汇率预测非常困难,其波动具有时变性、随机性和模糊性等统计特征.现存文献中各种方法和模型的预测效果受很多因素影响,其预测力都不及随机游走模型,这就是汇率预测领域所谓的"米斯和罗格夫之谜(The Meese and Rogoff puzzle)"...汇率预测非常困难,其波动具有时变性、随机性和模糊性等统计特征.现存文献中各种方法和模型的预测效果受很多因素影响,其预测力都不及随机游走模型,这就是汇率预测领域所谓的"米斯和罗格夫之谜(The Meese and Rogoff puzzle)".本文使用非参数方法研究汇率波动及其预测模型,发现较之任何参数方法、半参数方法都具有更大的灵活性.为了克服"维数魔咒",本文提出非参数可加模型来研究汇率预测问题.与现有模型相比,在同样的观察样本期内,非参数可加汇率预测模型有更好的样本外预测能力,这有力地证明了"米斯和罗格夫之谜"并非难以破解.此外,我们将非参数可加汇率模型应用于人民币对美元的汇率预测,其结果仍然揭示了该模型很好的拟合度和预测能力.本文为汇率预测这一研究领域提供了新的研究思路和方法.展开更多
主要研究了单位圆盘上l^2值D_(μ,q)函数,得到了l^2值D_(μ,q)函数的收敛性,若f(z)=sum from n=1 to∞x_nz^n∈D_(μ,q),0<μ<1,q>(2n)/μ,则对几乎所有的{ε_α}有f_ω(z)∈H~∞.这推广了标量值D_(μ,q)函数的性质,在此过程中...主要研究了单位圆盘上l^2值D_(μ,q)函数,得到了l^2值D_(μ,q)函数的收敛性,若f(z)=sum from n=1 to∞x_nz^n∈D_(μ,q),0<μ<1,q>(2n)/μ,则对几乎所有的{ε_α}有f_ω(z)∈H~∞.这推广了标量值D_(μ,q)函数的性质,在此过程中,利用了Banach空间几何学的知识.展开更多
In this note, we consider stochastic heat equation with general additive Gaussian noise. Our aim is to derive some necessary and sufficient conditions on the Gaussian noise in order to solve the corresponding heat equ...In this note, we consider stochastic heat equation with general additive Gaussian noise. Our aim is to derive some necessary and sufficient conditions on the Gaussian noise in order to solve the corresponding heat equation. We investigate this problem invoking two differen t met hods, respectively, based on variance compu tations and on pat h-wise considerations in Besov spaces. We are going to see that, as anticipated, both approaches lead to the same necessary and sufficient condition on the noise. In addition, the path-wise approach brings out regularity results for the solution.展开更多
文摘汇率预测非常困难,其波动具有时变性、随机性和模糊性等统计特征.现存文献中各种方法和模型的预测效果受很多因素影响,其预测力都不及随机游走模型,这就是汇率预测领域所谓的"米斯和罗格夫之谜(The Meese and Rogoff puzzle)".本文使用非参数方法研究汇率波动及其预测模型,发现较之任何参数方法、半参数方法都具有更大的灵活性.为了克服"维数魔咒",本文提出非参数可加模型来研究汇率预测问题.与现有模型相比,在同样的观察样本期内,非参数可加汇率预测模型有更好的样本外预测能力,这有力地证明了"米斯和罗格夫之谜"并非难以破解.此外,我们将非参数可加汇率模型应用于人民币对美元的汇率预测,其结果仍然揭示了该模型很好的拟合度和预测能力.本文为汇率预测这一研究领域提供了新的研究思路和方法.
文摘主要研究了单位圆盘上l^2值D_(μ,q)函数,得到了l^2值D_(μ,q)函数的收敛性,若f(z)=sum from n=1 to∞x_nz^n∈D_(μ,q),0<μ<1,q>(2n)/μ,则对几乎所有的{ε_α}有f_ω(z)∈H~∞.这推广了标量值D_(μ,q)函数的性质,在此过程中,利用了Banach空间几何学的知识.
基金supported by an NSERC granta startup fund of University of Albertasupported by the NSF grant DMS1613163
文摘In this note, we consider stochastic heat equation with general additive Gaussian noise. Our aim is to derive some necessary and sufficient conditions on the Gaussian noise in order to solve the corresponding heat equation. We investigate this problem invoking two differen t met hods, respectively, based on variance compu tations and on pat h-wise considerations in Besov spaces. We are going to see that, as anticipated, both approaches lead to the same necessary and sufficient condition on the noise. In addition, the path-wise approach brings out regularity results for the solution.
