|
Research Projects Supported by HKU's High Performance Computing Facilities |
|
¡@ |
| Researcher: |
| Dr K C Yuen, Department of Statistics and Actuarial Science |
| ¡@ |
|
Project Title: |
|
Comparing k Cumulative Incidence Functions through Resampling Methods |
| Project Description: |
|
Tests for the equality of k (k ³ 2) cumulative incidence functions in a competing risks model are proposed. Test statistics are based on a vector of processes related to the cumulative incidence functions. Since their asymptotic distributions appear very complicated and depend on the underlying distribution of the data, two resampling techniques, namely the well-known bootstrap method and the so-called random symmetrization method, are used to approximate the critical values of the tests. Without making any assumptions on the nature of dependence between the risks, the tests allow one to compare k risks simultaneously under the random censorship model. The tests are fully non-parametric and do not require arbitrary partitions of the sample space. Tests against ordered alternatives are also considered. Simulation studies indicate that the proposed tests perform very well with moderate sample size. A real application to cancer mortality data is given. |
| Project Duration: |
| 1 year |
| - Back to top- / Contents |
| Project Significance: |
| In the competing risks framework, an individual is exposed to k risks, but the actual cause of failure is due to only one of the risks. It is of great interest to examine whether there are possible differences in mortality from different causes of failure. The outcome of such an investigation provides useful information on fatal causes of failure, and hence allows one to be more cautious of them. In reliability, a fair amount of valuable time and resources can be saved by early identification of weak components in a system. In clinical studies, appropriate medical actions may be taken for a patient to reduce the occurrence of major risks. |
| Results Achieved: |
|
The project
leads to the following publication: |
| Remarks on the Use of High Performance Computing Cluster: |
| The simulation study requires intensive computations since it involves resampling methods. With the help of the machine, the computations can be done in an efficient way and the amount of computational time can be greatly reduced. |
| Email Address: |
| kcyuen@hku.hk |