Risk Analysis Using First Hitting Times and Threshold Regression

• Activity Number: 520
• Type: Topic Contributed
• Date/Time: Wednesday, August 12, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Section on Risk Analysis
• Author(s): Mei-Ling Ting Lee*
• Companies: University of Maryland
• Keywords: non-proportional hazards ; survival analysis ; Wiener process ; inverse Gaussian distribution ; degradation ; reliability

Abstract

In engineering applications, failure events of a system can be triggered when the cumulative usage and wear first reaches a critical threshold. In medical applications, the onset of a disease of patients can be modelled by the first time when the latent health degradation process reaches a critical threshold. The first-hitting-time based Threshold Regression (TR) model does not require a proportional hazards assumption and, hence, is applicable in many fields. Case examples will be presented to demonstrate its practical use. The TR model also provides researchers with statistical tools for estimating risk scores.