Statistická analýza cenzorovaných dat
Loading...
Date
Authors
Bah, Abdoulie B
ORCID
Advisor
Referee
Mark
C
Journal Title
Journal ISSN
Volume Title
Publisher
Vysoké učení technické v Brně. Fakulta strojního inženýrství
Abstract
This thesis deal with the statistical analysis of censored data by means of simulation studies on the weibull, log-Normal, and gamma distributions. The simulations are carry out by 10,000 repetitions at different parameter settings, sample sizes (n) and censoring schemes. For to all distributions, the obtained results exhibit the accuracy of parameters for larger sample sizes (n), as well as the reliability of parameters to different combinations of the parameters values. The results support the idea that sample size is a key factor in the enhancement of the accuracy of the parameter estimates in the cases of censored data, detailed simulation results are provided including tables and figures illustrating the estimator’s behaviour under different conditions. These findings offer valuable insights for statistical inference involving censored data in various practical applications.
This thesis deal with the statistical analysis of censored data by means of simulation studies on the weibull, log-Normal, and gamma distributions. The simulations are carry out by 10,000 repetitions at different parameter settings, sample sizes (n) and censoring schemes. For to all distributions, the obtained results exhibit the accuracy of parameters for larger sample sizes (n), as well as the reliability of parameters to different combinations of the parameters values. The results support the idea that sample size is a key factor in the enhancement of the accuracy of the parameter estimates in the cases of censored data, detailed simulation results are provided including tables and figures illustrating the estimator’s behaviour under different conditions. These findings offer valuable insights for statistical inference involving censored data in various practical applications.
This thesis deal with the statistical analysis of censored data by means of simulation studies on the weibull, log-Normal, and gamma distributions. The simulations are carry out by 10,000 repetitions at different parameter settings, sample sizes (n) and censoring schemes. For to all distributions, the obtained results exhibit the accuracy of parameters for larger sample sizes (n), as well as the reliability of parameters to different combinations of the parameters values. The results support the idea that sample size is a key factor in the enhancement of the accuracy of the parameter estimates in the cases of censored data, detailed simulation results are provided including tables and figures illustrating the estimator’s behaviour under different conditions. These findings offer valuable insights for statistical inference involving censored data in various practical applications.
Description
Keywords
Censored data, Weibull distribution, Log-Normal distribution, Gamma distribution, Parameter estimation, Scale parameter, Shape parameter, Simulation study, Maximum likelihood estimation, Fisher information matrix, musk Compound, Censored data, Weibull distribution, Log-Normal distribution, Gamma distribution, Parameter estimation, Scale parameter, Shape parameter, Simulation study, Maximum likelihood estimation, Fisher information matrix, musk Compound
Citation
BAH, A. Statistická analýza cenzorovaných dat [online]. Brno: Vysoké učení technické v Brně. Fakulta strojního inženýrství. 2024.
Document type
Document version
Date of access to the full text
Language of document
en
Study field
bez specializace
Comittee
doc. Ing. Luděk Nechvátal, Ph.D. (předseda)
prof. RNDr. Miloslav Druckmüller, CSc. (místopředseda)
prof. Mgr. Pavel Řehák, Ph.D. (člen)
doc. RNDr. Jiří Tomáš, Dr. (člen)
doc. Mgr. et Mgr. Aleš Návrat, Ph.D. (člen)
Mariapia Palombaro (člen)
Gennaro Ciampa (člen)
Matteo Colangeli (člen)
Carmela Scalone (člen)
Date of acceptance
2024-10-04
Defence
The student presented his master's thesis on the topic: Statistical analysis of censored data. The student presented the work, and then the reviews of the supervisor and opponent were read. The student answered the opponent's questions and explained ambiguities.
doc. Tomáš asked if any other than the presented probability distributions was considered, and the student answered that no other distribution was studied.
Mariapia Palombaro asked question on the applicability of the research, and the student gave an example of an application.
Result of defence
práce byla úspěšně obhájena
Document licence
Standardní licenční smlouva - přístup k plnému textu bez omezení