Shi Xiaoping, Wu Yuehua, Rao Calyampudi Radhakrishna
Department of Mathematics and Statistics, Thompson Rivers University, Kamloops, BC, Canada V2C0C8;
Department of Mathematics and Statistics, York University, Toronto, ON, Canada M3J1P3;
Proc Natl Acad Sci U S A. 2017 Apr 11;114(15):3873-3878. doi: 10.1073/pnas.1702654114. Epub 2017 Mar 29.
A change-point detection is proposed by using a Bayesian-type statistic based on the shortest Hamiltonian path, and the change-point is estimated by using ratio cut. A permutation procedure is applied to approximate the significance of Bayesian-type statistics. The change-point test is proven to be consistent, and an error probability in change-point estimation is provided. The test is very powerful against alternatives with a shift in variance and is accurate in change-point estimation, as shown in simulation studies. Its applicability in tracking cell division is illustrated.
提出了一种基于最短哈密顿路径的贝叶斯型统计量进行变点检测，并使用比率切割法估计变点。应用排列程序来近似贝叶斯型统计量的显著性。证明了变点检验是一致的，并给出了变点估计中的误差概率。如模拟研究所示，该检验对具有方差变化的备择假设非常有效，并且在变点估计中很准确。说明了其在跟踪细胞分裂中的适用性。
