Skip to main content

Master's Project: Reliability Estimation in Series Systems

To complete my master’s degree in statistics/mathematics at SIUE, I presented my master’s project in October 2023. There was also a paper associated with the project titled “Reliability Estimation in Series Systems: Maximum Likelihood Techniques for Right-Censored and Masked Failure Data”.

Overview

The project addresses a common challenge in reliability engineering: estimating component failure rates when:

  1. Masked failure data: You observe system failure but don’t know which component failed
  2. Right censoring: Some systems are still operational when observation ends

These data limitations are ubiquitous in real-world reliability studies, where identifying the exact failed component may be expensive or impossible.

Key Contributions

  • Likelihood-based framework for handling both masking and censoring simultaneously
  • Weibull distribution modeling with closed-form Fisher information for the exponential special case
  • R package implementation providing accessible tools for practitioners
  • Bootstrap methods for uncertainty quantification

This project connects to several other posts and projects:

See the full project page here.

Discussion