A non-linear forecast combination procedure for binary outcomes

Abstract We develop a non-linear forecast combination rule based on copulas that incorporate the dynamic interaction between individual predictors. This approach is optimal in the sense that the resulting combined forecast produces the highest discriminatory power as measured by the receiver operating characteristic (ROC) curve. Under additional assumptions, this rule is shown to be equivalent to the quintessential linear combination scheme. To illustrate its usefulness, we apply this methodology to optimally aggregate two currently used leading indicators – the ISM new order diffusion index and the yield curve spread – to predict economic recessions in the United States. We also examine the sources of forecasting gains using a counterfactual experimental set up.

• Publication year

  2015

• Venue

  Social Science Research Network

• Publication date

  Unknown publication date

• Fields of study

  Mathematics, Economics

• Identifiers
  DOI 10.1515/snde-2014-0054
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A simple, positive semi-definite, heteroscedasticity and autocorrelation consistent covariance matrix

  2014cited by this paper
• Predicting U.S. recessions through a combination of probability forecasts

  2014cited by this paper
• Handbook of Economic Forecasting, Vol 2A

  2013cited by this paper
• Evaluating Probability Forecasts for GDP Declines Using Alternative Methodologies

  2013cited by this paper
• Copula Methods for Forecasting Multivariate Time Series

  2013cited by this paper
• RISK OF BAYESIAN INFERENCE IN MISSPECIFIED MODELS, AND THE SANDWICH COVARIANCE MATRIX

  2013cited by this paper
• A Bivariate Model of Federal Reserve and ECB Main Policy Rates

  2012cited by this paper
• Forecasting Binary Outcomes

  2012cited by this paper
• A review of copula models for economic time series

  2012cited by this paper
• Evaluating the Classification of Economic Activity into Recessions and Expansions

  2011cited by this paper
• Comprehensive Benchmark Revisions for The Conference Board Leading Economic Index® for the United States

  2011cited by this paper
• Research Paper 2010-21 Forecast Combinations

  2010cited by this paper
• Combining probability forecasts

  2010cited by this paper
• Covariance Matrix

  2010cited by this paper
• Estimation and model selection of semiparametric multivariate survival functions under general censorship.

  2010cited by this paper
• ROC Curves for Continuous Data

  2009cited by this paper
• Multi-Market Direction-of-Change Modeling Using Dependence Ratios

  2009cited by this paper
• The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition

  2009cited by this paper
• Bayesian Computation with R

  2008influential reference
• Strictly Proper Scoring Rules, Prediction, and Estimation

  2007cited by this paper
• A Note On the Maximum Peirce Skill Score

  2007influential reference
• Copula Modeling: An Introduction for Practitioners

  2007cited by this paper
• MODELLING ASYMMETRIC EXCHANGE RATE DEPENDENCE a

  2006cited by this paper
• An introduction to ROC analysis

  2006cited by this paper
• Handbook of Economic Forecasting

  2006cited by this paper
• Contemporary Bayesian Econometrics and Statistics

  2005cited by this paper
• The Statistical Evaluation of Medical Tests for Classification and Prediction

  2005cited by this paper
• The t Copula and Related Copulas

  2005influential reference
• The Statistical Evaluation of Medical Tests for Classification and Prediction

  2003cited by this paper
• Dependence structures for multivariate high-frequency data in finance

  2003cited by this paper
• Combining Several Screening Tests: Optimality of the Risk Score

  2002cited by this paper
• Statistical Methods in Diagnostic Medicine

  2002cited by this paper
• The Elements of Statistical Learning: Data Mining, Inference, and Prediction

  2001cited by this paper
• An Introduction to Copulas

  2000cited by this paper
• Use of the “Odds Ratio” for Diagnosing Forecast Skill

  2000cited by this paper
• Better decisions through science.

  2000cited by this paper
• Economic and Statistical Measures of Forecast Accuracy

  1999cited by this paper
• Asymptotic behavior of Bayes estimates under possibly incorrect models

  1998cited by this paper
• Combining Qualitative Forecasts Using Logit

  1998cited by this paper
• Is a Group of Economists Better than One? Than None?

  1996cited by this paper
• 10 Interest rate spreads as predictors of business cycles

  1996influential reference
• The Yield Curve as a Predictor of U.S. Recessions

  1996cited by this paper
• Predicting U.S. Recessions: Financial Variables as Leading Indicators

  1995cited by this paper
• Predicting cyclical turning points with leading index in a markov switching model

  1994cited by this paper
• An Improved Heteroskedasticity and Autocorrelation Consistent Covariance Matrix Estimator

  1992cited by this paper
• Heteroskedasticity and Autocorrelation Consistent Covariance Matrix Estimation

  1991cited by this paper
• A General Method for Comparing Probability Assessors

  1989cited by this paper
• Improved methods of combining forecasts

  1984cited by this paper
• Present position and potential developments: some personal views

  1984cited by this paper
• Maximum Likelihood Estimation of Misspecified Models

  1982cited by this paper
• External correspondence: Decompositions of the mean probability score

  1982cited by this paper
• Signal detection theory and ROC analysis

  1975cited by this paper
• The Combination of Forecasts

  1969influential reference
• Tests for Specification Errors in Classical Linear Least‐Squares Regression Analysis

  1969cited by this paper
• Limiting Behavior of Posterior Distributions when the Model is Incorrect

  1966cited by this paper
• Signal detection theory and psychophysics

  1966cited by this paper
• VERIFICATION OF FORECASTS EXPRESSED IN TERMS OF PROBABILITY

  1950cited by this paper
• On the Problem of the Most Efficient Tests of Statistical Hypotheses

  1933cited by this paper

• Probabilistic Classification in Business Cycles Identification Based on Generalized ROC

  2025cites this paper
• Predicting binary outcomes based on the pair-copula construction

  2023cites this paper
• Semiparametric Averaging of Nonlinear Marginal Logistic Regressions and Forecasting for Time Series Classification

  2021cites this paper
• Application of Google Trends to Forecast Tourism Demand

  2019cites this paper
• Confidence Bands for ROC Curves With Serially Dependent Data

  2018cites this paper
• Forecast combination when outcomes are difficult to predict

  2017cites this paper
• A nonparametric approach to identifying a subset of forecasters that outperforms the simple average

  2016cites this paper