Parametric Evaluation of Lifetime Data

The development of a very large array of small antennas for the DSN is under consideration. Each receiving station will likely be equipped with a closed-cycle refrigerator (CCR) to cryogenically cool the low-noise amplifiers and microwave feed components. A previous article examined a non-parametric approach, known as the product-limit (PL) estimate, to the analysis of lifetime data [1]. This article considers the application of a parametric probability distribution, known as the Weibull distribution, to the analysis of lifetime data. Others have analyzed CCR lifetime data using this distribution [2,3]. The Weibull distribution is popular because of its versatility. Depending on the values of the parameters, an increasing, constant, or decreasing hazard rate can be modeled. There is both a two-parameter and a three-parameter version of the Weibull distribution. This article will be concerned with the two-parameter version.