Towards a flexible online mixed method design with a feedback loop

The notion of mixed methods design relates to the research studies that combine qualitative and quantitative approaches. However, most of these studies are tailored to specific research problem in a particular study and are typically limited to a fixed sequence of qualitative and quantitative approaches (e.g. qualitative interviews followed by a survey or vice-versa). This limitation historically arises from time, cost and logistic restrictions. As an alternative, we develop an general extension of fixed mixed method design by introducing a flexible feedback-loop so that several phases can be combined in a flexible order. In practice, such designs are now increasingly feasible within an information-communication technology environment, where online respondents are readily available for immediate participation. An online experiment combining interactive series of web surveys and in-depth web interviews was performed to compare this approach with standard two-phase designs involving mixed methods. The costs, timing, quality of finiding and experiences of researchers were systematically evaluated. In summary, the proposed approach proved to be very beneficial.     

The use of mixed methods research in the field of behavioural sciences

Mixed methods research involves the combined use of quantitative and qualitative methods in the same research study, and it is becoming increasingly important in several scientific areas. The aim of this paper is to review and compare through a mixed methods multiple-case study the application of this methodology in three reputable behavioural science journals: the Journal of Organizational Behavior, Addictive Behaviors and Psicothema. A quantitative analysis was carried out to review all the papers published in these journals during the period 2003–2008 and classify them into two blocks: theoretical and empirical, with the latter being further subdivided into three subtypes (quantitative, qualitative and mixed). A qualitative analysis determined the main characteristics of the mixed methods studies identified, in order to describe in more detail the ways in which the two methods are combined based on their purpose, priority, implementation and research design. From the journals selected, a total of 1,958 articles were analysed, the majority of which corresponded to empirical studies, with only a small number referring to research that used mixed methods. Nonetheless, mixed methods research does appear in all the behavioural science journals studied within the period selected, showing a range of designs, where the sequential equal weight mixed methods research design seems to stand out.     

QUALITATIVE AND MIXED‐METHODS RESEARCH IN ECONOMICS: SURPRISING GROWTH,PROMISING FUTURE

Qualitative research in economics has traditionally been unimportant compared to quantitative work. Yet there has been a small explosion in use of quantitative approaches in the past 10–15 years, including ‘mixed‐methods’ projects which use qualitative and quantitative methods in combination. This paper surveys the growing use of qualitative methods in economics and closely related fields, aiming to provide economists with a useful roadmap through major sets of qualitative methods and how and why they are used. We review the growing body of economic research using qualitative approaches, emphasizing the gains from using qualitative‐ or mixed‐methods over traditional ‘closed‐ended’ approaches. It is argued that, although qualitative methods are often portrayed as less reliable, less accurate, less powerful and/or less credible than quantitative methods, in fact, the two sets of methods have their own strengths, and how much can be learned from one type of method or the other depends on specific issues that arise in studying the topic of interest. The central message of the paper is that well‐done qualitative work can provide scientifically valuable and intellectually helpful ways of adding to the stock of economic knowledge, especially when applied to research questions for which they are well suited.     

Integrating quality into quantity: survey research in the era of mixed methods

As widely recognized during the golden age of survey research thanks to the work of the Columbia school, the use of mixed strategies allows survey research to overcome its limitations by incorporating the advantages of qualitative approaches rather than seeking alternative methods. The need to re-think survey research before embarking on this course impelled the author to undertake a critical analysis of one of the survey’s most important assumptions, proposing a shift from standardization of stimulus to standardization of meanings in order to anchor the requirement of answer comparability on a more solid basis. This proposal for rapprochement with qualitative research is followed by a more detailed section in which the author distinguishes four different types of mixed survey strategies, combining two criteria (time order and function of qualitative procedures). The most significant parts of the constructed typology are then brought together in a model called the multilevel integrated survey approach. This methodological model is concretely illustrated in an empirical study of homophobic prejudice among teenagers. The example shows how in research practice analytical mixed strategies can be creatively combined in the same survey research design, contributing to improvements in data quality and the relevance of research findings.     

基于层次分析及模糊综合评价的电子政务网站评价

本文建立电子政务网站评价指标体系,结合专家打分,利用层次分析法计算出每项评估指标相应权重,通过对用户进行问卷调查,采用模糊综合评价法对上海市政府门户网站进行了实证研究及评价,得出了公众对其满意度的评价结果。     

Qualitative Research in the Service of Understanding Learners and Users of Statistics

This paper seeks to add to a scholarly dialogue regarding the role and value of qualitative techniques in research on learning and using statistics. The paper briefly outlines some of the core assumptions of qualitative research methods, and presents four examples to illustrate selected qualitative methods that are used by educational researchers and service organizations. The discussion emphasizes the need to integrate quantitative and qualitative approaches in research on learners and users of statistics, and suggests that such integration may be needed to study emerging web-based communities of learners and users of statistics.     

