repaired. For this purpose, it is shown that, under the framework of the Martingale processes and the central limit resampling theorem (CLRT) over stochastic processes, the discounted warranty cost processes satisfy the conditions set by the central limit resampling theorem (CLRT). Additionally, a simulation study is performed on the most relevant variables, such that the nite sample features of the proposed bands may be assessed, based on their actual coverage probabilities. The results in the considered scenarios show that resampling-based simultaneous condence bands have coverage probabilities that are close to the nominal coverage. In particular, the agreement is good when there are 100 systems or more where a large number of resamples are used for the approximation.Key words: Central Limit Theorem; Coverage Probability; Point Process; Resampling; Semimartingales; Weak Convergence. ResumenEste trabajo desarrolla bandas de conanza simultáneas usando métodos computacionales intensivos basados en remuestreo, para el costo medio de garantía descontado en sistemas coherentes bajo reparo mínimo físico, esto a PhD. E-mail: cmlopera@unal.edu.co b PhD. E-mail: ngonzale@unal.edu.co 1 2 Carlos M. Lopera-Gómez & Nel G. González-Álvarez es, cuando el sistema es observado al nivel de sus componentes y sólo la componente que causa la falla es reparada mínimamente. Para ello se prueba que, bajo el marco teórico de los procesos martingala, los procesos de costos de garantía descontados cumplen las condiciones del teorema de límite central de remuestreo (CLRT). Un estudio de simulación Monte Carlo se realiza para evaluar, a través de las probabilidades de cobertura alcanzadas, el desempeño de las bandas propuestas en muestras nitas. Los resultados en los escenarios considerados muestran que las bandas de conanza basadas en remuestreo tienen probabilidades de cobertura con valores cercanos a los esperados, en particular para aquellas basadas en muestras con más de 100 sistemas donde el número de remuestras usado para la aproximación es grande.Palabras clave: convergencia débil; probabilidad de cobertura; proceso puntual; remuestreo; semimartingalas; teorema de límite central.

En este artículo se abordó la problemática de dos riesgos que están compitiendo para causar la falla de un sujeto; en particular determinar si los riesgos o probabilidad de falla asociada a cada tipo de falla son igualmente importantes o si un riesgo es más serio que el otro. Para este fin se hizo un estudio de la prueba de hipótesis para la igualdad de las dos funciones de incidencia acumulada asociadas a los riesgos. Se realizó un estudio de simulación donde se comparan algunos de los procedimientos de prueba que han sido propuestos para este fin; y así, poder determinar el comportamiento de estos procedimientos de prueba bajo varios escenarios que permitan evaluar el desempeño de los mismos. Se incluyen los procedimientos de prueba usando datos reales de pacientes con linfoma.

Copulas have become a useful tool for modeling data when the dependence among random variables exists and the multivariate normality assumption is not fulfilled. The copulas have been applied in several fields. In finance, copulas are used in asset modeling and risk management. In biomedical studies, copulas are used to model correlated lifetimes and competitive risks [1]. In engineering, copulas are used in multivariate process control and hydrological modeling [2]. The interest in modeling multivariate problems involving dependent variables is generalized in several areas, making this methodology in a convenient way to model the dependence structure of random variables. However, in practice a first step before modeling phenomena through copulas is to assess whether there is dependence among the variables involved. In this paper some graphical methods to detect dependence are discussed and their performance will be evaluated through a simulation study. An application of graphical methods presented to insurance data is illustrated.