|
|
Závislost na ropných výnosech, ceny ropy a měnové kurzy: analýza denních dat
Budkov, Roman ; Zouhar, Jan (advisor) ; Formánek, Tomáš (referee)
This paper studies the relationship between the oil prices and exchange rates of oil exporting countries, in terms of their dependence on oil rents. The study is based on data at the daily frequency over the period 2005-2015. In the first chapter, the data set and basic characteristics of the countries are described. The second chapter represents the econometric framework for the practical section. Applying a vector error correction model mainly produced controversial results. Analysis based on a GARCH approach found a positive relationship between the value of the currencies and the oil prices, although the link with the oil rents dependence is not sufficiently evident. The paper also supports stylized facts, such as a negative relationship between the U.S. dollar value and the oil prices.
|
|
|
Analysis of inflation in the Czech Republic
Holakovská, Adéla ; Formánek, Tomáš (advisor) ; Dlouhá, Zuzana (referee)
This work is focused on econometric analysis of inflation in the Czech Republic, there is also reported an analysis of inflation in Austria and continuity of both countries to the dominant German economy. The inflation with its forms and possibilities of measuring is described in the first part of this work. There is also mentioned the influence of Czech national bank on the inflation. Next, there is shown the impact of foreign exchange rates and inflation. Consequently there are described characteristics of time series, which are important from viewpoint of construction of econometric models. Next, there is described theory of econometrics analysis, focused on ordinary least squares method and method of instrumental variables. The empirical part contains econometric analysis of inflation itself, using models described in theoretical part. Moreover, this work includes other models, coming out of economic hypothesis. Firstly, it analyses inflation in Germany as the reference country. Secondly, further analysis performs inflation in the Czech Republic and Austria. Finally, an analysis based on ERPT (exchange rate pass-through) models is given. In conclusion, the results are well summarized and compared.
|
|
|
Econometric analysis of the prices of mobile phones
Nešpor, Radim ; Formánek, Tomáš (advisor) ; Polonyankina, Tatiana (referee)
The work deals with the econometric analysis of the prices of mobile phones based on the selected parameters. The aim of this thesis is to determine, which of the selected parameters affect the price of a new mobile phone and how they affects the price. The theoretical part deals at first with the regression model and determining statistically significant variables and significance of the model as a whole. Then I introduce different procedures for finding and selecting the best estimate for the model. In this thesis I will focus on three procedures for the selection of explanatory variables: best subset selection, forward stepwise selection and backward stepwise selection. Finally I mention the detection of multicollinearity and heteroscedasticity testing. In the second part, I apply different procedures for the selection of explanatory variables and afterwards, based on the criteria defined in the first part, I will select the best model. Finally, I compare these models and choose the best one.
|
|
|
Econometric analysis of inflation in open economy
Rebrova, Yulia ; Formánek, Tomáš (advisor) ; Kuchina, Elena (referee)
This bachelor thesis is focused on an econometric analysis of the inflation in an open economy. The aim of this paper is to investigate factors which influence the price level. A priority is given to the analysis of Austrian and Czech economies and of their dependence on the dominant German economy. Different specifications of Phillips curve and Exchange Rate Pass-Through method are used to breakdown the inflation rate. Theoretical part of the thesis carefully summarizes already known facts about inflation and its measuring. Moreover, it includes a closer look at econometrical models which will be used in this paper. The models for each country are developed and compared in the last part of this thesis. Results show that economies of selected countries underline macroeconomic theory and the inflation rate can be expressed by Phillips curve whereas Exchange Rate Pass-Through models cannot explain the behavior of the price level well. This paper reveals the complexity of the topic.
|
|
|
Ekonometric analysis of housing units prices in Prague
Garančovský, René ; Formánek, Tomáš (advisor) ; Frýd, Lukáš (referee)
The aim of this thesis is to find indicators that have a significant impact on the price of housing units in Prague. It will also be a comparison with analyses already done. My analysis is based on a sample of housing units and their data from real estate market. It is based on econometric analysis. The work is divided into four chapters, of which the first and second are theoretical and third and fourth carries a practical point. The first chapter is devoted to the basic description of the characteristics of housing units and territorial connection. In the second chapter we describe used econometric techniques. Into third chapter we enter outputs, made by us in eviews. In the fourth and final chapter we describe, disassemble, compare and analyse individual results of the preceding chapter.