珠三角经济区域港口物流与区域经济协调发展实证分析

运用定性与定量相结合的方法,在分析区域港口物流对区域经济发展的作用与影响的基础上,对珠三蜀经;齐区域港口物流与区域增长的关系进行数量经济分析．探寻港口物流与区域经济发展的关系及规律,以利于正确认识区域港口物流能力建设如何适应区域经济增长需要、与区域经济发展水平协调匹配。     

Use of mixed methods designs in substance research: a methodological necessity in Nigeria

The utility of mixed methods (qualitative and quantitative) is becoming increasingly accepted in health sciences, but substance studies are yet to substantially benefit from such utilities. While there is a growing number of mixed methods alcohol articles concerning developed countries, developing nations are yet to embrace this method. In the Nigerian context, the importance of mixed methods research is yet to be acknowledged. This article therefore, draws on alcohol studies to argue that mixed methods designs will better equip scholars to understand, explore, describe and explain why alcohol consumption and its related problems are increasing in Nigeria. It argues that as motives for consuming alcohol in contemporary Nigeria are multiple, complex and evolving, mixed method approaches that provide multiple pathways for proffering solutions to problems should be embraced.     

The distinction between qualitative and quantitative research methods is problematic

The distinction between qualitative and quantitative research is abstract, very general and its value is usually taken for granted. In contrast, this article attempts to show that the distinction between qualitative and quantitative research is unclear, poor and therefore of limited value and that its popularity risks leading to unfortunate consequences. Various arguments are presented for this conclusion. For example, it is argued that the heterogeneity of different stand-points on important issues among qualitative researchers (for example with respect to the use of quantification and causal analysis) makes the distinction as such unstable. Moreover, the presence of substantial overlap between many features of qualitative and quantitative research often makes it difficult to separate qualitative and quantitative research. It is also shown that three obvious ways of making the distinction between qualitative and quantitative research are unsatisfactory. Use of the distinction may restrict creativity in the development of new research methods and create confusion and unnecessary work. In general, it may be preferable not to conceptualize research approaches at such abstract levels as done in the context of qualitative or quantitative approaches. Instead, it is suggested that it is more fruitful to discuss the pros and cons of specific research methods, preferably in the context of specific research problems.     

Integrating Quantitative and Qualitative Analysis Using Latent and Manifest Variables

The relative virtues of quantitative and qualitative research have been vigorously debated. Several researchers recommend combining methodologies but there is little evidence in the literature to suggest how different research methods might be integrated (Bryman, 1988). The current study addresses this deficiency in the research by examining the use of latent variables in quantitative and qualitative research as a means of blending the two approaches. A study of entrepreneurial Locus of Control where quantitative and qualitative data were available illustrates the methodological issues. Analysis of quantitative data was conducted using LISREL (7.20) and qualitative data were categorised using NUD.IST (Non-numerical Unstructured Data Indexing Searching and Theorising computer software). Detailed comparisons are made between the methods described in this paper and other approaches to content analysis.     

Software as a facilitator of quality processes in social sciences research

The objective of this work is to evaluate the strategy of triangulation in the validation of information by integrating quantitative/qualitative information based on the use of different statistics software packages In our case, we opted to begin with a quantitative strategy and use IBM SPSS AMOS Statistics; we then replicated the study with a qualitative strategy using NVIVO. To this end, we used as an example case a study conducted on a sample of 445 university teaching personnel regarding intentions to use the blended learning teaching model in their usual teaching practice. We did so to analyse the extent to which it is possible to explain the process of adopting this educational method as well as its use and its dissemination in higher-education contexts, taking as a theoretical reference the Unified Theory of Acceptance and Use of Technology and the Theory of Diffusion of Innovation, proposed by E. Rogers. The analyses carried out verified the convergence or overlap of the results obtained after the application of different methods of data collection (a questionnaire and interviews) for the same study object. The results confirm the benefit of using data-processing software as a resource to facilitate multimethod strategies in educational research owing to its strengthening of results and the examination of the level of convergence or divergences within them.     

Dynamic institutional analysis: measuring corporatist intermediation

In this paper a framework for empirical analysis is introduced that allows for a dynamic analysis of the interactions between different types of actors and institutions. We elaborate our argument by focusing on a complex phenomenon—corporatism—to show how this concept can be developed into a measure that travels across nations and time. The heuristic framework we developed adequately captures the interactive behaviour of the relevant actors within a corporatist institutional context. We demonstrate the usefulness of this framework for the analysis of policy formation by applying it to Dutch incomes policy. We contend that this heuristic framework contributes to alleviating the often discussed methodological trade-off between single case studies and cross-national comparisons. We also argue that it can bridge the gap between qualitative and quantitative approaches. Lastly, we propose that it can be used for empirical analysis of policy-making processes in other policy areas.     

