Nonparametric estimates for conditional quantiles of time series
Nonparametric estimates for conditional quantiles of time series
复制标题
DOI：
10.1007/s10182-014-0234-4
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
J. Franke;P. Mwita;Weining Wang
中科院分区：
文献类型：
--
作者：
J. Franke;P. Mwita;Weining Wang
我们考虑在给定协变量$$\varvec{X}_{t}$$下估计时间序列的条件分位数的问题，其中$$\varvec{X}_{t}$$可以是外生变量或滞后变量。通过对条件分布函数的核估计进行反求来估计条件分位数，并证明了其渐近正态性和一致强相合性。通过仿真研究，对创新的轻尾分布和重尾分布的估计性能进行了评价。最后，将该方法应用于DAX股票的VaR估计，并与已有的标准方法进行回测比较。
We consider the problem of estimating the conditional quantile of a time seriesat timegiven covariates $$\varvec{X}_{t}$$, where $$\varvec{X}_{t}$$ can be either exogenous variables or lagged variables of. The conditional quantile is estimated by inverting a kernel estimate of the conditional distribution function, and we prove its asymptotic normality and uniform strong consistency. The performance of the estimate for light and heavy-tailed distributions of the innovations is evaluated by a simulation study. Finally, the technique is applied to estimate VaR of stocks in DAX, and its performance is compared with the existing standard methods using backtesting.