Companion

This approximation is based on a MOM argument. Pobocikova, Ivana, and Zuzana Sedliackova. “Comparison of Four Methods for Estimating the Weibull Distribution Parameters.” Applied Mathematical Sciences 8 (2014): 4137–49. https://doi.org/10.12988/ams.2014.45389.

Given a shape parameter estimate the corresponding scale parameter based on the data. The shape parameter must be greater than 0.0. The data must not be empty and there should not be any negative or zero values in the data.

Based on the recommendation on page 288 of Law(2007) There must be at least two observations. Returns an estimated initial shape parameter. There should not be any negative or zero values in the data.

Estimates the shape and scale parameters based on supplied values of the percentiles xp1 represents the estimated (from a sample) quantile for p1 represents the estimated (from a sample) quantile for p2 The quantiles must be non-negative and not equal. The probabilities must be within (0,1) and not equal. The returned pair has: component1 = shape component2 = scale See: Marks, Neil B. “Estimation of Weibull Parameters from Common Percentiles.” Journal of Applied Statistics 32, no. 1 (January 2005): 17–24. https://doi.org/10.1080/0266476042000305122.