Education of Future Industrial Statistical Consultants

1
Education of Future (Industrial) Statistical
Consultants

• Douglas C. Montgomery
• Professor of Engineering Statistics
• Arizona State University
• doug.montgomery_at_asu.edu

2
Challenges for Industrial Statisticians

• Todays industrial environment is often data-rich
  and highly automated
• Taxonomy of methods
• data collection
• data storage
• data analysis
• data warehousing
• data mining
• data drilling leading to
• data blasting, and finally
• data torturing

3
Challenges for Industrial Statisticians

• The multivariate nature of process data
• If you would not use a one-factor-at-a-time
  experiment, why do we continue to apply lots of
  univariate control charts?
• This has implications for what we teach
• Many techniques have promise, including
  multivariate generalizations of standard control
  charts, CART, MARS, latent structure methods we
  dont teach students enough about these techniques

4
Challenges for Industrial Statisticians

• Extending use of statistical methods into
  engineering design and development
• Methods for reliability improvement continue to
  be of increasing importance - driven by reduced
  design/development leadtimes, customer
  expectations
• Reliability of software, process equipment
  (predictive maintenance) are major considerations
• Robustness of products and processes are still
  important problems

5
Challenges for Industrial Statisticians

• Traditionally the industrial statistician has
  been viewed as a manufacturing person
• This perspective is changing as statistical
  methods penetrate into other key areas, including
• Information systems
• Supply chain management
• Transactional business processes
• Six-sigma activities have played a role in this

6
Education of Industrial Statisticians

• Its important to be a team member and not just
  a statistical consultant
• The mathematics orientation of many statistics
  programs does not make this easy
• Quote from Craig Barrett (INTEL)
• Statisticians often do not share in patent
  awards/recognition, other incentives sometimes
  regarded as merely data technicians

7
Some Must Courses for Modern Industrial
Statisticians

• Design of Industrial Experiments
• Emphasis on factorials, two-level designs,
  fractionals, blocking
• random effects, nesting, split plots
• Response Surface and Mixture Experiments (should
  include some robust design, process robustness
  studies)
• Reliability Engineering (should include RAM
  principles, test design, as well as survival data
  analysis)

8
Some Must Courses for Modern Industrial
Statisticians

• Modern Statistical Quality Control
• Analysis of Massive Data Sets
• Categorical Data Analysis, GLM
• Forecasting, Time Series Analysis Modeling
  (should overview a variety of methods, include
  system design aspects)
• Discrete Event Simulation
• Principles of Operations Research
• Basic optimization theory
• Linear nonlinear programming
• Network models

9

• I have just outlined about 27 semester hours of
  graduate work!!
• Most MS programs require 30 hr beyond the BS
  (non-thesis option), 24hr with thesis
• PhD programs require a minimum of 30 hr of course
  work beyond the MS
• Academic programs will need to be significantly
  redesigned if a serious effort is going to be
  made to educate industrial statisticians
• Most PhD programs require a minor (sometimes two,
  sometimes out-of-department)
• Require that this be in engineering,
  chemical/physical science, etc.
• Most departments will be eager to help set these
  up
• Could also work at MS level

10

• Recruit engineers/scientists for graduate
  programs in statistics
• But graduate programs had better be meaningful!
• Significant program redesign will be required
• Alternative develop joint graduate programs
  with engineering departments, business schools
• Where do graduates go?
• Lots of places, industry, government, academia
• But few of them will be theorists or
  teach/conduct research in theory-oriented
  programs
• So why do many graduate programs operate as if
  all of them will?