搜索结果: 1-13 共查到“管理学 ARMA”相关记录13条 . 查询时间(0.092 秒)
市场流动性与市场预期的动态相关结构研究——基于ARMA-GJR-GARCH-Copula模型分析
市场流动性 市场预期 时变信息熵 ARMA-GJR-GARCH-Copula 动态相关结构
2016/2/29
本文在兼顾"时间尺度"和"价格尺度"双重因素下构建了标准化的市场流动性测度,并利用时变信息熵方法提出了一类市场预期的新指标。将ARMA-GJR-GARCH模型与时变Copula模型相结合分析了市场流动性与市场预期之间的动态相关结构。利用2009年1月~2014年9月中国股市日度数据进行实证分析,结果表明:市场流动性和市场预期存在较明显的持续性和负向"杠杆效应",通过LL、AIC和BIC三种准则比较...
ARMA Time-Series Modeling with Graphical Models
ARMA Time-Series Modeling Graphical Models
2012/9/19
We express the classic ARMA time-series model as a directed graphical model. In doing so, we find that the deterministic re-lationships in the model make it effectively impossible to use the EM algori...
Strictly stationary solutions of multivariate ARMA equations with i.i.d. noise
Strictly stationary solutions multivariate ARMA equations i.i.d. noise
2011/6/17
We obtain necessary and sufficient conditions for the existence of strictly stationary
solutions of multivariate ARMA equations with independent and identically
distributed noise. For general ARMA(p...
Distribution processes of the fractional ARMA type, mixing properties
Distribution processes the fractional ARMA type mixing properties
2009/9/22
In this Pa per we firstly study f, the inverse Laplace transform of F(s) = n,=(,s - 0 3 . The distribution f is then used to
define a family of linear distribution processes. This family generalizes
...
On adaptive estimation based on ranks in ARMA processes
Local asymptotic normality (LAN) asymptotic linearity locally asymptotically minimax (LAM)
2009/9/21
This paper describe6 the adaptive estimation problem
based on ranks for the parameter of an ARMA process. Tbe local
asymptotic normality property with a ranked based central sequence
allows for the...
On ARMA(1,q) models with bounded and periodically correlated solutions
Periodically correlated ARMA model periodic coefficients
2009/9/21
In this paper, motivated by [2], we derive necessary
and suficient conditions for bounded and periodically correlated solutions
to the system of equations described by ARMA(1, q) model.
KALMAN-TYPE RECURSIONS FOR TIME-VARYING ARMA MODELS AND THEIR IMPLICATION FOR LEAST SQUARES PROCEDURE
Kalman-type recursions least squares procedure state-space representations time-varying ARMA models
2009/9/18
This paper is devoted to ARMA models with timedependent
coefficients, including well-known periodic ARMA models. We
provide state-space representations and Kalman-type recursions to derive a
Wold–C...
ARMA模型在管理科学领域有着广泛的应用,组合预测可以提高ARMA模型的预测效果,但是如何选择最优模型组是十分重要但尚未解决的问题。本文提出了一个基于Kullback-Leibler信息量(简称K-L信息量)的最优模型组选择方法确定那些与最优模型无显著差异的模型形成最优模型组。最后,本文通过模拟数据比较了基于最优模型组的组合预测与根据AIC准则确定的单个最优模型的预测效果,组合预测效果要优于单模型...
A Modified Box-Cox Transformation in the Multivariate ARMA Model
Box-Cox transformation limit theorems Monte-Carlo Wald test multivariate ARMA model ratio data transformation-linear process
2009/3/5
The Box-Cox transformation has been used as a simple method of transforming dependent variable in ordinary-linear regression circumstances for improving the Gaussian-likelihood fit and making the dist...
ON A CLASS OF Z+-VALUED AUTOREGRESSIVE MOVING AVERAGE (ARMA) PROCESSES
stationarity semigroup of probability generating functions Mittag–Leffler distribution Linnik distribution time-reversibility
2009/2/25
A convolution semigroup of probability generating functions and its related operator
⊙F are used to construct a class of stationary Z+-valued autoregressive moving average
(ARMA) processes. Several ...
缺失数据下ARMA(1, 1)模型的估计方法
缺失数据 ARMA(1,1)模型 似然函数 EM算法
2013/11/5
近几十年以来,国际上在对"风险的处理和效益的优化"这两个现代金融学的中心议题的分析和处理过程中,金融时间序列的计量学模型及其相应的分析越来越起到非常重要的作用.对于线性时间序列模型如AR(p),MA(q),ARMA(p,q)等,已经为我们所熟知.具体到模型的参数估计在数据没有缺失时,也有很多经典的办法,如最小二乘法、极大似然法等.但是当数据在中间有缺失时,上述方法将无能为力.本文将详细讨论在数据有...
A characterization of ARMA and Fractional ARIMA models with infinitely divisible innovations
Asymptotic dependence Infinitely divisible distributions ARMA Fractionally integrated ARMA Stable distributions Long memory
2010/4/27
The object of this paper is to study the asymptotic dependence structure of the linear
time series models with infinitely divisible innovations by the use of their characteristic
functions. Autoregr...
Estimation of AR and ARMA models by stochastic complexity
minimum description length principle Fisher information normalized maximum likelihood universal model Monte Carlo technique
2010/4/27
In this paper the stochastic complexity criterion is applied to estimation
of the order in AR and ARMA models. The power of the criterion
for short strings is illustrated by simulations. It requires...