Effects of missing data in competing risks on accelerated life testing
Accelerated life tests are a potential means to provide reliability of a new product in a very short time period. In order to extract useful information, it is important to understand how the accelerated stresses affect the failure distribution of the product. Accelerated life test data is then extrapolated to normal working conditions to analyze the product reliability. In real experiments, when stresses become too high, it is not appropriate to use conventional extrapolation methods to make inference about the component/product reliability. The main objective of this research is to evaluate the impact of missing data at high stress levels during accelerated life testing on the extrapolation to normal working conditions. A numerical study is performed to study the impact of missing data at two stress levels on the extrapolation to normal working conditions.
Gudipati, Venkata Sesha Sai Arvind, "Effects of missing data in competing risks on accelerated life testing" (2005). ETD Collection for University of Texas, El Paso. AAI1430249.