Appleton D R
Department of Medical Statistics, University of Newcastle upon Tyne, UK.
Nephrol Dial Transplant. 1988;3(6):830-2.
This is the last of six articles describing how to choose the appropriate statistical test to look for relationships between two variables. It shows that when the response variable is dichotomous and the explanatory variable is continuous it may not be appropriate to carry out a t-test. Some comments are made on extending the tests considered to more complex situations.
这是关于如何选择合适的统计检验来寻找两个变量之间关系的六篇文章中的最后一篇。文章表明,当反应变量是二分变量且解释变量是连续变量时,进行t检验可能并不合适。文中还对将所考虑的检验扩展到更复杂的情况提出了一些评论。