Corpus ID: 220825267

Predictive properties and minimaxity of Bayesian predictive synthesis

  title={Predictive properties and minimaxity of Bayesian predictive synthesis},
  author={K. Takanashi and K. McAlinn},
  journal={arXiv: Statistics Theory},
  • K. Takanashi, K. McAlinn
  • Published 2019
  • Mathematics, Economics
  • arXiv: Statistics Theory
  • We examine and compare the predictive properties of classes of ensemble methods, including the recently developed Bayesian predictive synthesis (BPS). We develop a novel strategy based on stochastic processes, where the predictive processes are expressed as stochastic differential equations, evaluated using It\^{o}'s lemma. Using this strategy, we identify two main classes of ensemble methods: linear combination and non-linear synthesis, and show that a subclass of BPS is the latter. With… CONTINUE READING
    1 Citations

    Figures and Tables from this paper


    Combining inflation density forecasts
    • 123
    • PDF
    Model Selection and Accounting for Model Uncertainty in Graphical Models Using Occam's Window
    • 1,230
    • PDF
    Comparing Density Forecasts via Weighted Likelihood Ratio Tests
    • 460
    • PDF
    Multivariate Bayesian Predictive Synthesis in Macroeconomic Forecasting
    • 13
    • PDF
    Optimal Prediction Pools
    • 308
    • PDF
    The Evolution of Forecast Density Combinations in Economics
    • 21
    • PDF