|
|
Selected aspects of robust regression and comparison of robust regression methods
Černý, Jindřich ; Blatná, Dagmar (advisor) ; Vrabec, Michal (referee) ; Dohnal, Gejza (referee)
This dissertation examines the robust regression methods. The primary purpose of this work is to propose an extension, derivation and summary (including computational algorithm) for Theil-Sen's regression estimates (or in some literature also referred to as Passing-Bablok's regression method) for multi-dimensional space and compare this method to other robust regression methods. The combination of these two objectives is the primary and the original contribution of the dissertation. Based on the available literature it is unknown if anyone has discussed this problem in greater depth and solved it in total. Therefore this work provides a summary overview of the issue and offers a new alternative of this multidimensional, nonparametric, robust regression method. Secondary goals include a clear summary of other robust methods, a summary of findings related to these robust regression methods, robust methods compared with each other placing emphasis on the comparison with the proposed Theil-Sen's regression estimates method and with the least squares method. The summary also includes individual mathematical context and interchangeability of the proposed methods. These secondary objectives are also another benefit of this dissertation in the field of robust regression problems; this is especially important to gain a unified view of the problems of robust regression methods and estimates in general.
|
|
| |
|
|
Possibilities of use of program R in the regression and contingency Possibilities of use of program R in the regression and contingency analysis
Ballarinová, Marie ; Blatná, Dagmar (advisor) ; Plašil, Miloslav (referee)
The aim of this bachelor thesis is to introduce the basics of the statistical program R and its application to regression and contingency analysis. The work focuses on basic user skills with data processing in the program R. The program is evaluated from many perspectives (eg, program benefits, data processing in R, working with PivotTables in R, graphs in R, import and export data, etc. .). Both analyses in this work are used for demonstration of commands and syntax for these statistics. The contribution of this work is to raise awareness about the great usefulness of the program and highlight the different functions both the analysis and the basis for statistical data processing. The main part of this work is focused on commands that can be applied directly to the command line in R in practice. The structure is divided into five main chapters. The first and second chapters provide a basic description of regression analysis and contingency. The third chapter introduces the syntax, commands and technical aspects of the program R. In the fourth and fifth chapter is application of both analyses in the program R. In the regression analysis is used simple and multiple regression analysis. The main scope of contingency analysis is working with data using tables in the program R.
|
|
|
Nonparametric tests in SPSS
Kantorová, Petra ; Pecáková, Iva (advisor) ; Blatná, Dagmar (referee)
This bachelor thesis deals with description of nonparametric tests, which we can find in so called statistical packet SPSS. The first part of the thesis covers examples of this specific kind of tests (nonparametric tests), selected according to different features, its characteristics and individual steps of testing this kind of hypotheses. In the second part the reader can find me-thods of how we can use this kind of tests in SPSS. The third and last part of the bachelor thesis offers practical application and comparison of outcomes of nonparametric test.
|
|
|
Nonparametric tests in statistical software
Skolil, Lukáš ; Blatná, Dagmar (advisor) ; Nenadál, Karel (referee)
Cílem této diplomové práce je praktické i teoretické seznámení uživatelů neparametrických metod s několika vybranými statistickými programy, v nichž je možné neparametrické analýzy provádět. Nedílnou součástí cíle je i porovnání těchto programů. V teoretické části jsou stručně popsány základy testování statistických hypotéz a teorie neparametrických testů. V praktické části jsou prozkoumány programy NCSS 2007, Statistica 7, SPSS 15, Systat 12, Stagraphics Centurion XV, Minitab 15, S-Plus 6.2, SAS 9.1 a StatXact 7. U každého software jsou popsány neparametrické testy, které obsahuje, a zjednodušeně i vkládání dat a výstupy. Nakonec jsou vybrané programy porovnány z několika hledisek. Všechny vybrané programy obsahují značné množství neparametrických testů a liší se většinou jen v detailech. Pro většinu analýz není potřeba hledat speciální programy a dají se použít všechny vybrané, pouze pro porovnávání rozptylů je nutné použít buď SAS nebo StatXact, protože v jiných programech ve výběru tyto testy nenalezneme.
|
guest ::
