Jankowski Katherine R B, Flannelly Kevin J, Flannelly Laura T
a Iona College , New Rochelle , New York , USA.
b Center for Psychosocial Research , Massapequa , New York , USA.
J Health Care Chaplain. 2018 Jan-Mar;24(1):30-39. doi: 10.1080/08854726.2017.1335050. Epub 2017 Jun 16.
The t-test developed by William S. Gosset (also known as Student's t-test and the two-sample t-test) is commonly used to compare one sample mean on a measure with another sample mean on the same measure. The outcome of the t-test is used to draw inferences about how different the samples are from each other. It is probably one of the most frequently relied upon statistics in inferential research. It is easy to use: a researcher can calculate the statistic with three simple tools: paper, pen, and a calculator. A computer program can quickly calculate the t-test for large samples. The ease of use can result in the misuse of the t-test. This article discusses the development of the original t-test, basic principles of the t-test, two additional types of t-tests (the one-sample t-test and the paired t-test), and recommendations about what to consider when using the t-test to draw inferences in research.
由威廉·S·戈塞特开发的t检验（也称为学生t检验和双样本t检验）通常用于比较一个样本在某一测量指标上的均值与另一个样本在同一测量指标上的均值。t检验的结果用于推断样本彼此之间的差异程度。它可能是推断性研究中最常被依赖的统计方法之一。它易于使用：研究人员可以用三种简单工具计算该统计量：纸、笔和计算器。计算机程序可以快速为大样本计算t检验。易用性可能导致t检验被误用。本文讨论了原始t检验的发展、t检验的基本原理、另外两种t检验类型（单样本t检验和配对t检验），以及关于在研究中使用t检验进行推断时应考虑的事项的建议。
