一款用于进行单因素方差分析事后检验的新软件。

A new software for carrying out one-way ANOVA post hoc tests.

作者信息

Brown Angus M

机构信息

Department of Neurology, Box 356465, University of Washington School of Medicine, Seattle, WA 98195, USA.

出版信息

Comput Methods Programs Biomed. 2005 Jul;79(1):89-95. doi: 10.1016/j.cmpb.2005.02.007.

DOI:10.1016/j.cmpb.2005.02.007

PMID:15963357

Abstract

The objective of this study was to develop a convenient, easy to use stand-alone program to statistically process experimental data. The method involves user input of data for analysis into a grid format, followed by one-way analysis of variance (ANOVA) of the data to determine the F ratio. If the value of the F ratio is greater than the appropriate critical F distribution at alpha=0.05, the null hypothesis is rejected, it is assumed that at least one of the group means is significantly different from the other group means, and it is valid to proceed with post hoc testing. A choice of four post hoc tests are available: Dunnett's, Fisher's, Scheffé's or Tukey's. The results of the post hoc test are displayed and can be printed for record keeping. The methodology developed in this present study should help scientists to carry out post hoc comparisons quickly and easily without the expense or time that commercial statistical packages require.

摘要

本研究的目的是开发一个方便、易用的独立程序，用于对实验数据进行统计处理。该方法包括用户将用于分析的数据以网格格式输入，然后对数据进行单向方差分析（ANOVA）以确定F比率。如果F比率的值大于α = 0.05时适当的临界F分布，则拒绝原假设，假定至少有一组均值与其他组均值存在显著差异，进而进行事后检验是有效的。有四种事后检验可供选择：邓尼特检验、费舍尔检验、谢费检验或图基检验。事后检验的结果会显示出来，并可打印出来用于记录保存。本研究中开发的方法应有助于科学家快速、轻松地进行事后比较，而无需商业统计软件包所需的费用和时间。