A blended learning course in quantitative methods for UK sociology, social policy and political science undergraduates.

我们将重新配置和扩展爱丁堡大学的20学分M级混合学习课程“核心定量数据分析”（CQDA），以提供大约60学分的学习资源，供任何英国高等教育机构在知识共享许可下使用，用于培训QM本科生。这些资源可以作为质量管理的完整课程使用（任何英国高等教育学院的本科生都可以使用），或者可以由质量管理教学人员将单个组件集成到现有课程中。CQDA课程已经开发了五年，利用爱丁堡大学电子学习计划的资源，提供质量管理培训，达到ERSC PG通用要求水平。它基于这样一种理念：当学生将质量管理作为解决研究中遇到的问题的一种方法，并通过使用真实数据的反复练习来学习时，他们就能最好地学习质量管理。它遵循Tukey（1977）和Marsh（1982）对数据探索的强调，但包括对推理和假设检验的价值和局限性的批判性讨论。它是高度互动的，使用屏幕动画，视频和问题/反馈测试，要求学生使用真实数据来解决问题，以完成每个模块。本课程旨在向学生展示质量管理的相关性和价值，并给他们在实践中应用质量管理的信心。这门课程的学生群体（每年约150人）取得了进步和优异的成绩，得到了外界的赞扬，学生们也给出了非常积极的反馈。该课程的一个特点是，它允许有限的工作人员集中时间帮助最需要支持的学生。为了最大限度地提高不同课程背景下的可用性，我们将把现有的课程学习资源（由Adobe Dreamweaver和Captivate编写）迁移到一个用户友好的开放访问内容管理系统中，该系统将允许教师和课程组织者以最小的努力重新安排和定制材料以满足他们的特定需求。爱丁堡大学将在其服务器上托管这些资源，供其他高等教育机构的用户下载。我们将为社会学、犯罪学、社会政策和政治学的学生制作新的学科特定内容。我们将重新编写模块，将所有示例和练习基于欧洲社会调查和世界银行教学数据集，这些数据集不需要学生或教师注册即可使用（目前课程使用GHS， BSAS， SSAS和其他数据集）。我们将把课程材料从要使用的软件平台（目前是SPSS）中分离出来，允许课程与SPSS， Stata或r一起使用。我们将在每个模块的末尾添加更大量的自我/导师测试练习，可用于自我或总结性评估。并利用模块内的学习评估练习引导学生学习相关的辅助材料。我们将通过制作关于数据来源、数据可视化和二手数据分析的额外模块，以及通过调整课程材料以适应更广泛的学生能力，使课程内容适应本科水平。这门课程目前的特点之一是，它能够使用网络形式来呈现那些能够吸引较强学生的材料，但那些希望专注于基础知识的较弱学生可以忽略的材料，以及纳入较弱学生需要但较强学生可以跳过的材料。因此，网络学习模块具有在讲座或研讨会形式中难以实现的灵活性。我们会监察学习资料的使用情况，并根据师生的意见进行修订和检讨，并继续维持学习资源伺服器和连结三年。在这段时间结束时，我们将整理和存档这些材料，以便它们继续可供使用。

We will reconfigure and expand University of Edinburgh's 20 credit M level blended learning course 'Core Quantitative Data Analysis' (CQDA) to provide approximately 60 credits worth of learning resources for use under a creative commons license by any UK HEI for training undergraduates in QM. These resources may be used 'off the shelf' as a complete course in QM (and accessible as such by any UK HEI undergraduate), or individual components can be integrated into existing courses by QM teaching staff. The CQDA course has been developed over five years, using resources from an Edinburgh University E-learning initiative, to deliver training in QM up to ERSC PG generic requirements level. It is based on the philosophy that students learn QM best when they are presented as a way of resolving problems encountered in research, and learned by repeated practice using real data. It follows Tukey (1977) and Marsh's (1982) emphasis on data exploration, but includes a critical discussion of inference and the value and limits of hypothesis testing. It is highly interactive, using screen animation, videos and question/feedback tests requiring students to use real data to solve problems in order to complete each module. The course aims to show students the relevance and value of QM, as well as giving them confidence to apply QM in practice. The course has delivered improved and excellent results from the cohorts of students taking it (around 150 each year), praise from externals and extremely positive feedback from students. A feature of the course is the way it allows limited staff time to be concentrated on helping students who need most support.To maximise usability in diverse curriculum contexts, we will migrate the existing course learning resources, authored in Adobe Dreamweaver and Captivate, to a user-friendly open access content management system that will allow teachers and course organisers to rearrange and customise the material to their particular needs with the minimum of effort. Edinburgh will host the resources on its servers, downloadable by users in other HEIs. We will produce new discipline specific content for sociology, criminology, social policy and political science students. We will re-write modules to base all examples and exercises on European Social Survey and World Bank teaching datasets that will not require student or teacher registration for use (currently the course uses GHS, BSAS, SSAS and other datasets). We will separate the course material from the software platform to be used (currently SPSS) allowing the course to be used with SPSS, Stata or R. We will add a much larger volume of self/tutor test exercises at the end of each module which may be used for either self- or summative assessment, and use learning assessment exercises within modules to route students through relevant support materialWe will adapt the course content to undergraduate level by producing additional modules on sources of data, on data visualisation, and on secondary data analysis, and by adapting the course materials to a wider range of student abilities. One of the current features of the course is its ability to use its web format to present material that will engage stronger students, but which can safely be ignored by weaker students wishing to concentrate on the basics, and to incorporate material that weaker students require but which stronger students can skip past. The web learning modules thus have a flexibility that is difficult to achieve in lecture or seminar formats. We will monitor the use of the learning materials, revise and review them in the light of teachers' and students' feedback, and continue to maintain the learning resources server and links for three years. At the end of this period we will curate and archive the materials so that they continue to be available for use.