Journal of Statistics Applications & Probability

Author Country (or Countries)



Birth Rate is one of the important measures in Vital Statistics. In Policy decision making, Birth rate of the state plays a major role and based on that Government makes decision for people welfare. Predicting births and birth rates are fundamental factors in predicting the future population of states. Time series models are one of the best methods for forecasting future values. In time series models, ARIMA models are the class of models which are used to predict the values which can be made the stationarity. In this study, the state TamilNadu birth rates from 1950-2019 has been considered to forecasts the birth rate of the state using Box-Jenkins methods. The ARIMA (5,1,1) models were found to have lower normalised Bayesian information criterion (BIC) and Akaike information criterion (AIC) values, making them more acceptable. The ARIMA (0,1,0) model was used to predict the birth rate for the next 30 years, and the results indicated that the birth rate will decline in succeeding years. In conclusion, co-efficient of robust ARIMA model compared with the classical ARIMA model and resulted the best ARIMA models to forecasts the birth rate of the state TamilNadu.

Digital Object Identifier (DOI)