Using Multilevel Statistical Models in Social Work Intervention Research

ABSTRACT

Statistical analyses of data from a classroom-based study illustrate the need to account for intra-class clustering in studies involving schools, classrooms, and other higher order units of analysis. Students were clustered in homerooms that were assigned to intervention and comparison conditions. Standard multiple linear regression analysis yielded a significant group effect but incorrectly ignored intra-cluster response correlations. A multilevel model appropriately accounting for the dependency among responses in the same cluster yielded a nonsignificant group effect. Implications for the analysis of intervention research data are discussed.     

Use of multiple cluster analysis methods to explore the validity of a community outcomes concept map

Concept mapping is now a commonly-used technique for articulating and evaluating programmatic outcomes. However, research regarding validity of knowledge and outcomes produced with concept mapping is sparse. The current study describes quantitative validity analyses using a concept mapping dataset. We sought to increase the validity of concept mapping evaluation results by running multiple cluster analysis methods and then using several metrics to choose from among solutions. We present four different clustering methods based on analyses using the R statistical software package: partitioning around medoids (PAM), fuzzy analysis (FANNY), agglomerative nesting (AGNES) and divisive analysis (DIANA). We then used the Dunn and Davies-Bouldin indices to assist in choosing a valid cluster solution for a concept mapping outcomes evaluation. We conclude that the validity of the outcomes map is high, based on the analyses described. Finally, we discuss areas for further concept mapping methods research.     

A new measure of risk-taking in gambling

This study uses a simple metric to assess the degree of risk an individual player takes on while gambling. The player’s average potential gross win per bet placed captures both the amount of money put at risk and the volatility of returns, each of which will be correlated with risk of gambling harm. To illustrate the potential usefulness of this metric, the study analyses individual account data relating to online bets on horse racing. Analysing total stakes, the traditional indicator of risk taking, and applying ordinary least squares regression, the greatest risk takers appear to be males in their mid-fifties. Using the new metric and applying quantile regression to allow a focus on heavier bettors, the highest risk takers are shown as substantially younger, males around 30. Choice of metric and estimation method therefore matter and the approach proposed here could be used by operators to identify which online players take greatest risks.     

统计显著性:一个被误读的P值——基于美国统计学会的声明

美国统计学会关于统计显著性与P值的官方声明发布之后,再次引发国内外研究学者对P值的广泛关注。在介绍国内统计教材中假设检验的基本内容和步骤的基础上,以硬币投掷与背影识人为例直观性解释P值、统计显著性与统计功效等相关概念,并引用心理学统计经典调查案例分析P值被误读的原因。同时,基于美国统计学会的声明,给出正确使用P值的建议。     

Pre-term Foetal Life Times in Scotland

A proportional hazards model was used to evaluate the association between ten categorical covariates and the risk of pre-term delivery for women having their first child and women in subsequent pregnancies. An adaptation of the model for use with grouped survival times made it possible to model foetal life times between 28 and 36 completed weeks of gestation for 67,000 Scottish singleton births in 1981. The use of the model was justified by testing time-dependent effects. For both groups of women age, and a history of abortion, were major factors associated with increased hazard. For women experiencing a second or higher-order birth a history of perinatal death was also associated with substantially increased hazard to the pregnancy.     

图书馆读者调查统计与分析

问卷调查情况表明,读者对学校图书馆服务满意度以及图书馆数据库资源的利用率两项均偏低。需要我们牢田树立“以人为本”的管理和服务理念,调整图书馆管理工作思路,提高馆员自身素质,才能适应时代发展的要求。     

高校毕业生就业率统计方法探析

随着我国由计划经济体制向市场经济体制转变,大学生就业也由统包统配向自主择业转变,高校就业率统计工作如何适应形势的发展,从而能够科学、准确地反映出高校实际的就业状况和办学水平,使之能够促进高校教育健康发展是一个值得研究的课题,本文主要总结了我国近年来就业率统计方式的形成、演变过程及现行就业率统计中存在的问题,为就业率统计方法的改革研究奠定基础。     

基于分形理论的时尚商品价格预测问题研究

在研究时尚商品价格规律及影响因素的复杂性、不确定性的基础之上,提出了基于分形理论的时尚商品价格预测新方法。该方法首先运用重标极差法分析了时尚商品价格时间序列预测的可行性,然后根据分形统计模型,得到时尚商品历史价格时间序列的分形维数,通过不断增加新销售或预测得到新的记录方法,求得增加新记录后的新分形维数,由此可以预测出下一时间单位的商品销售价格。通过实例进行了方法检验和结果比较,取得了较为理想的预测结果,证明了该方法的可行性和有效性。     

我国外语实证研究工具层面问题分析

我国现阶段外语实证研究存在两大工具层面的问题:(1)虚构统计量与误用统计方法或统计量;(2)论证违反逻辑规则。这些问题的表现形式多种多样,即使在外语类核心学术期刊登载的研究报告中也不鲜见。虽然主要原因是我国外语教育研究者对实证研究所需要的统计学与逻辑学学科体系了解不足,但有的高层次研究者在虚构时所表现的胆大妄为与无所顾忌,也实在令人诧异。     

居民生活质量的统计分析与综合评价

选择15个指标作为评价居民生活质量的指标体系。利用2004年31个省市的截面数据进行因子分析。依据因子分析结果的特点,计算31个省市居民生活质量的5个因子得分和综合得分。依据综合得分高低对31个省市居民生活质量进行排序与综合评价。