Out-of-Sample Dataset
Jump to navigation
Jump to search
An Out-of-Sample Dataset is a Dataset that is used in a Out-of-Sample Evaluation Task.
- Context:
- It is a dataset that is not used in a model learning task.
- …
- Example(s):
- Counter-Example(s):
- See: Cross-Validation, Out-of-Sample Forecasting Experiment.
References
2019
- (Fomby, 2019) ⇒ Thomas B. Fomby (2019). "Out-of-Sample Forecasting Experiment" Retrieved: 2019-05-01.
- QUOTE: Out-of-sample forecasting experiments are used by forecasters to determine if a proposed leading indicator is potentially useful for forecasting a target variable. The steps for conducting an out-of-sample forecasting experiment are as follows:
- 1) Divide the available data on the target variable, [math]\displaystyle{ y_t }[/math], (here we assume [math]\displaystyle{ y_t }[/math] is stationary) and the proposed leading indicator,[math]\displaystyle{ x_t }[/math] , (likewise we assume that [math]\displaystyle{ x_t }[/math] is stationary) into two parts: the in-sample data set (roughly 80% of the data) and the out-of-sample data set (the remaining 20% of the entire data set).
2017
- (Sammut & Webb, 2017) ⇒ Claude Sammut, and Geoffrey I. Webb. (2017). “Out-of-Sample Data.” In: (Sammut & Webb, 2011)
- QUOTE: Out-of-sample data are data that were not used to learn a model. Holdout evaluation uses out-of-sample data for evaluation purposes.