Conducting research on violence in Asian American communities: methodological issues

Conducting culturally competent research is a challenge as the United States becomes increasingly multicultural. When conducting research on violence in Asian American communities, researchers need to consider how culture, race, and ethnicity influence definitions of concepts, and methodological issues such as research designs, sampling, developing and translating instruments, ethical issues, recruiting research participants, supervising and training interviewers, and disseminating findings. Examples from the authors' research studies on community violence in the Khmer community, domestic violence in the Chinese American community, and dating violence in Asian American groups are extrapolated to highlight various themes. A commitment to a research program that collaborates with the community under study and cultural experts is vital at every stage of the research process.     

Bayer reorganizes in response to growth

In this article the Head of Strategic Planning at Bayer AG describes the new corporate structure which was introduced into the company in 1984, and the considerations which led to its development and implementation.     

A Perturbation Approach to Outlier Detection in Two-Way Contingency Tables

In order to identify outliers in contingency tables, we evaluate the derivatives of the perturbation-formed surface of the Pearson goodness-of-fit statistic. The resulting diagnostics are shown to be less susceptible to masking and swamping problems than residual-based measures. A Monte Carlo study further confirms the effectiveness of the proposed diagnostics.     

The use of formal inventory control models: A preliminary survey

Of the many papers and texts on the subject of inventory control, relatively few report the successful implementation of systems based on formal mathematical models developed with specific objectives in mind. This could be considered rather strange in the light of the relatively high number of papers reporting the development of models for dealing with a multitude of different hypothetical situations, and the widespread availability of computer systems capable of exploiting such models. Various reasons for this anomaly can be put forward. This paper reports the results of a preliminary survey designed to investigate this more deeply, and draws some necessarily tentative conclusions relating to factors contributing to the successful application of such systems.     

The effects of seasonal demand on depot location

Many of the cost functions associated with depot location algorithms assume an overall demand for a fixed period, usually one year. This paper describes an investigation into the effect of high seasonality within such demand figures on the optimal location of storage facilities. The preliminary results indicate that a more flexible approach for certain products could be worthwhile.     

Existence of unbiased covariance components estimators

The condition of PINCUS (1974) for the estimability of covariance components in normal models is extended to the case of singular covariance matrices     

Experiences and perceptions of intimate partner violence among older Chinese immigrants

This study examines the experiences and perceptions of domestic violence among older Chinese immigrants, using data from a larger sample of Chinese Americans who reside in a major metropolitan area in the West Coast (Yick, 2000). A subset of respondents 50 years and older who are foreign-born (n = 77) were selected to (1) examine older Chinese immigrants' experiences with physical abuse by a spouse, (2) explore the definitions and perceptions of intimate partner violence among older Chinese, and (3) examine the relationship between acculturation, victimization experiences, and perceptions of domestic violence among this population. Findings indicate that close to 7% of the women and 6% of the men have experienced minor physical violence by their spouses during the past 12 months. Gender and acculturation were associated with perceptions and attitudes towards domestic violence.     

Sensitivity of the portmanteau statistic in time series modeling

The portmanteau statistic is commonly used for testing goodness-of-fit of time series models. However, this lack of fit test may depend on one or several atypical observations in the series. We investigate the sensitivity of the portmanteau statistic in the presence of additive outliers. Diagnostics are developed to assess both local and global influence. Three practical examples demonstrate the usefulness of the proposed diagnostics.