Federal Statistical Coordination Today: An Epilogue as Prologue

A common data mining task is the search for associations in large databases. Here we consider the search for “interestingly large” counts in a large frequency table, having millions of cells, most of which have an observed frequency of 0 or 1. We first construct a baseline or null hypothesis expected frequency for each cell, and then suggest and compare screening criteria for ranking the cell deviations of observed from expected count. A criterion based on the results of fitting an empirical Bayes model to the cell counts is recommended. An example compares these criteria for searching the FDA Spontaneous Reporting System database maintained by the Division of Pharmacovigilance and Epidemiology. In the example, each cell count is the number of reports combining one of 1,398 drugs with one of 952 adverse events (total of cell counts = 4.9 million), and the problem is to screen the drug-event combinations for possible further investigation.     

Simultaneous Pitman closeness of progressively type-II right-censored order statistics to population quantiles

In this work, we extend prior results concerning the simultaneous Pitman closeness of order statistics (OS) to population quantiles. By considering progressively type-II right-censored samples, we derive expressions for the simultaneous closeness probabilities of the progressively censored OS to population quantiles. Explicit expressions are deduced for the cases when the underlying distribution has bounded and unbounded supports. Illustrations are provided for the cases of exponential, uniform and normal distributions for various progressive type-II right-censoring schemes and different quantiles. Finally, an extension to the case of generalized OS is outlined.     

A community treatment intervention advancing active treatment in the elderly (ACTIVATE): a pilot study

A growing population of older adults receive treatment for depression but remain symptomatic. We report on a feasibility pilot study of an intervention (ACTIVATE) to improve depression care by encouraging the older person to take a step to intensify the existing treatment. Older adults (N = 43) receiving home-meal service and in depression treatment, but still symptomatic, participated in the ACTIVATE intervention. Assessments were conducted to evaluate change in treatment. Many (66.6%) participants took a step to change their treatment; the rate (88.2%) was higher among individuals with major depression. ACTIVATE may be a useful social work intervention to improve depression care.     

India’s ‘Missing Women’ and Men’s Sexual Risk Behavior

Although scholars and policymakers have long been concerned with the ??missing women?? of India, little rigorous research has examined the consequences of India??s sex ratio imbalance for young men??s sexual risk behavior and reproductive health. We use data from the third wave of India??s 2005?C2006 National Family and Health Survey to examine the influence of the community female-to-male sex ratio at ages 10?C39 on men??s likelihood of marrying early in life, of engaging in premarital, multi-partnered, and commercial sex, and of contracting a sexually-transmitted disease. We estimate logistic regression models that control for respondents?? demographic and socioeconomic status and that adjust for the clustering of observations within communities. Net of the effects of other characteristics, the female-to-male sex ratio is positively and significantly associated with the likelihood that men marry prior to age 18 and inversely and significantly associated with the odds that men have had intercourse with a commercial sex worker. However, no significant net associations are observed between the sex ratio and the other outcomes. Education, wealth, religious affiliation, caste, and geographic region emerge as significant predictors of Indian men??s sexual risk behaviors.     

Correlates of Treatment Retention Among Persons with Serious Mental Illness Receiving Integrated Care in a Community Mental Health Setting

ABSTRACT

Knowledge about methods to retain community mental health (CMH) clients in integrated primary and behavioral health care (PBHC) programs is needed to address longstanding health disparities. A preexisting data set that contained the clinical records of 446 PBHC program participants was used to examine whether baseline sociodemographic, health, and psychosocial characteristics predicted retention in care at 6 months post-enrollment. Results indicated that less than half of PBHC participants (43.7%) were retained in care, and approximately 17% of the variance in retention was explained by the inclusion of seven predictors in the model (overall health, medications, laboratory data, primary care provider, disorder type, transportation, and living arrangement). Clients with thought disorders were almost twice as likely as those with mood disorders to be retained in care, and greater frequency of prescribed medications also increased the likelihood of treatment continuation (ORs = 1.99 and 1.20, respectively). Future research should identify factors that improve retention in integrated PBHC programs overall, and among persons with mood disorders, in particular.     

Race and income disparities in disaster preparedness in old age

ABSTRACT

This study investigated to what extent income status and race/ethnicity in old age interplayed with disaster preparedness. Data came from the 2010 Health and Retirement Study, a nationally representative panel survey of older Americans over 51 years old. Our sample was restricted to respondents who participated in a special survey about disaster preparedness (N=1,711). Disaster preparedness was measured as a score, which includes 13 variables. Race/ethnicity was categorized by White, Black, and Hispanic. Low income was defined as below 300% of the federal poverty line. OLS regression was used to examine the main and interaction effects of race/ethnicity and lower income status on disaster preparedness scores. We found that older adults in lower income status had lower preparedness level than those in higher income (Coef. =-0.318, p<.01). Hispanics tend to be less prepared compared to White and Blacks (Coef. =-0.608, p<.001). Preparedness of Black elders was not significantly different from that of Whites. However, interestingly, Black elders in lower income status were significantly less prepared for disaster than other groups (Coef. =- 0.622, p<.05). This study identified vulnerable subgroups of older adults for disaster preparedness and suggests that preparedness programs should target minority and low income elders.     

A history and a survey of lattice path enumeration

In celebration of the Sixth International Conference on Lattice Path Counting and Applications, it is befitting to review the history of lattice path enumeration and to survey how the topic has progressed thus far.