A simple model for linking life tables by survival mortality ratios

Patterns of variation in mortality can be studied by measuring changes in selected life table functions. A model is proposed in which the rate of change over time in the life table survivorship probability at any age has been assumed as proportional to the product of its own value and its complementary probability or the probability of dying by that age, where the proportion is the same for all ages and depends only on the time duration between successive life tables. The end result is that the logit functions of the survivorship probabilities at two points in time are linearly related with a slope of one. The projecting power of the model has been tested by using U.S. life tables for the years 1950 and 1970 as well as Coale and Demeny's regional model life tables. In the latter case, the model produced surprisingly close matches even when the expectations of life differed by as much as 20 years.     

When Do First-Year College Students Drink Most During the Academic Year? An Internet-Based Study of Daily and Weekly Drinking

Abstract

Objective: The authors investigated the alcohol consumption trajectories among first-year university students. Participants: A sample of 415 students attending a large university in Southwestern Ontario, Canada, was recruited. Methods: Students completed a baseline questionnaire and 26 weekly brief Internet surveys assessing alcohol consumption from September 2006 to April 2007. Results: Findings indicated that alcohol consumption varies considerably as a function of time of the academic year. Overall trends indicate that students drink more heavily at the beginning of each semester and less during exam periods. Daily patterns indicate that most drinking occurs on weekends. The highest drinking days in the first academic year included Halloween, New Year's Eve, and St. Patrick's Day. Conclusions: The present study provides evidence that periods of high and low alcohol consumption are contingent upon specific events and the time of the year.     

Bayesian variable selection for multioutcome models through shared shrinkage

Variable selection over a potentially large set of covariates in a linear model is quite popular. In the Bayesian context, common prior choices can lead to a posterior expectation of the regression coefficients that is a sparse (or nearly sparse) vector with a few nonzero components, those covariates that are most important. This article extends the “global‐local” shrinkage idea to a scenario where one wishes to model multiple response variables simultaneously. Here, we have developed a variable selection method for a K‐outcome model (multivariate regression) that identifies the most important covariates across all outcomes. The prior for all regression coefficients is a mean zero normal with coefficient‐specific variance term that consists of a predictor‐specific factor (shared local shrinkage parameter) and a model‐specific factor (global shrinkage term) that differs in each model. The performance of our modeling approach is evaluated through simulation studies and a data example.     

Timing of Immigration Effects Asset Change Among Hispanic Caregivers of Older Family Members

Journal of Family and Economic Issues - Given the cultural value of family in Hispanic culture, older Hispanic immigrants are likely to have family caregivers. This study examined the economic...     

Back pack injuries in Indian school children: risk factors and clinical presentations

The use of backpack increased substantially among the school children. Studies have shown that carrying a backpack cause to develop different symptoms of musculoskeletal disorders among the carrier of the backpack. In India there are fewer studies available in literature which explains the musculoskeletal discomfort among the school children. This study aimed at to find out the prevalence of different musculoskeletal problems among the school children. In a retrospective study data were collected for twenty two students. The main diagnostic criteria were pressure mark (redness or swelling) over neck and shoulder corresponding to the straps of the backpack, stooping posture while carrying the back pack, pain or stiffness in the neck, upper back and shoulders predominantly while carrying the back pack and absence of these symptoms during school holidays. Results revealed that pain in the upper back (40%), neck (27%) and shoulder (20%) were most prevalent body regions followed by forearm and wrist pain (7%) and low back (6%). Results further revealed that all the students participated in this study have a pressure mark over shoulder. 54.55% of the children were diagnosed with myofascial pain and rest with thoracic outlet syndrome.     

On Das Gupta's 'Birth function in a two-sex model'

Abstract I have read with great interest Das Gupta's(1) critique of my approach(2) towards the development of a two sex-model. To set the records straight, I must state that his criticisms are not well founded due to the following reasons:     

The Allocation of Blacks in Large Firms and Establishments and Black-White Wage Inequality in the U.S. Economy

Using data from the National Longitudinal Survey of Youth (NLSY) for 1988, this study analyzes the allocation of African Americans in large firms and establishments and the effects of the allocation process on Black-White wage inequality. The results show that Blacks are disproportionately employed in large establishments while being under-represented in supervisory positions. The Black-White wage differential, however, remains significant only in the large establishments, despite this study's use of detailed controls for worker quality.     

On Das Gupta's ‘Birth function in a two-sex model’

I have read with great interest Das Gupta's¹ critique of my approach² towards the development of a two sex-model. To set the records straight, I must state that his criticisms are not well founded due to the following reasons:     

About the Effect of Changes in Age-specific Mortality on Life Expectancy

About the Effect of Changes in Age-Specific Mortality on Life Expectancy