Work detail

GDPNow for the Czech Republic

Author: Mgr. Jan Kutman
Year: 2022 - winter
Leaders: prof. PhDr. Tomáš Havránek Ph.D.
Consultants:
Work type: Finance, Financial Markets and Banking
Masters
Language: English
Pages: 93
Awards and prizes: Deloitte Outstanding Thesis Award.
Link: https://dspace.cuni.cz/handle/20.500.11956/171343
Abstract: The gross domestic product (GDP) is an essential measure of the state of economic activity
and serves as a crucial tool for policymakers, investors, or businesses. However, the official
GDP estimate in the Czech Republic is only available with a lag of approximately 60 days, and
the Czech National Bank (CNB) announces its GDP forecast once in each quarter. This thesis
focuses on predicting GDP growth in the current quarter, referred to as nowcasting. I employ
several methods to nowcast the real GDP growth in the Czech Republic in a pseudo-real-time
setting and compare their performance. Additionally, I investigate the possibility of creating
an ensemble model by using a weighted average of several nowcasting models. The results
suggest that the Dynamic Factor Model (DFM) performs best in the GDP nowcasting task, and
its predictive accuracy is comparable with the official CNB nowcast. Furthermore, the model
averaging process yields accuracy close to the best individual model while addressing model
uncertainty. The GDP nowcast of the DFM will be made available to the public in real-time on
a website and updated with a daily frequency.
August 2022
MonTueWedThuFriSatSun
1234567
891011121314
15161718192021
22232425262728
293031    

Partners

Deloitte

Sponsors

CRIF
McKinsey
Patria Finance
Česká Spořitelna
EY