The Misuse of Statistics: Concepts,Tools, and a Research Agenda

This paper presents concerns regarding misuse of statistics in scientific work, especially in biomedical research. The paper discusses what is meant by "misuse." It appears that misuse arises from various sources: degrees of competence in statistical theory and methods, honest error in the application of methods, egregious negligence, and deliberate deception (misconduct.) The incidence of error is partly due to a perceived need to meet artificial statistical criteria for acceptance of research reports for publication by journals. There has been no systematic research into the prevalence of misuse or its breakdown by type. Nonetheless, there are ways to encourage, or even to enforce, good statistical practice. These can be greatly supported by use of available statistical ethics documents. This article suggests lines of further research that could define the problem more explicitly and that might lead to additional corrective measures.     

Statistics,ethics, and research: An agenda for education and reform

This essay argues that the research community needs to pay more attention to the appropriate use of statistical methods in discussions of research ethics, and proposes some strategies for enhancing discussions of the ethical uses of statistics within investigational, educational, and organizational settings. The essay supports its position by 1) explaining why statistics plays such a key role in research integrity, 2) describing how some common misuses of statistics in research violate ethical standards pertaining to honesty and error avoidance, and 3) reviewing evidence which suggests that the misuse of statistics is more prevalent (and perhaps more significant) than research misconduct (narrowly defined as “fabrication, falsification, or plagiarism").     

Psychological Malpractice and the Anti-Cult Battle: The Brain Awash

This paper looks at the appearance in Australia of ‘deprogramming’ (brainwashing) methods and the misuse of psychological techniques against cults. It is suggested that the misuse of such techniques is more dangerous and constitutes a greater threat to civil liberties than the cults themselves, and possibilities for action by psychologists are discussed.     

Statistical quantifiers in observational calculi: An application in GUHA-methods

GUHA or general unary hypotheses automaton aims at generating automatically all relevant statements and generalizations about a field of research, for example, a chosen empirical field of social research. For that reason the concept of observational calculi and their relation to the theoretical level of social research is discussed. A statistical generalization of the observational calculus, statistical inference rules and ten generalized statistical quantifiers are defined and discussed. After this formal outline of the theory of GUHA methods, some applications of statistical quantifiers in GUHA methods are discussed. Finally, a bibliography of GUHA methods concludes the paper.     

A family affair? Kinship care and parental substance misuse: some dilemmas explored

Both the Children Act 1989 and the Human Rights Act 1998 support the principle that children should remain within their birth families wherever possible and that this option must be considered when children are unable to live with their parents. Where parental substance misuse is an issue, family placements, whether formally or informally arranged, are increasingly being used and the support of grandparents, in particular, has been identified as a significant protective factor for children. This paper examines some of the issues that can arise with such placements, particularly in view of the part that substance misuse may play within the wider family system, the impact of parental drug and alcohol use on attachment and child development, and the complex dynamics that can ensue. Drawing on themes emerging from parental substance misuse literature and kinship care research, some practice dilemmas will be explored. While acknowledging the complex aetiology of substance misuse and the dangers of pathologizing family systems in which it is found, some hypotheses about potential risks and challenges will be debated. It will be argued that, although such placements can often provide children with a safe haven, they may demand a specific type of support and monitoring, if children’s welfare is to be safeguarded.     

Children living with parental substance misuse: A cross‐sectional profile of children and families referred to children's social care

Parental substance misuse is a significant public health and children's rights issue. In the United Kingdom, social workers frequently work with children and families affected by substance misuse. However, relatively little is known about this population, particularly at point of referral to children's social care. This paper reports on the largest known study of parental substance misuse as a feature of children's social care work in England. The paper provides a cross‐sectional profile of 299 children living with parental substance misuse and referred to children's social care in one local authority in England. Data were collected from social work case files at the point of referral to social care about the child, family, the wider environment, and parental substance misuse. The findings show that children affected by parental substance misuse frequently had other support needs relating to their well‐being and mental health. Children were also likely to be experiencing other parental and environmental risk factors. The significant historical—and in some cases intergenerational—social care involvement for some families indicates potential issues with the capacity of services to meet needs. Recommendations for practice are discussed with a particular focus on the need for early, comprehensive support for children and families.     

