论文标题
多个更改点估计的二进制分割的一致性和功能数据的一致性
Consistency of Binary Segmentation For Multiple Change-Points Estimation With Functional Data
论文作者
论文摘要
对于依次观察到的功能数据，在平均函数中表现出多个变更点，我们根据功能性cusum过程和标准二进制分割的规范为变更点的估计数和位置建立一致性结果。除了将标量数据的Venkatraman（1992）和Fryzlewicz（2014）扩展到一般的希尔伯特空间设置外，我们的主要结果是在不假设数据的高斯和模型误差的一般线性过程下建立的。
For sequentially observed functional data exhibiting multiple change points in the mean function, we establish consistency results for the estimated number and locations of the change points based on the norm of the functional CUSUM process and standard binary segmentation. In addition to extending similar results in Venkatraman (1992) and Fryzlewicz (2014) for scalar data to the general Hilbert space setting, our main results are established without assuming the Gaussianity of the data, and under general linear process conditions on the model errors.
