Transfer Function Model And Its Application In Hospital Income

A time series is a set of observations made at a succession of equally spaced points in time.The essence of time series is dependent between adjacent observations.Ordinary regression model is difficult to embody dependent relation between observations for each time period of variable.As a analyse technology of dependent relation between observations for each time period of variable,ARIMA model shows dependent relation between current observations and former observations of themself.thus,it has rich construction in expressing evolutive regular of dynamical system of variable.However ARIMA model can not give voice to affection of variables in system without calculating the predictor series affected the dependent series over time.A certain extent, transfer function model can remedy limitation of them.When an ARIMA model includes other time series as input variables, the model is sometimes referred to as multivariate time series model,ARIMAX model and Box-Tiao model that extended from the ARIMA models,Pankratz refers to these models as dynamic regression.Transfer function model was first popularized by George E.P.Box and Gwilym M. Jenkins under the ARIMA approach in 1970's.The general transfer function model employed by the ARIMA procedure was discussed by Box and Tiao. It can be considered that ARIMA models integrated regression model into transfer function model formally who related dynamic affection of variables clearly.As the extension of multiple regression model, transfer function model needs less presuppositions, thereby satisfied with condition easily, applied to practical system extensively. The most important purpose to analyze time series with transfer function model is improving the precision of forecast.We can forecast output series according to input series and output series if make sure how changes in the independent series affect the dependent series over time when we will forecast the series using former observations of themselves.Transfer function model reduced error of forecast due to it made use of ARIMA model theory as well as calculated affection of input series leading the predicted value of output series.In this paper,we will analyze independent series of hospital income using transfer function model.Meanwhile,we are going to forecast and compare the true value with outcomes of transfer function model and that of ARIMA model.