Stefan Steiner


Stefan SteinerContact Information:
Stefan Steiner

Watfactory virtual manufacturing process information (PDF)
Watfactory virtual manufacturing process login

Research interests

Professor Steiner's research interests cover the broad area of business and industrial statistics focusing on process improvement. The overall goal of his research is the development of innovative ways to use process data and statistical methods to drive process improvement and variation reduction.

One major recent project was the development of an algorithm for variation reduction called the Statistical Engineering algorithm. This step-by-step algorithm was designed to help practitioners solve chronic problems in existing high- to medium-volume manufacturing and assembly processes. The algorithm has some unique features, including focus on a dominant cause, explicit use of the baseline data to help plan further investigations, a new measurement system assessment plan, explicit consideration of the seven variation reduction approaches, use of the method of elimination to search for a dominant cause, and an emphasis on observational studies rather than experimental studies. The algorithm is described in detail in the Statistical Engineering book by Steiner and MacKay (2005).

Another application area is the data mining and monitoring of high-dimensional functional data. A good example application is the valve insertion process for an automotive engine. The valve is force inserted and a measurement device automatically records the distance travelled by the ram as well as the exerted force as a function of time. Professor Steiner has developed methodology that allows the characterization of such functional data in a way that captures the relevant information. By monitoring the characterizations over time looking for evidence of process upsets or gradual changes, process problems can be detected and addressed quickly.

Recently, Professor Steiner has been developing methods for monitoring surgical outcomes. The need to formally monitor surgical outcomes has come to the forefront in some recent well-publicized cases where undesirably high rates of surgical complications remained undetected for an undue length of time. In such cases, the rapid detection of deterioration in surgical performance is critical since it will result in prompt investigation of the cause and possible procedural changes to improve performance. In this context a risk adjustment is necessary since patients can be very heterogeneous. Professor Steiner has developed a risk-adjusted cumulative sum (CUSUM) monitoring procedure using a likelihood score based on an assessment of risk prior to surgery. This methodology has been widely applied to a variety of situations such as monitoring cardiac surgery outcomes. Software to support risk-adjusted CUSUM charts is available.

As a consultant, I have worked together with numerous organizations, including General Motors Canada, Ford, Toyota, Chrysler, Nortel, Wescast, PetroCanada, Precision Plastics, Woodbridge Foam, Atlantis Aerospace, Eaton Yale, the U.S. Army, the State of Utah, and the Counties of Tooele, Utah, and Salt Lake.

The consulting projects involved statistical process control, design of experiments, quality improvement, data analysis, data mining and process re-engineering. I am currently the director of the University of Waterloo's Business and Industrial Statistics Research Group (BISRG).


Since joining the University of Waterloo in 1995, Professor Steiner has carried out research-related consulting through the University's Business and Industrial Statistics Research Group. In the past five years he has worked with a wide variety of organizations including Atlantis Aerospace, Bendall Automotive, ComDev, Dana, Katlyn, General Motors Canada, Fisher and Paykel (New Zealand), Ford Motor Company, Nortel Networks, Research in Motion, Seagrams, Toyota, and Wescast. The consulting projects involved designed experiments, statistical process control, quality improvement, data analysis, and process re-engineering.

Since 2004 Professor Steiner has been the director of the BISRG at the University of Waterloo. From 2003-04 he was the director of the predecessor of BISRG, namely the Institute for Improvement in Quality and Productivity. The mandate of BISRG is to encourage the flow of knowledge, ideas, methods, and problems between the university and business communities to their mutual benefit.

Selected publications

  • Stevens N, Steiner SH and MacKay RJ (2015) “Assessing Agreement Between two Measurement Systems: An Alternative to the Limits of Agreement Approach" Statistical Methods in Medical Research, 1-22.
  • Jones-Farmer A, Woodall W, Steiner SH and Champ CW (2014), “An Overview of Phase I Analysis for Process Improvement and Monitoring” Journal of Quality Technology, 46, 265-280. (winner of the Statistics Division of the American Society for Quality’s Lloyd Nelson Award)
  • Danila O, Steiner SH and MacKay RJ (2013), “Assessing a Binary Measurement System with Varying Misclassification Rates when a Gold Standard is Available,” Technometrics, 55, 335-345.
  • Steiner SH, Stevens NT, Browne R and MacKay RJ (2011), “Planning and Analysis of Measurement Reliability Studies,” Canadian Journal of Statistics, 39, 344-355.
  • Browne R, Steiner SH, MacKay RJ (2010) “Leveraged Gauge R&R Studies,” Technometrics, 52, 294-302 (winner of the American Statistical Association’s W.J. Youden Award in Interlaboratory Testing).
  • Steiner SH and Jones M (2010) “Risk Adjusted Survival Time Monitoring with an Updating Exponentially Weighted Moving Average (EWMA) Control Chart” Statistics in Medicine, 29, 444-454.
  • Steiner SH, MacKay RJ and Ramberg JS (2008). “An Overview of the Shainin SystemTM for Quality Improvement”, with discussion Quality Engineering, 20:1, 6–19.
  • Steiner SH and MacKay RJ (2004) “Scale Counting”, Technometrics, 46, 348-354. (winner of the American Society for Quality’s Wilcoxon Prize for the best practical applications paper).
  • Steiner SH, Cook R, Farewell V and Treasure T (2000), “Monitoring Surgical Performance Using Risk Adjusted Cumulative Sum Charts,” Biostatistics, 1, 441-452.
  • Steiner SH (1999), “EWMA Control Charts with Time-Varying Control Limits and Fast Initial Response,” Journal of Quality Technology, 31, 75-86.

See additional publications by Stefan Steiner.

Google Scholar profile

October 2016 CV.pdf

University of Waterloo
Contact information: