合作问题解决能力测量:真实性与过程性评价视角

Measurement of Collaborative Problem-solving:From Perspective of Authenticity and Process Assessment

合作问题解决能力是一种复杂的高阶技能,其有效测量面临困境。文章遵循真实性与过程性评价理念,尝试建构全新教育测验形式,探索合作问题解决能力有效测量的方法与过程。首先,基于真实性评价理念建构真实任务情境,开发具有真实性、交互性、动态性的测验任务。其次,获取学生在测验任务中的过程性表现,从过程数据中提取有意义的行为模式作为观测指标,以此形成合作问题解决能力的测量证据。再次,鉴于“两人交互”的合作形式和三种观测指标并存的项目结构,应用两维度Rasch模型进行测验分析和估计学生能力。模型拟合结果显示测验项目的MNSQ值处于0.87~1.34之间,项目的整体分离度为0.981,大部分项目的区分度大于0.3,学生能力分布符合一般实际,表明测量模型拟合较好,测验项目质量较高。研究结果说明基于真实任务与过程性测验表现测量合作问题解决能力是一种可行的途径,这种新测验形式对复杂技能的有效测量具有重要借鉴意义。

Collaborative problem-solving is a complex higher-order skill,and its effective measurement is faced with difficulties.Following the concept of authenticity and process assessment,this paper tries to construct a new form of educational test,and explores an effective method and process for the measurement of collaborative problem-solving.Firstly,based on the concept of authentic assessment,authentic task situations are constructed,and test tasks featured authenticity,interaction and dynamics are developed.Secondly,the process performance of students in the test tasks is obtained,and meaningful behavior patterns are extracted from the process data as observation indexes to form the evidence for the measurement of collaborative problem-solving.Thirdly,a two-dimensional Rasch model is used to analyze the test and estimate students'abilities in view of the collaborative form of"two-person interaction"and the project structure with the coexistence of three kinds of observation indicators.The model fit results shows that the MNSQ value of the test items range from 0.87 to 1.34,the overall separation degree of the items is 0.981,and the discrimination of most items is greater than 0.3.The distribution of students'abilities is in line with the general condition,indicating a good fit of the measurement model and a high quality of the test items.The results shows that it is a feasible way to measure collaborative problem-solving based on authentic tasks and procedural test performance,and this new test form could benefit the effective measurement of complex skills.