Assessing the Importance of Experimental Outcomes

This article discusses a common statistical error that frequently appears in efforts to assess the importance of experimental outcomes in the social work practice and research literature, failure to provide proportions of explained variance in a manner which permits judgements as to their substantive importance or clinical significance. It then briefly describes a partial remedy and presents practical statistical formulas which research consumers can use to calculate proportions of explained variance when published reports fail to provide this information.     

Recognizing Diversity and Group Processes in International, Collaborative Research Work: A Case Study

The myth that most if not all senior researchers who have national prominence can 'successfully' manage international research is alive and well in the academy today. Many researchers believe that research management and consultancy is acquired through a process of trial and error and demands little contemplation or training. The purpose of this paper is to break these myths and to establish various benchmarks for good research management, particularly on an international level. The guiding assumption of the paper is that as research becomes more global, high-quality research management is a necessary resource, which demands sensitivity to diversity as well as an awareness of group processes. This means those issues such as language, race, ethnicity, gender, disability and group work should not only inform our research findings but also guide our research practice in international collaborative settings. Throughout this paper, I use a case study of a large EU-funded project as a way of illustrating key themes.     

Parental substance misuse and child care social work: findings from the first stage of a study of 100 families

Parental misuse of drugs or alcohol is known to be a common issue for child care social workers, yet there has been surprisingly little British research on the topic. The study reported here attempts to address this gap. All files going for long‐term allocation in four London boroughs over on average 1 year were examined (290 files). Parental substance misuse (PSM) emerged as a major feature of social work caseloads. Of the 290 cases, 100 (34%) involved concerns about parental substance misuse. The families involving substance misuse were more vulnerable on a variety of measures: the children were younger, the parents had more individual problems and the families lived in more difficult social situations. PSM cases tended to be ‘heavy end’ at the point of allocation: they accounted for 62% of all children subject to care proceedings and 40% of those placed on the child protection register. There was a fairly even spread between alcohol and drug misuse, and a number of cases involved both. Substance misuse specialists were rarely involved in working with families, primarily because parents said that they did not think that they had a problem. Suggestions for ways in which policy and practice with PSM might be improved are made in light of these findings.     

Did how we learn affect what we learn?: Methodological bias,multimethod research and the case of economic development

This article explores the question of “did how we learn affect what we learn in social science?” through a case study of economic development research. Total dependence on a single method can be a dangerous practice as the method may dictate research findings and make it impossible to eliminate the rival hypothesis of methodological bias. When the multimethod approach is preferred, a mechanical application of multiple methods will not make it better than a single method approach. Using the case of state and local economic development studies, this article illustrates the promise of multimethod research and the danger of its misuse. Poor implementation of the approach can create equally misleading findings and a false sense of confidence in our theories. Among other factors identified in the article, a major key to its successful implementation is having researchers well trained in multiple methods.     

统计模型的“不确定性”问题:与倾向值方法

量化社会学研究往往基于特定的统计模型展开。近十几年来日益流行的倾向值方法也不例外，其在实施过程中需要同时拟合估计倾向值得分的“倾向值模型”与估计因果关系的“结果模型”。然而，无论是其模型形式还是系数估计，统计模型本身都具有不可忽视的“不确定性”问题。本研究在倾向值分析方法的框架下，系统梳理和阐释了模型形式不确定性与模型系数不确定性的内涵及其处理方法。通过分析“蒙特卡洛模拟”数据与经验调查数据，本文展示了在使用倾向值方法进行因果估计的过程中，研究者如何通过“贝叶斯平均法”进行多个备选倾向值模型的选择，以及如何通过联合估计解决倾向值模型与估计模型中的系数不确定性问题。本文的研究也表明，在考虑倾向值估计过程的不确定性之后，结果模型中对于因果关系的估计呈现更小的置信区间和更高的统计效率。     

