|
|
Forecasting Czech GDP Using Mixed-Frequency Data Models
Franta, Michal ; Havrlant, David ; Rusnák, Marek
In this paper we use a battery of various mixed-frequency data models to forecast Czech GDP. The models employed are mixed-frequency vector autoregressions, mixed-data sampling models, and the dynamic factor model. Using a dataset of historical vintages of unrevised macroeconomic and financial data, we evaluate the performance of these models over the 2005–2012 period and compare them with the Czech National Bank’s macroeconomic forecasts. The results suggest that for shorter forecasting horizons the accuracy of the dynamic factor model is comparable to the CNB forecasts. At longer horizons, mixed-frequency vector autoregressions are able to perform similarly or slightly better than the CNB forecasts. Furthermore, moving away from point forecasts, we also explore the potential of density forecasts from Bayesian mixed-frequency vector autoregressions.
Fulltext:  PDF
|
|
| |
|
|
Analysis of the Price Convergence of CR towards EU
Havrlant, David ; Pánková, Václava (advisor) ; Mandel, Martin (referee) ; Singer, Miroslav (referee)
The price level convergence of the transition economies towards the reference economies is linked to the relative price of nontradables, which is explained by the total factor productivity differentials in tradable and nontradable sector. Basic concept is offered by the Balassa Samuelson model and its modifications. Testable equations are derived from these models, and the panel data approach is applied for their estimation. The results indicate faster growth of the relative price of nontradables in transition economies as succession of higher growth rate of the total factor productivity in tradable sector. Hence estimated models confirm the price level convergence of transition economies towards the reference economies. The analyses of price dynamics of the complementary field, i. e. of the tradables, follows, and the basic concept is represented by the rational bubble hypothesis. The stress is putted on the impact of the word prices on the price levels of the Czech Republic. After a cointegration analysis of the time series is carried out, the influence of the word prices of tradable commodities is estimated within a vector error correction model and regression analysis. This cost factors analysis is afterwards related to the export dynamics of the Czech Republic, and models suitable for quantitative analysis of export dynamics as well as its prediction based on vector error correction model and regression analysis are evaluated. Their forecasting ability is assessed within a simulation of ex-post forecasts and a root mean squared error. The aim is to consider the relationship between the price levels and the export dynamics, for the relation of both variables evaluated within the Granger causality seems to be less straightforward then the standard export equations suggest, and the estimated equations confirm significant influence of the export dynamics on the price level.
|
|
|
Modelování měnového kursu – parity a česká koruna
Mäsiarová, Jana ; Pánková, Václava (advisor) ; Havrlant, David (referee)
The paper analyses validity of main exchange rate theories in case of the Czech crown. Investigated relationships comprise purchasing power parity, interest rate parity and real interest monetary model. Technical part of the analysis involves cointegration, namely Johansen's method based on vector autoregressive models. Two currency pairs are in the focus: CZK/EUR and CZK/USD. Empirical calculations did not prove the absolute validity of the theories but pointed out to other factors of exchange rate, such as convergence process, impacts on inflation targeting decisions, non-monetarist determinants and the recent financial crisis.
|
|
|
Konvergence cenové hladiny České republiky k zemím EU na základě Balassova-Samuelsonova modelu
Havrlant, David ; Jablonský, Josef (advisor)
Konvergence cenové hladiny České republiky ke státům Evropské unie je posuzována prostřednictvím relativní ceny neobchodovatelných statků. Dynamika relativní ceny neobchodovatelných statků je vysvětlena vývojem celkové produktivity faktorů v obchodovatelném a neobchodovatelném sektoru. Výchozí koncepci poskytuje Balassův-Samuelsonův model a jeho modifikace, z nichž jsou odvozeny experimentálně ověřované regresní rovnice. Z výsledků je patrné, že relativní cena neobchodovatelných statků roste v České republice v závislosti na růstu kapitálové zásoby prokazatelně vyšším tempem než v Německu a EU15, a to zejména v důsledku relativně vyšší citlivosti celkové produktivity faktorů v obchodovatelném sektoru. Odhadnuté modely tedy potvrzují konvergenci cenové hladiny České republiky k Německu a EU15.
|
|
| |
|
|
Models with rational expectation.
Bechyňák, Petr ; Pánková, Václava (advisor) ; Havrlant, David (referee)
Práce popisuje vývoj konceptu mekonomického očekávání od extrapolativního, přes adaptivní až po racionální, včetně modelů, v nichž byla tato očekávání použita. V druhé části je odvozen a popsán model, využívající právě racionální očekávání. Tento agregovaný makroekonomický model je pak aplikován na prostředí ČR. Je zde testován i samotný předpoklad racionálního očekávání, což je myšlenka novější, než samotný model.
|
guest ::
