F
Francis X. Diebold
Researcher at University of Pennsylvania
Publications - 376
Citations - 82582
Francis X. Diebold is an academic researcher from University of Pennsylvania. The author has contributed to research in topics: Volatility (finance) & Exchange rate. The author has an hindex of 110, co-authored 368 publications receiving 74723 citations. Previous affiliations of Francis X. Diebold include International Monetary Fund & Duke University.
Papers
More filters
Journal ArticleDOI
Structural time series analysis and modelling package: A review
TL;DR: This package performs specialized tasks related to specification, estimation, prediction and diagnostic checking in the context of a particular class of unobserved-components models, and is menu-driven and easy to use.
Posted Content
Improving GDP measurement: a forecast combination perspective
TL;DR: In this paper, a "forecast combination" approach was proposed to combine two often-divergent U.S. GDP estimates, a widely-used expenditure-side version GDPE and a much less widely used income side version GDI.
Posted Content
Real-Time Multivariate Density Forecast Evaluation and Calibration: Monitoring the Risk of High-Frequency Returns on Foreign Exchange
TL;DR: In this paper, a framework for evaluating and improving multivariate density forecasts is proposed, and conditions under which a technique of density forecast "calibration" can be used to improve deficient density forecasts.
Posted Content
Unit Root Tests are Useful for Selecting Forecasting Models
TL;DR: In this paper, the usefulness of root tests as diagnostic tools for selecting forecasting models was studied, and it was shown that unit-root pretesting routinely improves forecast accuracy relative to forecasts from models in differences.
Posted Content
Globalization, the Business Cycle, and Macroeconomic Monitoring
TL;DR: In this paper, a framework for characterizing and monitoring the global business cycle is proposed and implemented, which utilizes high-frequency data, allows to account for a potentially large amount of missing observations, and is designed to facilitate the updating of global activity estimates as data are released and revisions become available.