Critical Realism,Dialectics, and Qualitative Research Methods

Critical realism has been an important advance in social science methodology because it develops a qualitative theory of causality which avoids some of the pitfalls of empiricist theories of causality. But while there has been ample work exploring the relationship between critical realism and qualitative research methods there has been noticeably less work exploring the relationship between dialectical critical realism and qualitative research methods. This seems strange especially since the founder of the philosophy of critical realism, Roy Bhaskar, employs and develops a range of dialectical concepts in his later work in order to extend the main tenets of critical realism. The aim of this paper is to draw on Bhaskar's later work, as well as Marxism, to reorient a critical realist methodology towards a dialectical approach for qualitative research. In particular, the paper demonstrates how dialectical critical realism can begin to provide answers to three common criticisms made against original critical realist methodology: that the qualitative theory of causal powers and structures developed by critical realists is problematic; that critical realist methodology contains values which prove damaging to empirical research; and that critical realists often have difficulties in researching everyday qualitative dilemmas that people face in their daily lives.     

Living with an elephant: Growing up with parental substance misuse

Although parental substance misuse is now a focus of concern in child welfare practice, we know little about what it is really like for children who grow up in families where adult drug and/or alcohol use is an issue. Set against a backdrop of research links between parental substance misuse and child maltreatment, this article examines a number of studies that focus on the experiences of children and young people in this context. Emerging themes are identified which provide insight into the world of children for whom a substance is, effectively, a family member –‘the elephant in the living room’– and the implications for practice, particularly in relation to children's visibility, disclosure and confidentiality, are considered. It is argued that a focus on the ‘elephant’ often leads to children remaining ‘invisible’ to those whose role it is to ensure their welfare.     

Misconduct versus honest error and scientific disagreement

Researchers sometimes mistakenly accuse their peers of misconduct. It is important to distinguish between misconduct and honest error or a difference of scientific opinion to prevent unnecessary and time-consuming misconduct proceedings, protect scientists from harm, and avoid deterring researchers from using novel methods or proposing controversial hypotheses. While it is obvious to many researchers that misconduct is different from a scientific disagreement or simply an inadvertent mistake in methods, analysis or misinterpretation of data, applying this distinction to real cases is sometimes not easy. Because the line between misconduct and honest error or a scientific dispute is often unclear, research organizations and institutions should distinguish between misconduct and honest error and scientific disagreement in their policies and practices. These distinctions should also be explained during educational sessions on the responsible conduct of research and in the mentoring process. When researchers wrongfully accuse their peers of misconduct, it is important to help them understand the distinction between misconduct and honest error and differences of scientific judgment or opinion, pinpoint the source of disagreement, and identify the relevant scientific norms. They can be encouraged to settle the dispute through collegial discussion and dialogue, rather than a misconduct allegation.     

Misconduct versus Honest Error and Scientific Disagreement

Researchers sometimes mistakenly accuse their peers of misconduct. It is important to distinguish between misconduct and honest error or a difference of scientific opinion to prevent unnecessary and time-consuming misconduct proceedings, protect scientists from harm, and avoid deterring researchers from using novel methods or proposing controversial hypotheses. While it is obvious to many researchers that misconduct is different from a scientific disagreement or simply an inadvertent mistake in methods, analysis or misinterpretation of data, applying this distinction to real cases is sometimes not easy. Because the line between misconduct and honest error or a scientific dispute is often unclear, research organizations and institutions should distinguish between misconduct and honest error and scientific disagreement in their policies and practices. These distinctions should also be explained during educational sessions on the responsible conduct of research and in the mentoring process. When researchers wrongfully accuse their peers of misconduct, it is important to help them understand the distinction between misconduct and honest error and differences of scientific judgment or opinion, pinpoint the source of disagreement, and identify the relevant scientific norms. They can be encouraged to settle the dispute through collegial discussion and dialogue, rather than a misconduct allegation.     

