Estimating beta-mixing coefficients

Estimating beta-mixing coefficients
复制标题

DOI:
--
复制
发表时间:
2011-03
期刊:
JMLR workshop and conference proceedings
影响因子:
--
通讯作者:
D. McDonald;C. Shalizi;M. Schervish
D. McDonald;C. Shalizi;M. Schervish
中科院分区:
其他
文献类型:
--
作者:
D. McDonald;C. Shalizi;M. Schervish

文献摘要

被引文献

相似文献

关于时间序列统计学习的文献假设数据生成过程的渐近独立或“混合”。这些混合假设从未经过检验,也没有从数据中估计混合率的方法。我们给出了一个基于单一平稳样本路径的β混合率估计,并证明它是l1风险一致的。
The literature on statistical learning for time series assumes the asymptotic independence or "mixing" of the data-generating process. These mixing assumptions are never tested, and there are no methods for estimating mixing rates from data. We give an estimator for the beta-mixing rate based on a single stationary sample path and show it is L1-risk consistent.