Forecast Evaluation in Macroeconomics and International Finance. Ph.D. thesis, George Washington University, Washington, DC, USA
Olga Bespalova
MPRA Paper from University Library of Munich, Germany
Abstract:
This dissertation focuses on forecasting rare macroeconomic events, such as GDP declines and currency crises, using non-parametric methods, highlighting the advantages of the Receiver Operating Characteristic (ROC) curves analysis and the value of qualitative information from expert surveys and textual analysis in macroeconomic forecasting. Chapter 1 shows that the qualitative WES survey can produce accurate directional macroeconomic forecasts for the USA by combining the ROC curves analysis with contingency tables, and that the ROC-optimal thresholds yield more accurate predictions than the alternatives in Hutson et al. (2014). Chapter 2 re-examines indicators of currency crises from Kaminsky and Reinhart (1999) and subsequent studies using the ROC curves analysis and shows that the ROC-optimal thresholds issue more accurate signals than the minimum noise-to-signal ratio previously used in the literature. Modified ROC curves display the relationship between the precision of sent signals and the recall of crisis episodes. Forecast combinations using several ad-hoc rules help to improve forecast accuracy. Chapter 3 highlights asymmetric information about the U.S. economy between the Federal Reserve System (FRS) and the Survey of Professional Forecasters (SPF) via textual analysis of the Federal Open Market Committee (FOMC) minutes. It shows that the SPF forecasters pay close attention to the FOMC minutes available to them at the time of the forecast deadline and efficiently use its information in their set. Yet, they could improve their forecasts should the FOMC minutes from the first quarterly meetings become available without a three-week publication lag. However, during their second quarterly meetings, the FOMC policy-makers accounted only for their own earlier assessment of the U.S. macroeconomy – they did not put weight on the SPF forecasts released a few weeks earlier in the same quarter.
Keywords: Forecasting; macroeconomics; international finance; rare events; forecasts accuracy; forecasts evaluation; GDP; currency crises; real exchange rate (RER); trend; foreign reserves, broad money (M2); the ratio of broad money to reserves; exports; World Economic Survey (WES); Federal Reserve System (FRS); Survey of Professional Forecasters (SPF); SPF forecasters; Federal Open Market Committee (FOMC); FOMC minutes; Greenbook (GB); GB forecasts; elicit casts; textual analysis; non-parametric methods; leading indicators; binary indicators; Receiver Operating Characteristic (ROC) curves; ROC-optimal thresholds; ROC curves analysis; in-sample predictive value; out-of-sample predictive value; signal approach; precision; recall; true positive rate; false positive rate; true negative rate; false negative rate; economic surveys; consumer surveys; business tendency surveys; qualitative surveys; quantitative surveys; contingency table; present economic conditions; future economic conditions; regression approach; balance statistics; probability approach; forecast error; consensus scores; forecasting rule; directional accuracy; accuracy ratio; probability of detection; classifier; informative classifier; random guess; J-index; threshold; area under the curve (AUC); future expectations; Early Warning Indicators (EWIs); encompassing tests; rationality tests; orthogonality tests; forecasts unbiasedness; forecasts efficiency. (search for similar items in EconPapers)
JEL-codes: C14 C18 C23 C44 C52 C53 E17 E52 E58 E65 E66 F31 F37 F43 F47 (search for similar items in EconPapers)
Date: 2018-03-28
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)
Downloads: (external link)
https://mpra.ub.uni-muenchen.de/117706/1/Bespalova_CCAS_PhDThesis_2018_ETD.pdf original version (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:pra:mprapa:117706
Access Statistics for this paper
More papers in MPRA Paper from University Library of Munich, Germany Ludwigstraße 33, D-80539 Munich, Germany. Contact information at EDIRC.
Bibliographic data for series maintained by Joachim Winter ().