novinsh / ts_analysis_coursework

Time Series Statistical Models Selection and Forecasting

Time Series Analysis Course Project

The goal of the project was to apply ARIMA, SARIMA, ARIMAX and holt-winter family of models on two different time series. At the end, the forecast performance of each fitted models studied and reported using the conventional error measures. Appropriateness of the models mainly studied by studying the residuals. Required preprocessing steps addressing stationarity of the series applied where needed.

Files

• series1.R Analysis of first time series ((S)ARIMA and Holt-winter)

• series2.R Analysis of second time series ((S)ARIMA and ARIMAX)

• Report

• Video Presentation

• Slides

• Instructions