|
Clustering and regression analysis of micro panel data
Sobíšek, Lukáš ; Pecáková, Iva (advisor) ; Komárek, Arnošt (referee) ; Brabec, Marek (referee)
The main purpose of panel studies is to analyze changes in values of studied variables over time. In micro panel research, a large number of elements are periodically observed within the relatively short time period of just a few years. Moreover, the number of repeated measurements is small. This dissertation deals with contemporary approaches to the regression and the clustering analysis of micro panel data. One of the approaches to the micro panel analysis is to use multivariate statistical models originally designed for crosssectional data and modify them in order to take into account the within-subject correlation. The thesis summarizes available tools for the regression analysis of micro panel data. The known and currently used linear mixed effects models for a normally distributed dependent variable are recapitulated. Besides that, new approaches for analysis of a response variable with other than normal distribution are presented. These approaches include the generalized marginal linear model, the generalized linear mixed effects model and the Bayesian modelling approach. In addition to describing the aforementioned models, the paper also includes a brief overview of their implementation in the R software. The difficulty with the regression models adjusted for micro panel data is the ambiguity of their parameters estimation. This thesis proposes a way to improve the estimations through the cluster analysis. For this reason, the thesis also contains a description of methods of the cluster analysis of micro panel data. Because supply of the methods is limited, the main goal of this paper is to devise its own two-step approach for clustering micro panel data. In the first step, the panel data are transformed into a static form using a set of proposed characteristics of dynamics. These characteristics represent different features of time course of the observed variables. In the second step, the elements are clustered by conventional spatial clustering techniques (agglomerative clustering and the C-means partitioning). The clustering is based on a dissimilarity matrix of the values of clustering variables calculated in the first step. Another goal of this paper is to find out whether the suggested procedure leads to an improvement in quality of the regression models for this type of data. By means of a simulation study, the procedure drafted herein is compared to the procedure applied in the kml package of the R software, as well as to the clustering characteristics proposed by Urso (2004). The simulation study demonstrated better results of the proposed combination of clustering variables as compared to the other combinations currently used. A corresponding script written in the R-language represents another benefit of this paper. It is available on the attached CD and it can be used for analyses of readers own micro panel data.
|
|
Míry podobnosti pro nominální data v hierarchickém shlukování
Šulc, Zdeněk ; Řezanková, Hana (advisor) ; Šimůnek, Milan (referee) ; Žambochová, Marta (referee)
This dissertation thesis deals with similarity measures for nominal data in hierarchical clustering, which can cope with variables with more than two categories, and which aspire to replace the simple matching approach standardly used in this area. These similarity measures take into account additional characteristics of a dataset, such as frequency distribution of categories or number of categories of a given variable. The thesis recognizes three main aims. The first one is an examination and clustering performance evaluation of selected similarity measures for nominal data in hierarchical clustering of objects and variables. To achieve this goal, four experiments dealing both with the object and variable clustering were performed. They examine the clustering quality of the examined similarity measures for nominal data in comparison with the commonly used similarity measures using a binary transformation, and moreover, with several alternative methods for nominal data clustering. The comparison and evaluation are performed on real and generated datasets. Outputs of these experiments lead to knowledge, which similarity measures can generally be used, which ones perform well in a particular situation, and which ones are not recommended to use for an object or variable clustering. The second aim is to propose a theory-based similarity measure, evaluate its properties, and compare it with the other examined similarity measures. Based on this aim, two novel similarity measures, Variable Entropy and Variable Mutability are proposed; especially, the former one performs very well in datasets with a lower number of variables. The third aim of this thesis is to provide a convenient software implementation based on the examined similarity measures for nominal data, which covers the whole clustering process from a computation of a proximity matrix to evaluation of resulting clusters. This goal was also achieved by creating the nomclust package for the software R, which covers this issue, and which is freely available.
|
|
Differences between men and women in the Czech labour market
Stroukal, Dominik ; Kadeřábková, Božena (advisor) ; Pavelka, Tomáš (referee) ; Němec, Otakar (referee)
This thesis consists of five articles that apply current world research on labor economics at the Czech Republic and confirms the significant differences between men and women in this market. It shows that gender has a significant influence on the preference on the labor market and, consequently, on employment and health. First, the thesis shows that preferences are relevant determinant of career and then we study the difference in preference of salary for men and women. Subsequently it shows that gender plays a significant role in explaining the relationship between homeownership, and unemployment, as well as unemployment and health. The first chapter was able to demonstrate that the preference for a career has a positive influence on the choice of career. The influence of higher education on prioritizing career proved to be positive and significant. Probability of a career choice is reduced by the presence of children, however, is not dependent on their number, which is contrary to the theory of preferences. The second chapter shows that Czech women prefer more non-monetary rewards than men. It has also been shown that people with university education are same in the preferences of non-monetary rewards regardless of the gender of the respondents, however, compared to the world's research, the Czech higher education increases this preference. It turned out that women prefer risk less than men. The third chapter demonstrates that although the housing market undermines labor mobility and employment in the Czech Republic at the regional level, therefore, that in regions with a higher rate of home ownership is higher unemployment, at the individual level, the owners of housing are unemployed are less likely. The estimates are significantly different for men and women. Men living in owner-occupied housing have a higher likelihood of employment than women. At regional level, however, this thesis shows that the high rate of home ownership increases unemployment for both men and women, in the long run only to women. The fourth chapter showed that men transition to homeownership reduces the likelihood of unemployment next year. For women, this relationship has proved to be insignificant. In addition, as insignificant showed the opposite relationship, the transition from unemployment to the newly acquired home ownership. The last chapter shows that the change in the working status to unemployment will increase in the future probability of worse health. Influence in less than two years, however, proved to be significant. An important conclusion is that men have a significantly stronger relationship between health and unemployment than women.
