Stat 567:Statistical Reliability
Ninth Class (September 23, 1996)
Maximum Likelihood Estimation:
Computations
Class Objectives:
- Learn to compute Maximum Likelihood Estimators (MLEs) for the Weibull
distribution
- Learn about some numerical issues in MLE calculations
- Learn to use JMP to obtain MLEs in the Weibull and lognormal case.
Homework Assignments:
- Verify that the Weibull MLEs of the ball bearing data presented in
Example 3.2, Page 57 of your textbook
satisfy Equations (3.8) and (3.9) on Page 55.
- Verify the variance-covariance matrix of the Weibull MLE estimates
of the ball bearing data presented in Example 3.2, Page 57 of your textbook satisfy the equations on top of
Page 56.
- Submit two new study questions for this or a prior lesson. Remember
that these questions could end up in the exams
Class Outline and Main Points:
- Computation of MLEs for the Weibull and Gumbel distributions with right
censoring
- Solving the equations of partial derivatives equated to zero
- Initial algebraic simplification of equations
- Final numerical solution by method of repeated bisections
- Computation of information matrix and variance-covariance matrix
- Algebraic manipulations for increasing calculation precision
- Ball Bearing Data of Example 2.1, Page 37 of your textbook.
- MLEs for a Weibull model
- Comparison with method-of-moments and graphical estimates
- MLEs for a lognormal model
- Using JMP to obtain MLEs
Using JMP to obtain MLEs:
To get the MLEs with JMP of the Weibull and Gumbel (Extreme-value) fits
of the ball bearing data of Example 2.1, Page 37 of your textbook
go to JMP's survival platform and obtain the P-L survival estimate as we
have done before. Then proceed as follows:



To get MLEs for a log-normal model of the ball bearing data proceed as above
but select the log-normal plot instead of the Weibull plot.
Notice that with this JMP platform we do not get the variance-covariance
matrix of the estimates. Later we will show how to get this matrix using
JMP's non-linear platform.
Study Questions:
- Why do we need numerical techniques to obtain MLEs?
SAS JMP file (Mac) of classroom example
- Ball Bearing data of Example 2.1, Page 37 of your textbook.

Find out how to download JMP files.
Do
you have something to tell me?