Schmelzer M
University of Texas at Arlington, School of Nursing, POB 19407, Arlington, TX 76019, USA.
Gastroenterol Nurs. 2000 Nov-Dec;23(6):269-74. doi: 10.1097/00001610-200011000-00005.
Understanding the methodology section of research articles is difficult for those unfamiliar with research design, but is essential for judging the credibility of the researchers' findings. The methodology section describes measures taken to avoid reaching the wrong conclusions. When comparing two or more treatments, researchers might find a difference in treatments when none exists (type I error) or not find a difference when there actually is one (type II error). Type I errors are minimized by random assignment to treatment and control groups, double blinding, ensuring that the treatment under study is the only difference between groups, and setting the level of significance in advance. Type II errors are minimized by using an adequately sized, homogenous sample, increasing the treatment strength, measuring precisely, and using appropriate statistics. The purpose of this article is to explain these common experimental strategies and statistical terms.
对于那些不熟悉研究设计的人来说，理解研究文章的方法部分是困难的，但这对于判断研究人员发现的可信度至关重要。方法部分描述了为避免得出错误结论而采取的措施。在比较两种或更多种治疗方法时，研究人员可能会在不存在差异时发现治疗方法之间存在差异（I型错误），或者在实际存在差异时未发现差异（II型错误）。通过随机分配到治疗组和对照组、双盲、确保所研究的治疗方法是组间唯一差异以及预先设定显著性水平，可将I型错误降至最低。通过使用足够大的同质样本、增加治疗强度、精确测量以及使用适当的统计方法，可将II型错误降至最低。本文的目的是解释这些常见的实验策略和统计术语。
