A review of classic non-asymptotic methods for comparing two proportions by means of independent sampLES

The 2 × 2 tables used to present the data in an experiment for comparing two proportions by means of two observations of two independent binomial distributions may appear simple but are not. The debate about the best method to use is unending, and has divided statisticians into practically irreconcilable groups. In this article, all the available non-asymptotic tests are reviewed (except the Bayesian methodology). The author states which is the optimal (for each group), referring to the tables and programs that exist for them, and contrast the arguments used by supporters of each of the options. They also sort the tangle of solutions into "families", based on the methodology used and/or prior assumptions, and point out the most frequent methodological mistakes committed when comparing the different families.     

Basu's Lemma and Goodness-of-Fit Tests

In this paper we develop a technique that is useful in goodness of fit problems with nuisance location and scale parameters. Using Basu's lemma, we transform the sample so that it is independent of the nuisance parameters. The technique will be illustrated by several examples, a discussion of the efficiency of the proposed procedure, and some concluding remarks will given.     

For Your Information

Abstract

The criteria for selecting a serials management system are often the same as those for selecting an integrated library system in toto. In the post-selection/production environment, the library–vendor relationship matures as a new operational framework is established. Serials management systems must become more efficient and make better use of electronic commerce, especially as a greater emphasis is placed on access to electronic journals (e-journals). Serials Review 2002; 28:93–101.     

The Child Abuse Risk Evaluation Dutch Version (CARE-NL): A retrospective validation study

Abstract

The Child Abuse Risk Evaluation – Dutch version (CARE-NL) is a structured professional guideline for assessing the risk of all types of child abuse. The CARE-NL comprises 18 risk factors: eight Parental characteristics, three Parent-Child interaction factors, five Family factors, one Child vulnerability factor, and an extra factor for child sexual abuse risk. We examined interrater reliability and predictive accuracy of the instrument in a retrospective study at Advice and Reporting Centers on Child Abuse (ARCCA) in The Netherlands. The ARCCA files contained limited information on Parental risk factors, while parental characteristics, such as mental disorder and substance abuse, are the most important risk factors for (repeated) child abuse. On the other hand, the majority of the files included ample information on child and family characteristics. The CARE-NL could be reliably coded by trained raters and the predictive accuracy for out-of-home placement (AUC = .73) and placement of the child under court supervision (AUC = .78), at two years follow-up, was adequate. Use of the CARE-NL ensures that the assessment of the risk of child abuse focuses on the most important, empirically based risk factors in a structured and coherent way.     

Colonization and habitat selection of a declining farmland species in urban areas

Despite the accelerating global urbanization and its associated implications for wildlife and humans, we know little about the biology of urban ecosystems. Here, we investigated colonization and habitat selection of the European hare (Lepus europaeus), a declining farmland species, in urban areas in Denmark, using a combination of citizen science data and transect counts. Further, we estimated the population density of urban hares in Aarhus, Denmark’s second largest city. Our results provide the first evidence that hares have established populations in urban areas, potentially in response to decreasing habitat quality in rural areas due to agricultural intensification. The hare density in Aarhus was ca. 8 hares per km², which is comparable to or slightly higher than hare abundance estimates from various pastural areas in Europe, suggesting that urban areas provide suitable habitat for hares. Hare habitat selection was generally associated with areas consisting of large lawns, such as high buildings and parks, which potentially provide high-quality forage throughout the year. Considering the increasing expansion of urban areas and deteriorating habitat quality of agricultural areas, urban planning that incorporates habitat requirements for wildlife could help to support urban animal populations, especially for species of conservation concern.

     

Birth Intervals and Health in Adulthood: A Comparison of Siblings Using Swedish Register Data

A growing body of research has examined whether birth intervals influence perinatal outcomes and child health as well as long-term educational and socioeconomic outcomes. To date, however, very little research has examined whether birth spacing influences long-term health. We use contemporary Swedish population register data to examine the relationship between birth-to-birth intervals and a variety of health outcomes in adulthood: for men, height, physical fitness, and the probability of falling into different body mass index categories; and for men and women, mortality. In models that do not adjust carefully for family background, we find that short and long birth intervals are clearly associated with height, physical fitness, being overweight or obese, and mortality. However, after carefully adjusting for family background using a within-family sibling comparison design, we find that birth spacing is generally not associated with long-term health, although we find that men born after very long birth intervals have a higher probability of being overweight or obese in early adulthood. Overall, we conclude that birth intervals have little independent effect on long-term health outcomes.     

Iwi community justice panels reduce harm from re-offending

ABSTRACT

The effect of iwi community justice panels is assessed using data from seven years of implementation. Panel participants of 1013 are compared to a control group drawn from 73,000 offenders charged with similar offences and propensity-matched by age, gender, ethnicity, offending history and location. The dependent measure is re-harm from offending calculated using the NZ Crime Harm Index. Panel participants did not reduce their rate of offending compared to matched controls. However, there is a significant reduction in harm from post-panel offending, on average by 26.9 ± 21.05 equivalised prison days. The relative reduction is 22.25% of the harm committed by matched controls. Iwi panels are an effective alternative justice resolution. Panel participants are found to re-offend with minor offences and thus any focus on rates of offending would miss the complexity of the restorative justice process that reduces the harm of re-offending.