|
Testování homogenity a dobré shody v analýze přežití
Timková, Jana
The present paper deals with the goodness of fit and the twosample problem related to the event-history type data. The proposed methods are derived from bayesian nonparametric approach and take advantage of MCMC estimation of the hazard rate. The technique is based on Bayes construction of martingale residuals.
|
|
O vybraných modelech pro částečnou obnovu
Ševčík, Jaroslav ; Volf, Petr
Models of imperfect repairs are based on the reduction of cumulated hazard rate, either directly or indirectly. Other set of models connects the repair with the change of time scale. Further, repair degree can be connected with the reduction of the deterioration. We discuss mainly the question of repair schemes, their consequences, and possibilities of an 'optimal' repair policy leading to the hazard rate stabilization.
|
| |
| |
| |
| |
| |
|
Gene Expression Data Analysis for in Vitro Toxicology
Šimeček, Petr
Microarray analyses have been performed on CD34-progenitor derived dendritic cells that have been exposed to chemical skin sensitizers; allergens (4) and irritants (2). The aim of this work is to identify genes whose expression is affected by exposure to the allergens but not by the irritants. The inference is based on a dataset containing 72 microarrays.
|
| |
|
Nezávislostní modely
Šimeček, Petr
The paper inspects a possibility of construction of constraint–based learning algorithms based on the knowl- edge of representable independence models.
|