带趋势项的持久性变点的Ratio检验  

Ratio test of persistence change point with trend

作　　者：侯安然 赵文芝[1] 孙怡玮 HOU An-ran;ZHAO Wen-zhi;SUN Yi-wei(School of Science,Xi’an Polytechnic University,Xi’an 710048,China)

机构地区：[1]西安工程大学理学院,西安710048

出　　处：《哈尔滨商业大学学报（自然科学版）》2023年第1期95-101,共7页Journal of Harbin University of Commerce：Natural Sciences Edition

基　　金：国家自然科学基金面上基金(12171391);陕西省自然科学基础研究计划项目(2022JM-024)。

摘　　要：为研究带趋势项的持久性变点检验问题,表明Ratio统计量适用于带趋势项的I(0)向I(d)过程的转变.在假设条件下,推导其极限分布并证明检验的一致性.通过Monte Carlo方法进行仿真模拟,结果表明,检验方法可以控制经验水平值和势函数值.最后将检验方法用于美国国民实际生产总值数据,验证了检验方法的有效性.In order to study the problem of persistence change-point test with trend,it was showed that Ratio statistic was applicable for a change from short to long memory process.The limit distribution was derived and the consistency of the test was proved under hypothetical conditions.The Monte Carlo method was used for simulation,results showed that the test method could control the empirical sizes value and power value.The method was applied to the real GROSS national product data of the United States to verify the effective of the method.

关 键 词：短记忆 长记忆 持久性变点 RATIO Monte Carlo方法 

分 类 号：O212.1[理学—概率论与数理统计]