Female harassment after ending a relationship: A preliminary study

While dramatic instances of male aggression directed toward women, such as rape and wife battering, have been frequently studied, a more subtle form of male aggression—female harassment—has been investigated less often. In the present study, 50 women who had terminated relationships with males and then were harassed were interviewed. In general, the harassment lasted for about a year, and episodes which occurred on a daily basis consisted of calls, letters, visits to home or work, being followed, verbal threats, and physical aggression. For the most part, these aggressive actions were perceived as both threatening and disturbing. Findings indicated that assertive female strategies were not more effective in reducing harassment than more sex-role stereotyped passive and nonassertive responses to male aggression. In the second phase of this study a sample of college undergraduates was interviewed on the topic of harassment. Fifty-six percent of the women indicated that they had been harassed by men.My thanks to Lyn De Amicis and LaVome Robinson for their instructive and helpful comments.     

Car Occupant Life Expectancy: Car Mass and Seat Belt Effects

Average human life expectancies for the U.S. resident population are calculated using tabulated population and survival rate data. These life expectancies are recalculated assuming elimination of various types of motor vehicle fatalities using Fatal Accident Reporting System (FARS) data. The differences between the original and recalculated values provide estimates of life expectancy reductions due to the motor vehicle fatalities. These estimates are combined with prior work relating the likelihood of an occupant fatality to car mass, so that reductions in life expectancy are determined as a function of car mass. The estimates of life expectancy reductions are also used to determine the effect of seat belt use on life expectancy. The estimates, which are based on data for 1978, assume that survival rates remain unchanged. Estimates of the changes in life expectancy associated with switching from a large (1800 kg) car to a small (900 kg) car, and switching from not using to using a seat belt are presented as functions of the age at which an individual makes the switch.     

Data entry workers perceptions and satisfaction response to the "stop and stretch" software program

Cumulative Trauma Disorder (CTD) is a collection of chronic musculoskeletal disorders caused by frequent, sustained, and repetitive movements, most notably by computer usage at the workplace. A computer based break reminder program (Stop and Stretch) has been developed and installed to prevent CTDs caused by prolonged computer usage at the workplace. We investigated users' opinions to the Stop and Stretch program at their work place. 19 computer users were recruited as the subjects of the study. We conducted a survey after all the subjects used the Stop and Stretch program for one month. Among the nineteen subjects, 52.5% or 10 noticed a difference of symptoms after using the program; 63.3% or 12 thought the program had positive effect on their productivity; 100% or all 19 thought the program was easy to follow; 100% or all 19 thought it was helpful; 94.7% or18 were satisfied with the program; and the same value would recommend the program to others. When grouped into those who had prior experience with using stretch and exercise as part of their work routine15 subjects had no prior experience; and 14 participants within that group were satisfied or very satisfied with the program; 93.3% or 14 would recommend it to co-workers; and over half of those 15 thought the program is easy to use. The study provided insight to the response to using "stretch break software" and provided indicators of satisfaction with the Stop and Stretch program and that the program had sufficient usability and acceptance within a workplace setting which might be applied in other work settings similar to these.     

Diagnostic tests for the distribution of random effects in multivariate mixed effects models

Abstract

Fourier methods are proposed for testing the distribution of random effects in classical and robust multivariate mixed effects models. The test statistics involve estimation of the characteristic function of random effects. Theoretical and computational issues are addressed while Monte Carlo results show that the new procedures compare favorably with other methods.     

An improved comorbidity summary score for measuring disease burden and predicting mortality with applications to two national cohorts

Abstract

Research involving administrative healthcare data to study patient outcomes requires the investigator to account for the patient’s disease burden in order to reduce the potential for biased results. Here we develop a comorbidity summary score based on variable importance measures derived from several statistical and machine learning methods and show it has superior predictive performance to the Elixhauser and Charlson indices when used to predict 1-year, 5-year, and 10-year mortality. We used two large Veterans Administration cohorts to develop and validate the summary score and compared predictive performance using the area under ROC curve (AUC) and the Brier score.