Correcting data for measurement error in generalized linear models

This paper discusses a general strategy for reducing measurement-error-induced bias in statistical models. It is assumed that the measurement error is unbiased with a known variance although no other distributional assumptions on the measurement-error are employed,

Using a preliminary fit of the model to the observed data, a transformation of the variable measured with error is estimated. The transformation is constructed so that the estimates obtained by refitting the model to the ‘corrected’ data have smaller bias,

Whereas the general strategy can be applied in a number of settings, this paper focuses on the problem of covariate measurement error in generalized linear models, Two estimators are derived and their effectiveness at reducing bias is demonstrated in a Monte Carlo study.     

Is It Safer to Fly or Drive?

In attempts to soothe the nascent fear of the scheduled airline traveler, passengers waiting takeoff are sometimes reminded of the cliche that they may have already completed the most dangerous part of their trip — the drive to the airport. The objective of this paper is to communicate under what conditions air travel is indeed safer than highway travel and vice versa. The conventional wisdom among risk communicators that air travel is so much safer than car travel arises from the most widely quoted death rates per billion miles for each — 0.6 for air compared to 24 for road. There are three reasons why such an unqualified comparison of aggregated fatality rates is inappropriate. First, the airline rate is passenger fatalities per passenger mile, whereas the road rate is all fatalities (any occupants, pedestrians, etc.) per vehicle mile. Second, road travel that competes with air travel is on the rural interstate system, not on average roads. Third, driver and vehicle characteristics, and driver behavior, lead to car-driver risks that vary over a wide range. Expressions derived to compare risk for drivers with given characteristics to those on airline trips of given distance showed that 40-year-old, belted, alcohol-free drivers of cars 700 pounds heavier than average are slightly less likely to be killed in 600 miles of rural interstate driving than in airline trips of the same length. Compared to this driver, 18-year-old, unbelted, intoxicated, male drivers of cars 700 pounds lighter than average have a risk over 1000 times greater. Furthermore, it is shown that the cliche above is untrue for a group of drivers having the age distribution of airline passengers.     

Ethical Considerations in Sex Therapy

The most ethical sex therapy is that which cures the symptom and improves the marital relationship in the briefest time at the least cost. Neither insight therapy, nor direct sexual interaction with the client satisfy these criteria. Examples are given of effective ethical therapies, useful in male and female sexual dysfunctions.     

The relationship between bonding and bridging social capital among Christian denominations across Australia

This article is an intricate empirical examination of the relationship between bridging and bonding with respect to subcultural differences in religious denomination and faith orientation. The respondents were 2,710 Christian church attendees from nineteen denominations across Australia. They were surveyed with a closed‐answer questionnaire covering the topics of faith, demographics, involvement in the congregation, and involvement in the wider community. The results revealed a positive relationship between bonding and bridging social capital, with a high level of bonding associated with a high level of bridging for all denominations and faith identities. There was no evidence that high bonding within the congregation restricted bridging beyond the congregation. The results support the notion that the relationship between bonding and bridging may vary with societal subcultures.     

Social class and political participation: A review and an explanation

This paper reviews and explains the relationship between socioeconomic status and political participation from a structural perspective; i.e., social organization influences people's range of options, producing different rates of behavior among those in varying locations in the society. There are six categories of political participation: cognitive, expressive, organizational, electoral, partisan, and governmental. In each case, the poor display the lowest and the rich the highest rate of participation. This difference reflects variations in political and psychological resources and the structure of the electoral process. As a result, political benefits also differ by social class.