二项型指数曲线在药-时曲线拟合中的应用  

The Application of Bionomial Exponential Curve in the Fitting of Drug Concentration-time Curve

作　　者：高辉[1] 胡良平[1] 李长平[2] 郭晋[3] 鲍晓蕾[1] 毛玮[1] 

机构地区：[1]军事医学科学院生物医学统计学咨询中心,100850 [2]天津医科大学公共卫生学院卫生统计学教研室,300070 [3]北京协和医学院阜外心血管病医院生物统计部,100037

出　　处：《中国卫生统计》2011年第5期520-522,共3页Chinese Journal of Health Statistics

摘　　要：目的探讨二项型指数曲线在药-时曲线拟合中的应用及其SAS实现。方法借助SAS软件,调用REG过程以常规的残数法得到曲线参数的估计值,然后以这些估计值为初始值,调用NLIN过程进行非线性最小二乘法估计,得到优化的曲线模型。结果残数法与非线性最小二乘法相结合所得最终曲线模型较残数法计算而来的模型有更好的拟合效果。结论 SAS编程可便捷实现二项型指数曲线对药-时曲线的拟合,且拟合效果较好,具有广阔的应用前景。Objective To explore the application of binomial exponential curve in the fitting of drug concentration-time curve and the SAS realization.Methods Use the traditional residual method by applying REG procedure in SAS to the data to get the estimate values of the curve parameters,then perform non-linear least squares method by applying NLIN procedure to the estimate values as starting values to optimize the curve fitting.Results Compared to the residual method,the combination of residual method and non-linear least squares method fits a better final curve model.Conclusion SAS program easily realizes the binomial exponential curve in the fitting of drug concentration-time curve.It fits the model well and has a wide application prospect.

关 键 词：二项型指数曲线 “药-时”曲线 曲线拟合 残数法 非线性最小二乘法 

分 类 号：R195[医药卫生—卫生统计学]