Kuo M, Mohler B, Raudenbush S L, Earls F J
Harvard School of Public Health, Boston, MA 02120, USA.
J Child Psychol Psychiatry. 2000 Nov;41(8):1049-56.
The present study assesses the effects of demographic risk factors on children's exposure to violence (ETV) and how these effects vary by informants. Data on exposure to violence of 9-, 12-, and 15-year-olds were collected from both child participants (N = 1880) and parents (N = 1776), as part of the assessment of the Project on Human Development in Chicago Neighborhoods (PHDCN). A two-level hierarchical linear model (HLM) with multivariate outcomes was employed to analyze information obtained from these two different groups of informants. The findings indicate that parents generally report less ETV than do their children and that associations of age, gender, and parent education with ETV are stronger in the self-reports than in the parent reports. The findings support a multivariate approach when information obtained from different sources is being integrated. The application of HLM allows an assessment of interactions between risk factors and informants and uses all available data, including data from one informant when data from the other informant is missing.
本研究评估了人口统计学风险因素对儿童暴力暴露（ETV）的影响，以及这些影响如何因信息提供者的不同而有所差异。作为对芝加哥邻里人类发展项目（PHDCN）评估的一部分，从儿童参与者（N = 1880）和父母（N = 1776）那里收集了9岁、12岁和15岁儿童的暴力暴露数据。采用具有多变量结果的两级分层线性模型（HLM）来分析从这两组不同信息提供者那里获得的信息。研究结果表明，父母报告的儿童暴力暴露情况通常比孩子自己报告的要少，而且在自我报告中，年龄、性别和父母教育程度与儿童暴力暴露之间的关联比父母报告中的更强。这些发现支持了在整合来自不同来源的信息时采用多变量方法。HLM的应用允许评估风险因素与信息提供者之间的相互作用，并使用所有可用数据，包括当一个信息提供者的数据缺失时来自另一个信息提供者的数据。
