arXiv (Cornell University) · 2015 · 36 citations · 1 references
BusinessRisk ManagementEconometricsPredictive AnalyticsStatistical ModelingRegressionRisk EstimationRisk MeasurementRisk ModelingRobust Statistical ModelingRobust StatisticsConsistencyEmpirical Risk ManagementMean Absolute ErrorMean Absolute Error AnalysisMean Squared Error Estimation
We study in this paper the consequences of using the Mean Absolute Percentage Error (MAPE) as a measure of quality for regression models. We show that finding the best model under the MAPE is equivalent to doing weighted Mean Absolute Error (MAE) regression. We show that universal consistency of Empirical Risk Minimization remains possible using the MAPE instead of the MAE.
1
Methods of Correlation Analysis
Edgar Z. Palmer, Mordecai Ezekiel · Southern Economic Journal · 1942 · 243 citations