THE IMPACT OF METHOD CHOICE ON META-ANALYSIS

This paper focusses mainly on three crucial choices identified in recent meta-analyses, namely (a) the effect of using approximate statistical techniques rather than exact methods, (fa) the effect of using fixed or random effect models, and (c) the effect of publication bias on the meta-analysis result. The paper considers their impact on a set of over thirty studies of passive smoking and lung cancer in non-smokers, and addresses other issues such as the role of study comparability, the choice of raw or adjusted data when using published summary statistics, and the effect of biases such as misclassification of subjects and study quality. The paper concludes that, at least in this example, different conclusions might be drawn from metaanalyses based on fixed or random effect models; that exact methods might increase estimated confidence interval widths by 5–20% over standard approximate (logit and Mantel-Haenszel) methods, and that these methods themselves differ by this order of magnitude; that taking study quality into account changes some results, and also improves homogeneity; that the use of unadjusted or author-adjusted data makes limited difference; that there appears to be obvious publication bias favouring observed raised relative risks; and that the choice of studies for inclusion is the single most critical choice made by the modeller.     

Efficient network meta-analysis: A confidence distribution approach

Network meta-analysis synthesizes several studies of multiple treatment comparisons to simultaneously provide inference for all treatments in the network. It can often strengthen inference on pairwise comparisons by borrowing evidence from other comparisons in the network. Current network meta-analysis approaches are derived from either conventional pairwise meta-analysis or hierarchical Bayesian methods. This paper introduces a new approach for network meta-analysis by combining confidence distributions (CDs). Instead of combining point estimators from individual studies in the conventional approach, the new approach combines CDs, which contain richer information than point estimators, and thus achieves greater efficiency in its inference. The proposed CD approach can efficiently integrate all studies in the network and provide inference for all treatments, even when individual studies contain only comparisons of subsets of the treatments. Through numerical studies with real and simulated data sets, the proposed approach is shown to outperform or at least equal the traditional pairwise meta-analysis and a commonly used Bayesian hierarchical model. Although the Bayesian approach may yield comparable results with a suitably chosen prior, it is highly sensitive to the choice of priors (especially for the between-trial covariance structure), which is often subjective. The CD approach is a general frequentist approach and is prior-free. Moreover, it can always provide a proper inference for all the treatment effects regardless of the between-trial covariance structure.     

Small sample properties of tests on homogeneity in one—way Anova and Meta—analysis

Received: January 12, 2000; revised version: July 26, 2000     

The ‘Freshman 5’: A Meta-Analysis of Weight Gain in the Freshman Year of College

Abstract

Objective: (1) To use the available research to estimate the amount of weight gained by college freshman during their first year of college. (2) To identify potential predictors of freshman weight gain. Methods: A meta-analysis was conducted in November 2008. The analysis focused on articles published in English scientific journals between 1985 and 2008 available on the MEDLINE, Web of Science, and PsycINFO databases and excluded studies of weight change over periods beyond freshman year. Results: Twenty-four studies met the inclusion criteria. Based on a pooled sample of 3,401 cases, mean weight gain was 3.86 (95% confidence intervals [CI] = 3.81–3.91) lbs. Potential contributors to gain were recent dieting, high baseline weight, and psychological stress. Conclusions: The first year of college is a period of vulnerability for weight problems. Further research is needed to better understand freshman weight gain and devise appropriate prevention strategies based on predictors of gain.     

Mapping agenda-setting research in China: a meta-analysis study

Since the 1968 Chapel Hill study by McCombs and Shaw (1972), agenda-setting theory has become a main perspective of research on media effects, and it has been tested in many other countries outside the United States. The thematic meta-analysis of Chinese agenda-setting articles performed in this study identifies some important trends of agenda-setting research in mainland China, including an increase of interest in agenda-setting theory, a dominance of the original agenda-setting approach and focus, a diversity of topical domains, an atheoretical and non-empirical research tradition, and an increasing concern about the Internet. Challenges and future directions of Chinese agenda-setting research are also discussed in this study.     

企业社会资本与企业绩效关系的元分析

根据76篇关于企业社会资本与企业绩效关系的实证文献的研究结果,运用元分析技术,再研究企业社会资本与企业绩效之间的关系,以克服单一研究中存在的样本代表性不够或样本量不足等问题.首先汇总估计企业内部和外部社会资本在结构、关系、认知三个维度上与企业绩效之间的相关系数,进而运用回归分析,在控制社会资本不同维度的相关性后,检验不同维度的企业内、外部社会资本对企业绩效影响的相对强度,结果表明:企业内、外部社会资本的三个维度对企业绩效的影响均显著为正；在内部社会资本中,认知维度对企业绩效的影响明显大于结构维度和关系维度；企业外部社会资本的三个维度对企业绩效的影响无明显差别.     

A Meta-analysis of Gender Differences in Attitudes Toward Seeking Professional Psychological Help

Abstract

Objective: The present study aims to examine gender differences in attitudes toward professional psychological help–seeking behavior and how gender differences could be affected by other cultural factor such as race. Participants: The authors selected studies that involved undergraduate and graduate students as samples, making the total number of participants in this meta-analysis 5,713. Methods: Statistical procedures were administrated by the MIX (Meta-analysis with Interactive eXplanations) program, which does meta-analyses. Results and Conclusions: The results indicated that gender itself was a significant predictor on attitudes toward seeking professional psychological help. In addition, individual's cultural background (eg, Western versus non-Western ethnicity) moderated the gender differences on attitudes toward seeking professional psychological help. Practical implications for mental health professionals in college settings were discussed.     

基于元分析的上市公司治理与关联交易关系研究

上市公司治理与关联交易关系的研究一直是我国学者所关注的热点问题。采用定性分析和定量分析相结合的元分析方法,对2004—2011年关于上市公司治理与关联交易关系的实证研究文献进行二次统计分析。元分析的结果显示,控股股东持股比例、董事会规模与关联交易之间呈正相关关系,独立董事比例与关联交易之间呈负相关关系。     

基于元分析的新生代农民工心理健康研究

文章采用元分析方法对2007—2015年间使用SCL-90量表研究新生代农民工心理健康的文献进行系统评价,共20篇研究报告纳入分析?研究结果发现,合并效应量波动范围在0.144~0.328,新生代农民工心理健康水平低于全国常模,但是没有预期严重?焦虑和恐怖两个因子最为突出,在研究跨度时间内心理健康水平稳定?男性农民工和女性农民工心理健康水平没有差异,婚姻因素对心理健康水平没有影响?不同地域农民工的心理健康水平差异明显,内陆地区农民工心理健康状况比沿海地区差?     

我国研究生心理健康状况的横断历史研究

搜集1998—2013年间使用SCL-90量表考察研究生心理健康的研究报告64篇,采用横断历史研究的方法探讨研究生心理健康随年代的变化趋势。结果发现,研究生心理健康水平整体逐渐提升。强迫、人际关系、抑郁、焦虑、敌对、偏执和精神病性七个方面有明显改善。群体之间存在差异:重点大学研究生SCL-90的9个因子皆与年代显著负相关,其心理健康水平的改善比普通大学幅度更明显、维度更全面;男生整体心理健康水平略优于女生,虽在变迁的轨迹上有各自的特点,但总体差异不显著,二者抑郁和偏执的改善程度较明显;医学相关专业研究生心理健康水平提升缓慢,只有部分因子有所改善。