명상도서관
Mindful Machine Learning: Using Machine Learning Algorithms to Predict the Practice of Mindfulness
자세히보기
- 자료유형학술지논문
- 저자명Sauer, Sebastian,Buettner, Ricardo,Heidenreich, Thomas,Lemke, Jana,Berg, Christoph,Kurz, Christoph
- 학회/출판사/기관명HOGREFE & HUBER PUBLISHERS
- 출판년도2018
- 언어영어
- 학술지명/학위논문주기EUROPEAN JOURNAL OF PSYCHOLOGICAL ASSESSMENT
- 발행사항Vol.34No.1[2018]_x000D_
- ISBN/ISSN1015-5759
- 소개/요약Mindfulness refers to a stance of nonjudgmental awareness of present-moment experiences. A growing body of research suggests that mindfulness may increase cognitive resources, thereby buffering stress. However, existing models have not achieved a consensus on how mindfulness should be operationalized. As the sound measurement of mindfulness is the foundation needed before substantial hypotheses can be supported, we propose a novel way of gauging the psychometric quality of a mindfulness measurement instrument (the Freiburg Mindfulness Inventory; FMI). Specifically, we employed 10 predictive algorithms to scrutinize the measurement quality of the FMI. Our criterion of measurement quality was the degree to which an algorithm separated mindfulness practitioner from nonpractitioners in a sample of N = 276. A high predictive accuracy of class membership can be taken as an indicator of the psychometric quality of the instrument. In sum, two findings are of interest. First, over and above some items of the FMI were able to reliably predict class membership. However, some items appeared to be uninformative. Second, from an applied methodological point of view, it appears that machine learning algorithms can outperform traditional predictive methods such as logistic regression. This finding may generalize to other branches of research
TOP
사전신청
오시는길
명상챗봇
