ESTIMATION OF CHANGE POINT IN BINOMIAL RANDOM VARIABLES

Abstract

Statistically, change point is the location or the time point such that observations follow one distribution up to the point and then another afterwards. Change point problems are encountered in our daily life and in disciplines such as economics, finance, medicine, geology, literature among others. In this paper, the change point in binomial observations whose the mean is dependent on explanatory variables is estimated. The maximum likelihood method was used to estimate the change point while the conditional means were estimated using the artificial neural network The consistency and asymptotic normality of neural network parameter estimates was also proved. We used simulated data to estimate the change point and also estimated the LD50 for the Bliss beetles data.