One Person—No Vote; One Vote; Two Votes: Voting Methods, Ballot Types, and Undervote Frequency in the 2000 Presidential Election

Objectives . Political science long ignored the actual mechanics of voting—until the 2000 presidential contest. This research note offers a systematic empirical inquiry into the potential effects of various voting methods and electorate–specific variables on the rate at which citizens register a preference via the act of voting. Methods . Voting methods were analyzed in relation to the rate of undervotes recorded in Georgia's 159 counties during the 2000 general election using a set of multivariate models. Results . Lever machines and fill in the oval optical scan ballots are associated with lower rates of undervoting. Counties with large numbers of new registrants, lower education levels, and a higher proportion of African–American voters were found to have higher error rates. Conclusions . The results of this study provide strong evidence that voting methods and ballot types, as well as electorate–specific characteristics, are key factors in determining the error rate associated with the process of voting at the county level.     

从实证视角理解个案研究:三阶段考察渠文的方法创新

本文尝试对话渠敬东“迈向社会全体的个案研究”一文：一方面通过实证视角，就渠文进行爬梳与理解，盼激发更多跨界对话；另一方面针对方法应用，自该文提炼策略与建议，盼有助催生具体的研究策略。基于上述目的，本文将“从个案到全体”的历程划分为三个阶段：选择个案、研究个案、推论个案，藉以条理渠文丰富多彩的方法论述。讨论过程中就渠文提示的个案研究途径与传统实证和诠释路径并列对照，帮助说明渠文创新所在。在总的方向上，本文与渠文一致，一方面力图论证个案研究的价值，尝试勾勒出规范、系统的个案方法；另一方面尝试通过个案研究对话，使实证阵营能够理解、欣赏诠释阵营的研究思路与丰厚内涵。     

罚似然图模型与社会网络测量

随着互联网及智能设备的普及，越来越多的用户行为轨迹和互动数据的获得成为可能并进入社会学研究者的视野。这类行为或互动事件的数据在数据结构上属于社会网络分析方法中常见的双模网络。但传统的社会网络分析所面对的数据规模较小，研究者一般采用矩阵分解、主成分分析等描述性分析方式来对网络子群进行区分或测量。而在大数据的背景下，参与互动的群体规模巨大、群体成员的构成动态变化、事件具有时序特征、事件发生存在异质性等特征，使得传统的分析方法无法有效应对此类数据。 近十年来，高维高斯图模型在网络关系探测研究中被广泛应用。本文拟对基于罚似然回归的高斯图模型进行综述。罚似然高斯图模型是一个发展迅速的分析工具，本文并不侧重具体的算法和优化过程，而是就罚似然图模型及其扩展模型对社会科学应用研究可能带来的贡献进行梳理。最后，本文亦对涉及的相关模型及其R软件包进行汇总，以期拓展该方法在社会科学领域的应用。     

对美欧学者关于邻里效应研究的述评

文章回顾、评论了美欧学者对于邻里效应作用机制和研究方法的归纳、邻里效应研究方法面临的挑战以及具体的经验研究和实践。文章指出,邻里效应有助于减少社会差别、促进社会平等,这在理论和实践上都能得到说明。如果要采取某种混合居住的政策以帮助社会下层并降低住房不平等以及总的社会不平等程度,那么现行住房政策将不得不做出改进。具体说来,可以考虑采取渐进式的改革：配合户籍制度改革,逐步把少数常年在城市打工、表现良好的农民工纳入经济适用房和廉租房等制度的照顾范围以内。同时本文希望抛砖引玉,激发社会学界乃至于社会科学界住房和城市问题研究者更多关注于邻里效应和社会不平等研究。