Inductive Discovery by Machine Learning for Identification of Structural Models

摘要：

　　Automatic extraction of structural models interferes with the deductive research method in information systems research.Nonetheless it is tempting to use a statistical learning method for assessing meaningful relations between structural variables given the underlying measurement model.In this paper,we discuss the epistemological background for this method and describe its general structure.Thereafter this method is applied in a mode of inductive confirmation to an existing data set that has been used for evaluating a deductively derived structural model.In this study,a range of machine learning model classes is used for statistical learning and results are compared with the original model.

关键词： Structural models Machine learning SEM Data science

作者: Wolfgang Maass Iaroslav Shcherbatyi

作者单位: German Research Center for Artificial Intelligence(DFKI),Kaiserslautern,Germany

会议类型: 国际会议

会议名称: The 37th International Conference on Conceptual Modeling(第37届概念建模国际会议(ER2018)

会议地点: 西安

会议语种:英文

页码: 545-552

在线出版日期: 2018-10-22（万方平台首次上网日期，不代表论文的发表时间）