|
|
|
Odhad zajišťovacího poměru: srovnání konstantních metod odhadu založených na MNČ, ARCH a GARCH
Paříková, Adéla ; Černý, Michal (advisor) ; Formánek, Tomáš (referee)
Volatile prices of commodities relate to financial risk faced by individuals or economic subjects exposed to them. One way to minimize the impact of change in market price is to use its hedging by futures contracts. The optimal hedge ratio estimation (ratio between units of spot and futures contracts) is the focus of this study. Its objective is to compare hedge ratios based on minimum variance methodology using three methods - OLS, ARCH and GARCH, by measuring their hedging effectiveness using variance and value at risk reduction. The results differ across commodities, however several conclusions can be made. The ARCH-based hedge ratios do not perform significantly worse than the GARCH-based hedge ratios. The same estimation method can be used for assets having similar returns development and a well performing hedge can be expected. Results of hedge ratios of strongly correlated assets estimated by different methods tend to have very similar values to one another and to the related correlation coefficient. More generally, the best performing hedge ratios are those having very similar values to correlation between spot and futures 1-day returns.
|
|
|
Econometric analysis of the economy in game World of Warcraft
Buchníčková, Michaela ; Kuchina, Elena (advisor) ; Formánek, Tomáš (referee)
This thesis analyses the impact of real exchange rate and the official exchange ratio of fiat currencies and in-game golds on the price level in the game World of Warcraft. The work also includes a brief summary of the mechanisms of the in-game economy. The analysis is based on cointegration test and Granger causality test. Individual estimations are model based on the VAR and VEC models theory. The conclusions of this study are made for specific randomly selected pairs of servers with different populations. These results are not easily generalized for the entire regions, but they offer insight into the possible factors affecting the price level in each virtual economy. The results show that the price level on the American server Aegwynn affects the exchange rates of fiat and game currencies as well as that game currency exchange rate in the European region is sensitive to changes in exchange rates of the euro and the yuan. All calculations in this work were implemented in Eviews 8 software.
|
|
|
An analysis of individual efforts of NHL players
Houdek, Jakub ; Černý, Michal (advisor) ; Formánek, Tomáš (referee)
The thesis is focused on application of econometric methods in the area of sport statistics, specifically in the area of ice hockey. Datasets were extracted from the National Hockey League (NHL) website, from the RTSS (Real Time Scoring System) from seasons 2002/2003 to 2014/15 by using the R package nhlscrapr. The Analysis of these datasets is based on previous work by Brian Macdonald [1]. The result is an adjusted +/- statistics (plus - minus), which describes the individual performance of each player. These statistics were later used for an estimation of probability of advance of selected teams to the playoffs, assuming the selected team uses anticipated players. These estimations were obtained by usage of logistic regression. It was found out, that the predictive ability of these models is weak.
|
|
|
Analysis of migration in the Czech Republic on the district level
Houšková, Helena ; Formánek, Tomáš (advisor) ; Dlouhá, Zuzana (referee)
This bachelor thesis focuses on internal migration in the Czech Republic on the district level. The aim of the thesis is to explain the relative number of immigrants to particular districts, relative number of emigrants from districts and mainly their difference - growth in the year 2013 with the help of different factors, such as criminality, unemployment, area, and so on. The factors are named and their influence on the relative number of immigrants, emigrants and growth is predicted. Then these data are analysed and three different models are constructed to explain the growth of population. In the first model all districts are taken into account. In the second model three districts of Prague are removed and in the last one, in addition to Prague, central districts of Brno and Ostrava are also removed. After comparing the three models we find out that models are quite similar and not all factors influence the growth of population as we expected.
|
|
|
The Estimation of Probability of Default Using Logistic Regression
Chalupa, Tomáš ; Dlouhá, Zuzana (advisor) ; Formánek, Tomáš (referee)
The aim of this work is to develop a suitable model that estimates a probability of default of client's loan. As estimation method was used a logistic regression and a probit regression and two definitions of default, 60 and 90 days overdue. The work describes the method of construction, estimation and testing of scoring models and a structure of dataset, which was used in the practical part. Firstly, it was created a theoretical model that was later confronted with estimates. Estimated models were compared by described statistics as McFadden R^2, the ability to diversify was investigated by the Lorenz curve and by the Gini coefficient. It was found that the logistic and the probit regressions have almost the same results, and that 90 days is preferable definition of default than 60 days.
|
guest ::
