TIME SERIES ANALYSIS — DU B.Sc (hons) Statistics Previous Year Question Papers

Attempt five questions in all. (b) Define an autoregressive process of order p, AR (p). Derive and discuss the stationarity conditions for an AR (1) model. 5. (a) Express the parameters of an autoregressive process of order p in terms of its autocorrelation function (ACF). Show that for the model $1 = P1, and pi is the lag-l autocorrelation coefficient. (b) For each of the following models: Express each model using the backshift operator B. Determine whether each model is stationary and/or invertible. 6. (a) State the basic principles of forecasting in time series analysis. Describe the exponential smoothing technique and explain how it is used for forecasting. (b) Define a non-stationary time series. What does the "I" component represent in an ARIMA model? 7 Write short notes on any three of the following: (a) Estimation of Seasonal variation under changing patterns (b) Variate ditterence method (C) Non-linear Time Series Models (d) Box-Jenkins Approach to Forecasting