二项自回归过程在装备使用数量统计上的运用
|
摘要
装备使用数量统计在装备管理上有着重要的意义,而一般的预测模型很难实现整值计数问题的预测;深入研究了一类基于稀疏算子的二项自回归模型在装备数量统计上的应用,该模型可以利用样本数据得到后验信息,提高了预测精度;最后进行了实例分析,结果显示所建模型是行之有效的。
Counts of equipment is a matter of cardinal significance,however,normal models cannot forecast in count time series of integer-value. We considered the application of binomial autoregressive in counts of equipment based on "thinning"operator. When we got the sample data,the model would obtain the posteriori information in order to improve the accuracy of prediction. In the last,we gave a sample with actual data.
Counts of equipment is a matter of cardinal significance,however,normal models cannot forecast in count time series of integer-value. We considered the application of binomial autoregressive in counts of equipment based on "thinning"operator. When we got the sample data,the model would obtain the posteriori information in order to improve the accuracy of prediction. In the last,we gave a sample with actual data.
引文
[1]Steutel F,Van Harn K.Discrete analogues of self-decomposability and stability[J].Ann.Probab,1979,7:893-899.
[3]Wei C H.A new class of autoregressive models for time series of binomial counts[J].Communications in StatisticsTheory and Methods,2005,38,447-460.
[2]Wei C H.Jumps in Binomial AR(1)processes[J].Statistics and Probability Letters,1998,79(19):2012-2019.
[4]Wei CH,Kim H.Parameter estimation for binomial AR(1)models with applications in finance and industry[Z].2012.
[5]崔帅.二项AR(1)模型的拟似然统计推断[D].长春:吉林大学,2013.
[6]Fokianos K.Some recent progress in count time series[J].Statistics,2011,45(11):49-58.
[7]Wei B C H,Pollett P K.Chain Binomial Models and Binomial Autoregressive Processes[J].Biometrics.2012,68(3):815-824.
[8]Mckenzie E.Some simple models for discrete variate time series[J].Water Resour.Bull.1985,24(4):645-650.
[9]Mc Kenzie E.Discrete variate time series[C]//Rao C R,Shanbhag D N.Handbook of Statistics.Amsterdam:Elsevier Science B V,573-606.
[10]Wei B C.H.Thinning operations for modeling time series of counts-a survey[J].Advances in Statistical Analysis,2008,92(10):319-343.
[3]Wei C H.A new class of autoregressive models for time series of binomial counts[J].Communications in StatisticsTheory and Methods,2005,38,447-460.
[2]Wei C H.Jumps in Binomial AR(1)processes[J].Statistics and Probability Letters,1998,79(19):2012-2019.
[4]Wei CH,Kim H.Parameter estimation for binomial AR(1)models with applications in finance and industry[Z].2012.
[5]崔帅.二项AR(1)模型的拟似然统计推断[D].长春:吉林大学,2013.
[6]Fokianos K.Some recent progress in count time series[J].Statistics,2011,45(11):49-58.
[7]Wei B C H,Pollett P K.Chain Binomial Models and Binomial Autoregressive Processes[J].Biometrics.2012,68(3):815-824.
[8]Mckenzie E.Some simple models for discrete variate time series[J].Water Resour.Bull.1985,24(4):645-650.
[9]Mc Kenzie E.Discrete variate time series[C]//Rao C R,Shanbhag D N.Handbook of Statistics.Amsterdam:Elsevier Science B V,573-606.
[10]Wei B C.H.Thinning operations for modeling time series of counts-a survey[J].Advances in Statistical Analysis,2008,92(10):319-343.