As the authors did not provide the number of observations after the change point so the reproduction is done at the total 100 observations with 20 replicates. This makes the parameters estimated are much different, however; It is found that, for both cases, the lower the beta is, the larger in confidence interval. So the author should provide the number of observations as well as the signal to noise ratio (mean/variance) so that the parameters are estimated more accurate and more precise.