Gender differences in the experience of violence,discrimination, and stress hormone in African Americans: Implications for public health

Violence is more prevalent in African American communities than in other American communities. This has impacts not only on criminal justice interventions but also on the physical and mental health of these communities including their risk for acquiring life-threatening diseases. While many studies have focused on the effects of violence on African American males, we sought to understand the relative gender effects that violence has on African American females. This is of particular interest given the wide array of scientific literature suggesting maternal health has inter-generational health effects. Understanding gender differences associated with exposure to violence, depression, and immune function is an important step in understanding how young women perceive and internalize societal violence directed toward and around them. We analyzed a cohort of 557 young African American adults aged 18–25 years old from the Washington, DC area. We use sociological, epidemiological, mental health, computational biology, and quantitative genetics approaches to build a predictive portrait of the effects of violence on African American health. This study demonstrates that African American males and females experience different constellations of societal violence, that African American women report greater perception of racial and gender bias, and that cortisol, an indicator of stress response, is correlated to perceived discrimination. This work contributes to current understandings of how violence contributes to negative health outcomes and lays the foundation for a predictive model for sociological, health, and behavior risk that young African Americans encounter.     

On the estimation of missing values in AR(1) model with exponential innovations

We consider estimation of a missing value for a stationary autoregressive process of order one with exponential innovations and compare two methods of estimation of the missing value, with respect to Pitman's measure of closeness (PMC).