Albers M, Pereira C A
Departamento de Cirurgia, Faculdade de Medicina, Universidade de São Paulo.
Rev Hosp Clin Fac Med Sao Paulo. 1995 Sep-Oct;50(5):294-6.
Doctors as researchers often resort to hypothesis testing and confidence intervals in the statistical analysis of study results. On the one hand, the use of statistical software has made this task easier. On the other hand, this has not contributed to neither a better understanding of statistical concepts nor to a seminal cooperation between doctors and statisticians. This note shows that the classical statistical theory, also called frequentist or Fisherian, offers probability statements that are very indirect ones. Bayesian statistics, on the other hand, gives a probability statement which is a more direct answer to the research question. Of course, this latter approach would hardly be considered without a close cooperation with an statistician. An improvement in the meaning of the probability statements may be seen as a gain in quality. An effective cooperation with statisticians, an issue that is more ethical than methodological, is directed to achieving a research of a better quality, so avoiding the scandal of poor medical research.
作为研究人员的医生在研究结果的统计分析中经常采用假设检验和置信区间。一方面，统计软件的使用使这项任务变得更容易。另一方面，这既没有促进对统计概念的更好理解，也没有促进医生与统计学家之间富有成效的合作。本笔记表明，经典统计理论，也称为频率论或费希尔理论，提供的概率陈述非常间接。另一方面，贝叶斯统计给出的概率陈述是对研究问题更直接的回答。当然，如果没有与统计学家的密切合作，很难考虑后一种方法。概率陈述含义的改进可被视为质量的提高。与统计学家的有效合作是一个比方法论更具伦理性质的问题，旨在实现更高质量的研究，从而避免糟糕医学研究的丑闻。
