|
|
Classification based on longitudinal observations
Bandas, Lukáš ; Komárek, Arnošt (advisor) ; Kulich, Michal (referee)
The concern of this thesis is to discuss classification of different objects based on longitudinal observations. In the first instance the reader is introduced to a linear mixed-effects model which is useful for longitudinal data modeling. Description of discriminant analysis methods follows. These methods ares usually used for classification based on longitudinal observations. Individual methods are introduced in the theoretic aspect. Random effects approach is generalized to continuous time. Subsequently the methods and features of the linear mixed-effects model are applied to real data. Finally features of the methods are studied with help of simulations.
|
|
|
Bayesian Statistics - Limits and its Application in Sociology
Krčková, Anna ; Soukup, Petr (advisor) ; Hendl, Jan (referee)
The purpose of this thesis is to find how we can use Bayesian statistics in analysis of sociological data and to compare outcomes of frequentist and Bayesian approach. Bayesian statistics uses probability distributions on statistical parameters. In the beginning of the analysis in Bayesian approach a prior probability (that is chosen on the basis of relevant information) is attached to the parameters. After combining prior probability and our observed data, posterior probability is computed. Because of the posterior probability we can make statistical conclusions. Comparison of approaches was made from the view of theoretical foundations and procedures and also by means of analysis of sociological data. Point estimates, interval estimates, hypothesis testing (on the example of two-sample t-test) and multiple linear regression analysis were compared. The outcome of this thesis is that considering its philosophy and thanks to the interpretational simplicity the Bayesian analysis is more suitable for sociological data analysis than common frequentist approach. Comparison showed that there is no difference between outcomes of frequentist and objective Bayesian analysis regardless of the sample size. For hypothesis testing we can use Bayesian credible intervals. Using subjective Bayesian analysis on...
|
|
|
Stochastic Loss Reserving Models
Košová, Nataša ; Justová, Iva (advisor) ; Cipra, Tomáš (referee)
In present thesis we study and describe a stochastic loss reserve model for individual insurers. Specifically, it is the model based on the three following features. Modelling of expected claims depends on unknown parameters which estimates need to be the most accurate. Aggregated occurred and paid losses for particular years are modelled by a collective risk model. The final reserve is estimated by Bayesian methodology that uses a prior information from a significant number of insurers. Part of the thesis is also an implementation of the program that calculates reserves by using our model and its testing on simulated data.
|
|
|
Introduction to Bayesian Statistics
Chuchel, Karel ; Komárek, Arnošt (advisor) ; Hušková, Marie (referee)
The aim of this thesis is to cover the basics of Bayesian inference. Bayesian logic is to consider parameter as a random variable with specific prior distribution. Prior distrubution can be chosen from wide range of possibilities. In this thesis miscellaneous choices of prior distribution are discussed and are followed with many examples. The another part of thesis concerns with building Bayesian point and interval estimates. Everything is compared to classical approach towards statistics. Last section shows the application of previous topics on real data.
|
|
|
Classification based on longitudinal observations
Bandas, Lukáš ; Komárek, Arnošt (advisor) ; Kulich, Michal (referee)
The concern of this thesis is to discuss classification of different objects based on longitudinal observations. In the first instance the reader is introduced to a linear mixed-effects model which is useful for longitudinal data modeling. Description of discriminant analysis methods follows. These methods ares usually used for classification based on longitudinal observations. Individual methods are introduced in the theoretic aspect. Random effects approach is generalized to continuous time. Subsequently the methods and features of the linear mixed-effects model are applied to real data. Finally features of the methods are studied with help of simulations.
|
guest ::
