cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Choose Language Hide Translation Bar
临床试验中统计学风险的控制(How to control statistical errors in clinical trials)_陈峰教授(Prof.Feng.Chen)

演讲嘉宾:陈峰教授,南京医科大学研究生院院长,CCTS组长

Speaker: Feng Chen, Professor of Biostatistics, Nanjing Medical University

 
主题:临床试验中统计学风险的控制
Topic:How to Control Statistical Errors in Clinical Trials
 
 
 
摘要:
新药的临床试验,无论成功或者失败,都有可能犯错误。从统计学角度讲,一个无效的药物做出阳性结果,就是犯了一类错误,又称假阳性错误,这类错误是监管部门要严格控制的;而一个有效的药物没有做出阳性结果,就犯了二类错误,又称假阴性错误,这类错误是申办方应该尽量避免的。报告者从统计学角度阐述在新药的临床试验中如何有效控制这些错误的发生率。

 

Abstract:

New drug clinical trials, whether successful or failed, are likely to have errors. From a statistical point of view, there are two types of errors: Type I and Type II. The Type I error, also known as a false-positive error, occurs when an ineffective drug shows positive results, suggesting that the drug in question is efficacious for treating the indicated disease or condition. A Type I error is most concerning to regulatory authorities who strive to keep ineffective or harmful drugs from the market. The Type II error, also known as a false-negative error, occurs when an effective drug does not show positive results, suggesting that the drug in question is ineffective for treating the indicated disease or condition. A Type II error is most concerning to the sponsors of the trial because of the very real likelihood of keeping an effective drug from providing a return on their research investments. This report suggests statistical methods to effectively control the Type I error and minimize the Type II error in the clinical trials of new drugs.