
Setting of the exposition limit for brokerage companies using risk quantifying methods
Nováková, Kateřina ; Zouhar, Jan (advisor) ; Holý, Vladimír (referee)
This thesis is focused on brokerage companies, the middlemen of investors' demands for buying and selling currency pair, and their problems of determining the proper limit on their currency exposition. The limit value has an influence on company's gains and losses resulting from exchange rate movement. The thesis describes a method how to quantify the risk of loss utilizing common financial indicators like Value at Risk and Expected Shortfall. The aim of the~thesis is to describe how to estimate these indicators. Real data supplied by brokerage company are used for calculation. The replication method is applied for determining the values of indicators, data for calculation are stochastically simulated. All calculations are implemented in R.


Empirical comparison of imputation methods for missing values in data
Ostrenska, Alona ; Holý, Vladimír (advisor) ; Zouhar, Jan (referee)
Missing values are present in all types of data such as different surveys, socioscientific information etc. In many applications, it is necessary to replace missing observations to maintain the size of the dataset needed for the statistics. This bachelor thesis at first place introduce the categories of causes of missing data and the problems connected with them. The next step is to acquaint with common methods of imputation of missing values and the explanation of applicating those methods on real data in the context of linear regression. Then the assumptions of linear regression models that are based on data with artificially created missing observations are verified. These observations are removed using the mentioned mechanisms and different proportion of missing, with seven subsequent imputation methods. Regression models constructed based on such imputed datasets are then statically verified. Finally, imputation models are compared using different statistics and visualizations and is suggested possible solution  particular methods in case of a real problem of incomplete data.


Implementation of Heuristics for Vehicle Routing Problem with Time Windows
Trunda, Otakar ; Pelikán, Jan (advisor) ; Holý, Vladimír (referee)
Vehicle Routing Problem with Time Windows is a hard optimization problem. Even though it has numerous practical applications, the question of solving it efficiently has not been satisfyingly solved yet. This thesis studies the Vehicle Routing Problem with Time Windows and presents several new algorithms for solving it. There are two heuristics presented here, as well as several more complex algorithms which use those heuristics as their components. The efficiency of presented techniques is evaluated experimentally using a set of test samples. As a part of this thesis, I have also developed a desktop application which implements presented algorithms and provides a few additional features useful for solving routing problems in practice. Among others, there is a generator of pseudorandom problem instances and several visualization methods.


The Lasso and its application to time series
Holý, Vladimír ; Prášková, Zuzana (advisor) ; Hendrych, Radek (referee)
This thesis first describes the Lasso method and its adaptive improvement. Then the basic theoretical properties are shown and different algorithms are introduced. The main part of this thesis is application of the Lasso method to AR, MA and ARCH time series and to REGAR, REGMA and REGARCH models. An algorithm of the adaptive Lasso in a more general time series model, which includes all above mentioned models and series, is developed. The properties of methods and algorithms are shown on simulations and on a practical example. Powered by TCPDF (www.tcpdf.org)


Tests in multinomial distribution
Holý, Vladimír ; Anděl, Jiří (advisor) ; Antoch, Jaromír (referee)
In this paper there are at first described classical goodnessoffit tests  the Pear son's χ2 test and the log likehood ratio test. The more modern method of testing is the family of statistics based on power divergence which is generalisation of classical statistics. Another type of generalisation is the family of disparity statis tics which includes beside the family of power divergence also the families BWHD and BWCS. It is demonstrated that all these test statistics have an asymptotic χ2 distribution. In the program R the exact level and exact power can be calculated for individual tests. Hereafter, moments of test statistics can be derived. On the basis of these comparisons there will be shown which test statistics are the most suitable for the goodnessoffit tests. 1


Creation of a Client Database for a Financial Advisor
Holý, Vladimír ; Holá, Lucie (referee) ; Luhan, Jan (advisor)
This bachelor´s thesis deals with the formation of the database application in Microsoft Access 2003 that will serve to the financial advisors to make their communication with customers easy and faster. The contents include the formation of the proposal, charts, forms, arrangements and the visual database setting. The last part of the solution proposal deals with the important asset.


Use of Benford's Law in election results analysis
Pikhart, Miroslav ; Holý, Vladimír (advisor) ; Zouhar, Jan (referee)
The topic of the thesis is introduction to Benford's law and its usage in forensic data analysis. First part of the thesis covers the theoretic basics and explains how conformity is tested. All introduced tests are then applied in second part, which works with two independent datasets. Russian presidental elections 2012, where several scientific articles discuss whether there was foul play involved or not. In comparsion, the second dataset contains czech presidental elections 2013, where no suspicions were ever raised. Both datasets are analyzed using the R software and it is shown that while the czech data indeed conforms to Benford's law, the russian data shows no conformity whatsoever. Also a mistake in one of the R packages used is found and an update is suggested.
