Zen and the art of reporting differences in data that are not statistically significant

Professional communicators reporting the results of experiments often need to express the fact that the differences in the data were not statistically significant and that the null hypothesis could not be rejected. It is suggested that communicators may find it difficult to express these results par...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on professional communication 1993-06, Vol.36 (2), p.75-80
Hauptverfasser:	Battle, M.V., Rakow, E.A.
Format:	Artikel
Sprache:	eng
Schlagworte:	Communication Exact sciences and technology Experiments Hypotheses Information and communication sciences Information science. Documentation Library and information science. General aspects Logic Probability Sciences and techniques of general use Statistical methods Statistics Subspace constraints Terminology Theories, definitions and sources in information science Writing
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Professional communicators reporting the results of experiments often need to express the fact that the differences in the data were not statistically significant and that the null hypothesis could not be rejected. It is suggested that communicators may find it difficult to express these results partly because failing to reject a null hypothesis is not the same as accepting a null hypothesis. Writers may report failing to reject a null hypothesis in any of five ways: directly and briefly; directly with the exact level of statistical probability stated; directly with the confidence interval specified; directly with an explanation of not claiming causation; and directly with a discussion of possible reasons.< >
ISSN:	0361-1434 1558-1500
DOI:	10.1109/47.222685