QMS 703 Lecture Notes - Lecture 5: Causal Inference, Economy Class, Sam Lecure
Document Summary
Qms 703: lecture 5: forecasting with moving average a strategy to evaluate forecasting models. Divide the data you have into two halves: The initialization or fitting half ( the training set ) used to determine the structure and parameters of the forecasting model. The test or forecasting half ( the validation set ) the forecasting method is used to forecast for the test part of the data, and the forecasting error is calculated. Complicated statistical models are not always required to develop accurate forecasts. The principle of parsimony suggests that the simpler the model, the better. The main advantage of simple models is that they serve as a benchmark with which to gauge applicability, reliability, and necessity of more sophisticated models. Time series models are good tools for forecasting short term events. The assumption underlying all time series models is that the historical pattern of the dependent variable can be used as the basis for developing the forecast.