中国居民消费的数据生成过程研究  

Research on Data Generation Process of Chinese Domestic Consumption

作　　者：汪燕敏[1] 陈年红[1] 

机构地区：[1]安徽财经大学经济发展研究中心,安徽蚌埠233041

出　　处：《统计与信息论坛》2007年第3期69-72,共4页Journal of Statistics and Information

基　　金：安徽省教育厅自然科学研究项目(04K2052);安徽省青年教师项目(2006jqw075)

摘　　要：如果非平稳总量时序列存在结构变化,那么传统的单位根检验往往会得出错误的统计推断。在考虑经济结构变化的基础上,对中国居民消费时序列是具有单位根的非平稳还是分段趋势平稳进行研究,结果发现该时序列是围绕着1个结构断点的分段趋势平稳。分段趋势平稳的结论说明政策主导下的长期经济发展战略能够改变居民消费总量的增长路径;短期消费政策也是值得应用的。The classical unit root test will draw false statistical inference if structural change lies in nonstationary time series. The paper applies unit root tests to Chinese domestic consumption that allow for the possibility of endogenous structural break. We find that the series can be more accurately characterized as a segmented trend stationary process around one structural break as opposed to a stochastic unit root process. The conclusion suggests that long - term economic growth strategy can change the growth path of domestic consumption and short- run stabilization policies are applicable.

关 键 词：数据生成过程 单位根检验 结构断点 分段趋势平稳 

分 类 号：C220[社会学]