利率期限结构静态拟合方法研究  

Research on Static Fitting Method of Interest Rate Term Structure

作　　者：王雪标 张奇松 WANG Xue-biao;ZHANG Qi-song(School of Mathematics, Dongbei University of Finance and Economics,Dalian 116023,China;School of Economics, Dongbei University of Finance and Economics,Dalian 116023,China)

机构地区：[1]东北财经大学数学学院,辽宁大连116023 [2]东北财经大学经济学院,辽宁大连116023

出　　处：《商业研究》2018年第12期116-124,共9页Commercial Research

基　　金：国家自然科学基金面上项目"我国通胀预期和风险溢价与宏观因子作用机制的计量研究";项目编号:71273044;国家自然科学青年基金项目"分形市场中分数阶导数期权定价模型的建立;解法与应用研究";项目编号:71501031;辽宁省社科规划基金"技术并购对企业创新能力影响及经济后果研究";项目编号:L17CGL004

摘　　要：建立健全完整的利率期限结构,并反映经济市场的供求关系,对于我国市场经济的发展具有重大的意义。本研究目的是构建适合于中国实际情况的计量经济学模型对利率期限结构进行更加精准地刻画。静态估计和动态估计是利率期限结构估计的两种基本方式,其中静态估计是验证动态估计模型以及进行动态分析的基础。通过分析静态估计中的重要方法——三次样条函数估计方法的基本模型结构,根据市场经验和基本遗传算法对三次样条函数进行分界点估计的劣势,提出一种基于分层机制和动态概率的改进遗传算法对三次样条函数分界点进行估计;对比多个债券样本时间点的估计结果证明,基于改进遗传算法的三次样条函数在对利率期限结构估计方面,无论在样本内的模型估计,还是样本外模型预测,均优于基于市场经验和单纯遗传算法对于利率期限结构的估计。Establishing a sound and complete term structure of interest rates and reflecting the supply and demand relationship in the economic market is of great significance to the development of China′s market economy.The purpose of this study is to construct an econometric model that is suitable for China′s actual situation.And the model can more accurately describe the term structure of interest rates.Static estimation and dynamic estimation are two basic methods for estimating the term structure of interest rates.Static estimation is the basis for verifying the dynamic estimation model and performing dynamic analysis.By analyzing the important methods in static estimation-the basic model structure of the cubic spline function estimation method,and based on the disadvantages of market experience and basic genetic algorithm for the demarcation point estimation of the cubic spline function,improved Genetic Algorithm,which has a hierarchical mechanism and dynamic probability,is used to estimate the breakpoint of cubic spline function;comparing the estimation results of time points of multiple bond samples,it is proved that the cubic spline function based on improved genetic algorithm is better than market experience and simple genetic algorithm in estimating the term structure of interest rate both in-sample model estimation and out-of-sample model prediction.

关 键 词：样条函数 改进遗传算法 动态交叉概率 利率期限结构 

分 类 号：F820[经济管理—财政学]