Fit Life by X

Question

Can anyone suggest a way to run "Fit Life by X" when the form is

mu (log lifetime) = beta0 + X^(beta1)?

From running the reciprocal and custom relations, beta1 values between -1 and -2 seems to give the best fit to the observed failure times.

Many thanks!

JYakura · Accepted Answer

Thank you!  I'll give it a try!

JYakura · Accepted Answer

The Nonlinear Model platform seems to work well.  Carrying this beyond the original question, it looks as though I would need to create a 'dummy' X variable in order to combine two factors, e.g. Peck's Power-law humidity model.

JYakura · Accepted Answer

Dr. Bill Meeker also pointed out that this model's parameters can also be obtained, in a different form, by using the Box-Cox relationship in the Fit Life By X platform and then using the distribution results sensitivity profiler to maximize lambda's likelihood and then re-running Box-Cox with that lambda. (Thanks Dr. Meeker!)