期刊名称：Tutorials in Quantitative Methods for Psychology
电子版ISSN：1913-4126
出版年度：2009
卷号：05
期号：2
页码：40-50
DOI：10.20982/tqmp.05.2.p040
出版社：Université de Montréal
摘要：Most psychological research employs tables to report descriptive and inferential statistics. Unfortunately, those tables often misrepresent critical information on the shape and variability of the data’s distribution. In addition, certain information such as the modality and score probability density is hard to report succinctly in tables and, indeed, not reported typically in published research. This paper discusses the importance of using graphical techniques not only to explore data but also to report it effectively. In so doing, the role of exploratory data analysis in detecting Type I and Type II errors is considered. A small data set resembling a Type II error is simulated to demonstrate this procedure, using a conventional parametric test. A potential analysis routine to explore data is also presented. The paper proposes that essential summary statistics and information about the shape and variability of data should be reported via graphical techniques.
关键词：Statistics; Exploratory data analysis; Box plot; Confidence intervals; Violin plot
