Quality Engineering Statistics
Course Description: This course presents the fundamental concepts of statistical data analysis and interpretation for quality engineering including acceptance sampling, statistical process control, reliability, and design of experiments. The material covered includes: graphical data presentation methods; basic concepts of counting (permutations and combinations); the discrete probability distributions (hypergeometric, binomial, and Poisson); and the continuous probability distributions (normal, Student’s t, chi-square, and F). Students will learn to use these distributions to describe the data from various types of processes and use the data to construct confidence intervals and perform hypothesis tests to make data-based decisions. Extensive examples will be taken from acceptance sampling and SPC applications. Introductions will be presented to linear regression, correlation, analysis of variance, sample size calculations, and reliability. The use of statistical software (e.g. MINITAB) to solve problems may be integrated into the course and is highly recommended.
Prerequisite: Students should have good basic algebra skills.
Textbook: Quality Engineering Statistics by MM&B Inc. The Customer may also provide students with a copy of an appropriate reference quality engineering statistics text, e.g. Ostle, Turner, Hicks, and McElrath (1996), Engineering Statistics: The Industrial Experience, Duxbury Press, ISBN 0-534-26538-3.
Contact Hours: 32 to 40 hours. Students have better command and retention of the material if the course is delivered over an extended period of time, such as in one four-hour session each week for nine weeks.
Homework: Ten assignments requiring about 2-6 hours each (3 hours nominal) will be given. The Customer may decide if students are required to do the homework although students’ post-course statistics skills are strongly and positively correlated to the amount of homework that they do.
Upon completion of this course students should be able to:
- Use simple graphical techniques to perform preliminary analysis of data.
- Use the counting rules to solve permutation and combination problems associated with SPC run rules and experimental design.
- Calculate and interpret statistics for measuring location and variation.
- Apply and interpret the basic discrete probability distributions and apply them to attribute acceptance sampling and SPC (np, p, c, and u) charts.
- Set up, maintain, and operate basic SPC control charts for attributes and variables.
- Use the normal distribution to estimate the fraction defective of a process and set specs to achieve a desired fraction defective.
- Use approximations between the various distributions to obtain numerical solutions and to approach problems from various viewpoints.
- Use normal probability plots and quantitative methods to test data for normality.
- Calculate and interpret process capability and performance statistics (cp, cpk, Pp, Ppk) and understand how to evaluate the capability of non-normal data.
- Perform hypothesis tests and construct confidence intervals for means, standard deviations, and fractions.
- Use the results from hypothesis tests and confidence intervals to make data-based decisions.
- Identify and interpret cases of Type 1 and Type 2 testing errors.
- Fit lines and simple curves to data using linear regression.
- Evaluate linear regression models for assumption validity, goodness of fit, and model significance.
- Perform and interpret simple one-way and two-way analysis of variance problems.
- Calculate sample sizes for hypothesis tests and confidence intervals for measuring means, standard deviations, and fractions defective.
- Estimate product reliability from experimental data using the exponential, normal, and Weibull models.