Gregor von Schweinitz
- 23 February 2017
- WORKING PAPER SERIES - No. 2025Details
- Abstract
- Early-warning models most commonly optimize signaling thresholds on crisis probabilities. The ex-post threshold optimization is based upon a loss function accounting for preferences between forecast errors, but comes with two crucial drawbacks: unstable thresholds in recursive estimations and an in-sample overfit at the expense of out-of-sample performance. We propose two alternatives for threshold setting: (i) including preferences in the estimation itself and (ii) setting thresholds ex-ante according to preferences only. Given probabilistic model output, it is intuitive that a decision rule is independent of the data or model specification, as thresholds on probabilities represent a willingness to issue a false alarm vis-
- JEL Code
- C35 : Mathematical and Quantitative Methods→Multiple or Simultaneous Equation Models, Multiple Variables→Discrete Regression and Qualitative Choice Models, Discrete Regressors, Proportions
C53 : Mathematical and Quantitative Methods→Econometric Modeling→Forecasting and Prediction Methods, Simulation Methods
G01 : Financial Economics→General→Financial Crises