Specify the accelerated life test factor distribution and details of prior estimates for the model parameters.
Figure 23.5 Prior Specification
Distribution Choice
Select a life distribution (LogNormal or Weibull) for each acceleration factor. See Statistical Details for the ALT Design Platform.
Prior Mean
Enter prior estimates of the acceleration model parameters. The prior estimates are hyperparameters in a Bayesian prior distribution. The Prior Mean values can be a best guess based on subject matter knowledge or they can be based on a previous study.
Specify Intercept
Enter the priors for the model parameters including the intercept.
Specify Quantile
Enter the priors for the acceleration factor, the expected failure proportion at a given time, and value for the acceleration factor. This information is used to calculate the intercept.
Specify prior uncertainty
Select to enter values for the standard error and correlations of the priors for the acceleration model parameters. The standard errors reflect uncertainty relative to the prior estimates of the acceleration model parameters.
Note: When prior uncertainty measures are not specified, the design is created by treating the priors as the true parameter values. This design is close to optimal if the prior mean parameters are close to the true values. However, this design is not robust to misspecification of the parameter estimates. If you are unsure about your prior estimates, use the Prior Uncertainty specifications to reflect your uncertainty.