Published Paper Details:

For a given sequential data such as stock market prices or streaming stories in a newswire, we might be interested in when these data change in some way, such as a stock price falling or the document topics shifting. This abrupt change can cause shift in sequence and divide the sequence into two parts. For example If n items are put to test their lives then their lives will be x_1,x_2,.....,x_n. If there is one break in sequence, then sequence is divided into two parts. Suppose the change occurs at point mth, the sequence will be x_1,x_2,.....,x_m. and x_m,x_2,.....,x_(n+1). If we view our data as observations from a generative process, then we care about when the generative parameters change. Now the problem is how to detect and estimate the break point. For a given sequential data such as stock market prices or streaming stories in a newswire, we might be interested in when these data change in some way, such as a stock price falling or the document topics shifting. The goal of this paper is to explain a technical report on Bayesian changepoint detection and estimation by applying the Bayesian preliminary test estimation(BPTE) method in my research work, and to work through the framework and code for a Weibull model.