高校产学研合作教育的意义及评价

教育、科研、产业三者的结合是历史发展的必然。高校实施产学研合作教育对增强企业竞争力、发展地区经济有显著的推动作用。产学研合作教育的开展需要科学的理论和合理的评价体系。通过层次分析法,可对涉及产学研合作教育各种因素进行分类,建立统一的评价指标体系。高校可以结合具体情况,对教育成果进行定性和定量的评估。     

Mixed methods research synthesis: definition, framework, and potential

Literature on the combination of qualitative and quantitative research components at the primary empirical study level has recently accumulated exponentially. However, this combination is only rarely discussed and applied at the research synthesis level. The purpose of this paper is to explore the possible contribution of mixed methods research to the integration of qualitative and quantitative research at the synthesis level. In order to contribute to the methodology and utilization of mixed methods at the synthesis level, we present a framework to perform mixed methods research syntheses (MMRS). The presented classification framework can help to inform researchers intending to carry out MMRS, and to provide ideas for conceptualizing and developing those syntheses. We illustrate the use of this framework by applying it to the planning of MMRS on effectiveness studies concerning interventions for challenging behavior in persons with intellectual disabilities, presenting two hypothetical examples. Finally, we discuss possible strengths of MMRS and note some remaining challenges concerning the implementation of these syntheses.     

多层次模糊综合评判法在企业战略选择中的应用

企业战略选择是个复杂的多层次的决策问题,传统的定性方法已不能很好的满足需要。采用模糊决策方法,建立综合评判的企业战略选择模糊决策模型,综合考量评价系统中的各定性和定量指标,并结合实例验证了该方法的有效性。     

Daily retail demand forecasting using machine learning with emphasis on calendric special days

Demand forecasting is an important task for retailers as it is required for various operational decisions. One key challenge is to forecast demand on special days that are subject to vastly different demand patterns than on regular days. We present the case of a bakery chain with an emphasis on special calendar days, for which we address the problem of forecasting the daily demand for different product categories at the store level. Such forecasts are an input for production and ordering decisions. We treat the forecasting problem as a supervised machine learning task and provide an evaluation of different methods, including artificial neural networks and gradient-boosted decision trees. In particular, we outline and discuss the possibility of formulating a classification instead of a regression problem. An empirical comparison with established approaches reveals the superiority of machine learning methods, while classification-based approaches outperform regression-based approaches. We also found that machine learning methods not only provide more accurate forecasts but are also more suitable for applications in a large-scale demand forecasting scenario that often occurs in the retail industry.     

算术四则运算智能测试教学软件的设计

采用UML建模和ActionScript技术,为小学数学的加减乘除四则运算设计制作了一种能随机出题、交互解答、智能评测、图音并茂的教学软件。该教学软件克服了传统多媒体教学软件缺乏交互性、随机性的缺点。该软件既可用作小学数学课堂教学,也可放到网页里让学生们自行测试练习。     

Generalization practices in qualitative research: a mixed methods case study

The purpose of this mixed methods case study was to examine the generalization practices in qualitative research published in a reputable qualitative journal. In order to accomplish this, all qualitative research articles published in Qualitative Report since its inception in 1990 (n =  273) were examined. A quantitative analysis of the all 125 empirical qualitative research articles revealed that a significant proportion (i.e., 29.6%) of studies involved generalizations beyond the underlying sample that were made inappropriately by the author(s). A qualitative analysis identified the types of over-generalizations that occurred, which included making general recommendations for future practice and providing general policy implications based only on a few cases. Thus, a significant proportion of articles published in Qualitative Report lack what we call interpretive consistency.     

A common base for quality control criteria in quantitative and qualitative research

In the social sciences, several scientific paradigms are mutually isolated owing to their use of specific sets of methodological criteria and quality control procedures. In this article, the central hypothesis, to be tested by conceptual analysis and logical reasoning, is that recommended procedures for quality control in quantitative as well as qualitative research can be derived from a common base of regulative ideas. By ‘qualitative’, we mean the complex of ethnographic, anthropological, symbolic interactionist, ethnoscience and related approaches. A second goal is to demonstrate the use of regulative ideas as a parsimonious and fruitful base for a comparative analysis of methodological canons. Although our focus is on the comparison of quantitative and qualitative (or: naturalistic) research, we also pay attention to policy research as opposed to fundamental research.     

Empirical research consolidation: a generic overview and a classification scheme for methods

I define research consolidation as comparing and combining (amalgamating or, at least, juxtaposing) results or other output from multiple previously conducted research activities, relevant to a goal or topic of interest. The concept, not limited to empirical research or any specific method, is similar to and subsumes what is often referred to as research synthesis or research integration; I explain the concept and my rationale for the new term. After introducing the broader concept, I focus on consolidation of empirical research. As background for this, I offer a brief introduction to empirical research. Then I provide a generic overview of empirical research consolidation, abstracted from several of its specific methods, such as quantitative meta-analysis and qualitative meta-synthesis; this sort of overview—method agnostic and capturing the commonality—is not readily available in the literature. At the core of the paper, I propose a scheme to classify methods for empirical research consolidation followed by a review and classification of selected methods, illustrating the scheme. I also discuss and clarify related terminology. The classification scheme differentiates between two major attributes of methods—consolidation technique and type of content to be consolidated—that may reflect the positivist or constructivist research paradigm. Consolidation techniques could be aggregative, interpretive, or a combination thereof. Content consolidated, from empirical research reports, could be empirical or not and could be from quantitative research, qualitative research, other kinds of empirical research, or a combination thereof.