Bayesian Forecasting the Cumulative First-time Reach of TV Programs

摘要

School of Statistics, Renmin University of China, Beijign, P.R. China, 100872;SONG Dawo@Center for Applied Statistics, Renmin University of China, Beijign, P.R. China, 100872 School of Statistics, Renmin University of China, Beijign, P.R. China, 100872 Reach of TV programs is a measure of the overall popularity of the program and is used as a criterion to sell the television time. Recognizing its importance, Lu and Lo (2010) propose a new statistical model to predict it for TV programs. This paper follows their approach to propose a new parameter estimation method for the model; and to incorporate the model into Bayesian framework to forecast the cumulative reach of TV program in advance. Empirical results show the new estimation method is better than Maximum Likelihood Method (MLE) and the Bayesian forecasting accuracy is quite high.