Abstract
Change point in a panel data refers to the time when a change(s) takes a place in the cross-sections of the panel. This key time helps practitioners to analyze the root cause(s) of the change manifested itself to the process. This paper attempts to introduce a new hybrid approach called Double-CUSUM-Modified EWMA (DCME) which is capable of providing a high sensitivity of detecting the change point in a panel data. The step change analysis of this paper addressees that the performance of the proposed model is more sensitive compared to the best available methods based on location accuracy and power terms. Furthermore this paper develops the proposed hybrid method using the binary method to identify the multiple change points in a panel data. Several numerical examples are considered to evaluate the capability of the proposed hybrid method.