Validity, reliability, and significance

• Verfasst von: Riezler, Stefan [VerfasserIn]
• Verfasst von: Hagmann, Michael [VerfasserIn]
• Titel: Validity, reliability, and significance
• Titelzusatz: empirical methods for NLP and data science
• Verf.angabe: Stefan Riezler, Michael Hagmann
• Verlagsort: San Rafael, CA
• Verlag: Morgan & Claypool Publishers
• E-Jahr: 2022
• Jahr: [2022]
• Umfang: xvii, 165 Seiten
• Illustrationen: Illustrationen, Diagramme
• Gesamttitel/Reihe: Synthesis lectures on human technologies ; #55
• ISBN: 978-1-63639-271-4
• ISBN: 978-1-63639-273-8
• DOI: doi:10.2200/S01137ED1V01Y202110HLT055
• Sprache: eng
• Bibliogr. Hinweis: Erscheint auch als : Online-Ausgabe: Riezler, Stefan: Validity, Reliability, and Significance. - San Rafael : Morgan & Claypool Publishers, 2022. - 1 online resource (165 pages)
• K10plus-PPN: 1780936990

Abstract

Empirical methods are means to answering methodological questions of empirical sciences by statistical techniques. The methodological questions addressed in this book include the problems of validity, reliability, and significance. In the case of machine learning, these correspond to the questions of whether a model predicts what it purports to predict, whether a model's performance is consistent across replications, and whether a performance difference between two models is due to chance, respectively. The goal of this book is to answer these questions by concrete statistical tests that can be applied to assess validity, reliability, and significance of data annotation and machine learning prediction in the fields of NLP and data science.