|
|
Building and use of smaller computer networks
Kyzivát, Marek ; Pinkas, Otakar (advisor) ; Šmejkal, Ivo (referee)
The thesis describes the initial state of the computer network Basic Schools and Kindergartens Ohradní (ZŠMŠ Ohradní) in Prague 4 and then its reconstruction, which I largely contributed. ZŠMŠ Ohradní consists of four pavilions and from one building on the other side of the street. The aim of this study is to assess the initial state of the network and point out the shortcomings that we discovered. We found deficiencies in the operation stress tests, measurements and data cabling overall analysis. Original networks connectivity was 100Mb/s. Together with a colleague, we are network administrators. Furthermore, I am going to introduce a new form of network, which has identified deficiencies improved, by using on newer technologies. I will describe its structure, address allocation, active and passive components, and operated services. New network is capable of 1Gb/s, and its spine is going to be 10Gb/s soon. Benefits of this reconstruction is faster, more stable and more modern network that will facilitate the work of employees of ZŠMŠ Ohradní. To these improvements, I have mainly contributed by measurements. I participated in the design and implementation of new form of data network. I collaborated with fellow Poc to the configuration of active elements and network services in reconstructed network.
|
| |
|
Marketing strategy of amateur theatre Tleskejtekruciš
Rafaj, Martin ; Postler, Milan (advisor) ; Jarolímek, Petr (referee)
Main goal of this thesis is the identification and evaluation of marketing strategy of the amateur theatre Tleskejtekruciš and proposal of a new strategy, that will enable the development of the theatre in region of centre Bohemia. The thesis is split in two main parts. Goal of the theoretical part is to define marketing specifics of amateur theatre. Goal of the practical part is the analysis of current marketing strategy of the theatre Tleskejtekruciš in form of SWOT analysis, competition analysis, questionaire survey ans following recommendation of a enhanced marketing strategy, based on analysis results.
|
|
Design of processes of business department in IT company and measuring their performance
Schütz, Martin ; Oškrdal, Václav (advisor) ; Bruckner, Tomáš (referee)
The thesis deals with design of new processes of business department in IT company which provides server hosting, web hosting and domain registration services. These processes come from identification and analysis of current processes and the theory of business department management. Key Performance Indicators (KPIs) were set for selected processes which can be used for managing the company as a whole. Models of processes were created due to EPC notation. New processes were designed to continuously create data in CRM information system providing evidential and information support necessary for business department management, including the possibility of measuring its performance. Processes also automatize often repetitive activities and provide relevant information to other affected business units within the company. Contribution of the thesis lies in results of analysis of current identified processes containing solution proposals of discovered problems and newly created process models. Both can be used as a pattern for optimization of current processes in already existing organization or for designing new process models in new organization in the same or similar field of business.
|
|
Role of UNHCR in case of asylum seekers, refugees and stateless persons – the case study of Turkey
Unzeitigová, Klára ; Novotná, Markéta (advisor) ; Kuchařová, Alžběta (referee)
Inspired by the Kratochvíl, Cibulková and Beník´s model of actorness, the thesis explores the framing power of UNHCR. The critical discourse analysis introduced by Norman Fairclough is applied in order to analyze the textual, contextual and sociocultural dimension of the UNHCR framing power. The case of Turkey was chosen for this study due to the current situation and the fact that Turkey is one of the biggest hosting country in the refugees´ crisis. Through the critical discourse analysis, the thesis explores whether UNHCR is considered as a framing actor in the case of asylum seekers, refugees and stateless people in Turkey. The analysis shows that UNHCR is globally respected and takes important part in the issue. However, not all of the international organizations refer to UNHCR as the lawmaker and the initiator of debates in the issues mentioned above.
|
|
Zjednodušení kvantových obvodů pro modulární umocňování
Fišer, Petr ; Ivánek, Jiří (advisor) ; Nentvich, Libor (referee)
This thesis is based on top of the previous thesis "Security of modern encryption protocols" where we introduced a new paradigm for constructing quantum circuits. We have built circuits for modular arithmetic (addition, multiplication and exponentiation) in order to break El-Gamal asymmetric cryptosystem. Current thesis reviews all proposed circuits and discusses possibilities of their further optimization in goal of lowering the number of used qbits at least by an order of magnitude. It also shows that this is not possible due to existence of COPY gates which make the design inherently unoptimizable. Getting rid of COPY gates is, however, not possible without substantial rewrite of the whole paradigm. The overall estimate of number of qbits used in circuits thus remains O(log(m)log^2(N)) where m is a processed number and N is a modulus. The thesis also proposes optimization of the modular multiplication circuit that, if issues with COPY gates are resolved, allows us to lower the number of used qbits by about O(log(m)) at the price of a longer execution time.
|
|
CRM System Optimization
Fučík, Ivan ; Mildeová, Stanislava (advisor)
This thesis is focused on CRM solutions in small and medium-sized organizations with respect to the quality of their customer relationship. The main goal of this work is to design an optimal CRM solution in the environment of real organization. To achieve this goal it is necessary to understand the theoretical basis of several topics, such as organizations and their relationship with customers, CRM systems, their features and trends. On the basis of these theoretical topics it is possible to analyze current CRM solution in the organization. From the data obtained by the methods of observation and controlled interview it was possible to prepare a design for optimal CRM solution. This optimal solution comes also from user and organization requirements. The optimal CRM solution saves time and costs associated with current CRM solution and replaces existing and ineffective CRM tools.
|
guest ::
