|
|
Predicting Czech Economic Activity Using Toll Data
Učňová, Jana ; Kocourek, David (advisor) ; Šestořád, Tomáš (referee)
Many analysts coincide that transportation is closely linked to economic activity. How- ever, data containing information about transportation have not been part of their re- search for a long time. Introduction of electronic toll collection systems in recent years led to a new source of data containing information about truck transport. This thesis aims to examine the ability of seasonally adjusted toll data to predict Czech economic activity. Economic activity is represented by four variables - real GDP, nominal GDP, in- dustrial production index and the volume of foreign trade. Seven models - five dynamic models, ARIMA model, and regression with ARIMA error - are constructed for each dependent variable. These models are then compared using both Akaike and Bayesian information criterion and the most appropriate model for each dependent variable is selected. It was concluded that both real GDP and industrial production index can be predicted using toll data. Both the number of kilometers travelled, and the amount of toll collected seems to be good predictors of economic activity. Particularly, data con- taining information about toll collected might be more beneficial because the amount of toll collected in given quarter can even predict economic activity in the next quarter. 1
|
|
|
Risk factor modeling of Hedge Funds' strategies
Radosavčević, Aleksa ; Princ, Michael (advisor) ; Šopov, Boril (referee)
This thesis aims to identify main driving market risk factors of different strategies implemented by hedge funds by looking at correlation coefficients, implementing Principal Component Analysis and analyzing "loadings" for first three principal components, which explain the largest portion of the variation of hedge funds' returns. In the next step, a stepwise regression through iteration process includes and excludes market risk factors for each strategy, searching for the combination of risk factors which will offer a model with the best "fit", based on The Akaike Information Criterion - AIC and Bayesian Information Criterion - BIC. Lastly, to avoid counterfeit results and overcome model uncertainty issues a Bayesian Model Average - BMA approach was taken. Key words: Hedge Funds, hedge funds' strategies, market risk, principal component analysis, stepwise regression, Akaike Information Criterion, Bayesian Information Criterion, Bayesian Model Averaging Author's e-mail: aleksaradosavcevic@gmail.com Supervisor's e-mail: mp.princ@seznam.cz
|
guest ::
