Quality Engineering and Industrial Statistics


Place of this course in the curriculum: this course is an advanced course in applied industrial statistics. A primary course in probability and statistics is required.
Goal: To teach the students a profound knowledge of industrial statistcs and familiarize them with common statistical tools for quality control, process monitoring and process improvement; to activate the knowledge through cases, projects and exercises – with pen & paper as well as with statistical software.


•  Introduction to quality systems: quality concepts, philosophies and systems
•  Multidimensional data: Exploratory Data Analysis and Principal Component Analysis.
•  Overview of preliminaries (industrial) statistics: random samples, statistical inference,  tests of hypotheses, point estimation of quality parameters, confidence intervals for  quality parameters
•  Simple and multiple linear regression, nonparametric tests and Bayesian inference
•  Statistical process control: methods and philosophy of statistical process control,  control charts for variables, control charts for attributes
•  Other process monitoring techniques and capability analysis: Cumulative Sum and
•  Exponentially Weighted Moving Average control charts, other statistical process  monitoring and control techniques, process and measurement system capability analysis
•  Acceptance sampling plan systems: acceptance sampling for attributes and variables
•  Design and analysis of experiments: designed experiments, experiments with a single factor, analysis of variance (ANOVA), randomized blocks, latin squares, and related designs
•  Design and analysis of experiments: designed experiments with multiple factors, 2k factorial design, blocking and confounding
•  Design and analysis of experiments: fractional factorial designs, 2k-p designs, two-level, three-level and mixed-level factorial designs, fitting, regression models
•  Process optimization with designed experiments: response surface methods and other approaches to process optimization, experiments with random facts, Taguchi approach to quality and robust designs
•  Introduction to reliability engineering: basic reliability models and the failure distribution, constant and time-dependent failure rate model, reliability, maintainability and availability of complex systems
Implementation of all these aspects using software for statistical computing, in casu R.