Modified information criterion for linear regression change-point model with its applications

The linear regression model with normal distribution errors in detecting change in the regression parameters beta 0 and beta 1 has been studied. We propose a testing procedure based on a modified information criterion (MIC) to locate change points, such procedure is the modified version of the Schwartz information criterion (SIC). The asymptotic distribution of the test statistic based on MIC is shown to be chi-square distribution with freedom three. The simulations have been conducted under different changes among parameters of interest with various sample sizes n to investigate the performance of the proposed test. The power comparisons between MIC and SIC have been given. Such procedure applied on a NASA data to illustrate the detecting process.