The Crow-AMSAA model is frequently used for analyzing and assessing reliability growth. In case of grouped data the Crow-AMSAA model parameters have to be estimated by numerical optimization. Grouped data occurs when only the number of failures within a given time period are known.
The Crow-AMSAA model in the R code fits a NonHomogenous Poisson Process (NHPP) having a power law intensity function. See this post for fitting a NHPP model having a loglinear intensity function. Continue reading R code for fitting the Crow-AMSAA model to grouped data