# Advanced Forecasting Models with R

Last Update: May, 2018

1. Course Objective

Learn Advanced Forecasting Models main topics using R statistical software® in this practical course for expert knowledge level. Feel free to take a look at Course Curriculum.

2. Skills Learned

At the end of this course you will know how to:

• Identify Box-Jenkins Non-Seasonal, Seasonal Auto Regressive Integrated, Fractionally Integrated Moving Average ARIMA, SARIMA and ARFIMA models integration and fractional integration order (first order trend stationary augmented Dickey-Fuller and Phillips-Perron unit root tests), seasonal integration order (first order seasonal stationary Hylleberg-Engle-Granger-Yoo seasonal unit root test), non-seasonal, seasonal autoregressive and moving average orders (normal and partial autocorrelation functions charts).
• Estimate ARIMA, SARIMA and ARFIMA models (non-seasonal, seasonal, fractional random walk with drift, non-seasonal, fractional differentiated first order autoregressive, general seasonal).
• Recognize Generalized Auto Regressive Conditional Heteroscedasticity GARCH modeling need (second order stationary Engle ARCH test, Ljung-Box autocorrelation test) and non-Gaussian GARCH modeling need (multiple order stationary Jarque-Bera normality test, Q-Q plot).
• Approximate ARIMA models with residuals assumed as Gaussian or Student’s t distributed and with Bollerslev simple, Nelson exponential or Glosten-Jagannathan-Runkle threshold GARCH effects (random walk with drift, differentiated first order autoregressive).
• Select methods or models (Akaike, corrected Akaike and Schwarz Bayesian information loss criteria).
• Evaluate methods or models forecasting accuracy (mean absolute error, root mean squared error, mean absolute percentage error, mean absolute scaled error).
• Assess model standardized residuals strong white noise requirement (Ljung-Box autocorrelation test, Jarque-Bera normality test).

3. Typical Student

This course is ideal for you as: