药时曲线的两组对比检验  

Comparative Test of Two Groups for Concentration-time Curves

作　　者：赵丽萍 夏志明 

机构地区：[1]西北大学数学学院,西安710127

出　　处：《工程数学学报》2018年第1期33-44,共12页Chinese Journal of Engineering Mathematics

基　　金：国家自然科学基金(11771353;11201372)~~

摘　　要：本文针对药代动力学中来自不同总体的两组样本进行对比检验.首先给出了原假设与备择假设下的似然函数,然后构造了似然比统计量,并证明了在原假设成立时统计量的极限分布为χ~2(3)分布.最后通过数值模拟验证理论的正确性.结果表明:对于参数相同的两组样本,当样本量较大时,统计量的经验分布与极限分布拟合较好.对于参数不同的两组样本,随着参数间差异增大,p值变小,拒绝原假设的证据越充分.Aiming at two groups of samples from different populations in the pharmacokinetics,we developed a comparative test of two groups. Firstly, we provided the likelihood function when the null hypothesis and the alternative hypothesis are given. Then the likelihood ratio statistic is constructed, and we proved that the limit distribution of the statistic is χ2(3) when null hypothesis is true. Lastly the numerical simulation is conducted to confirm the truth of the theory through data verification. The results show that for the two groups with the same parameters, the empirical distribution and the limit distribution fitting well when the sample size is large. On the contrary, the more differences parameters with the smaller values of the p-value, and the evidence to refuse the null hypothesis will be more sufficient.

关 键 词：药时曲线 变点 两组对比检验 

分 类 号：O213[理学—概率论与数理统计]