Skip to Content

Essential Statistical Concepts for the Quality Professional

By D. H. Stamatis

CRC Press – 2012 – 510 pages

Purchasing Options:

  • Add to CartHardback: $89.95
    978-1-43-989457-6
    May 2nd 2012

Description

The essence of any root cause analysis in our modern quality thinking is to go beyond the actual problem. This means not only do we have to fix the problem at hand but we also have to identify why the failure occurred and what was the opportunity to apply the appropriate knowledge to avoid the problem in the future. Essential Statistical Concepts for the Quality Professional offers a new non-technical statistical approach to quality for effective improvement and productivity by focusing on very specific and fundamental methodologies and tools for the future.

Written by an expert with more than 30 years of experience in management, quality training, and consulting, the book examines the fundamentals of statistical understanding, and by doing so demonstrates the importance of using statistics in the decision making process. The author points out pitfalls to keep in mind when undertaking an experiment for improvement and explains how to use statistics in improvement endeavors. He discusses data interpretation, common tests and confidence intervals, and how to plan experiments for improvement. The book expands the notion of experimentation by dealing with mathematical models such as regression to optimize the improvement and understand the relationship between several factors. It emphasizes the need for sampling and introduces specific techniques to make sure accuracy and precision of the data is appropriate and applicable for the study at hand.

The author’s approach is somewhat new and unique; however, he details tools and methodologies that can be used to evaluate the system for prevention. These tools and methodologies focus on structured, repeatable processes that can be instrumental in finding real, fixable causes of the human errors and equipment failures that lead to quality issues.

Contents

What Is Statistics?

Deductive and Inductive Statistics

The Stages of a Sample Study

Warning!!!

Control the Data

Significance Testing

Wrong Signs

Summary

References

Selected Bibliography

Data

Describing Data

Data Orientation

Nominal, Ordinal, Interval, and Ratio

Sampling Considerations

The Frequency of the Sample

Degrees of Freedom

Where Do I Start?

What Is a P-Value?

Assessing Normality

Summary

Selected Bibliography

Summarizing Data

Frequency Distributions

Dot Plots

Stem and Leaf Displays

Box Plots

Descriptive Statistics

Measures of Dispersion

Normality

Areas in the Normal Distribution

Standard Score

A Sample from the Normal Distribution

Distributions that Aren’t Normal

The Standard Error of the Mean

Tests of Distributions as a Whole

Transformations to Obtain Normality

Confidence and Sensitivity

Test for Independence in Contingency Tables

Summary

References

Selected Bibliography

Tests and Confidence Intervals for Means

Test for μ When σ Is Known

Test for μ When σ Is Unknown

Test for μ − μ When σ and σ Are Known

Test for μ − μ When σ and σ Are Unknown

Test for Two Independent Samples When σ = σ

Test of μ − μ = for Two Independent Samples When σ ≠ σ

Test for Differences Between Proportions p – p

Test for Differences Among Several Means

Detection of a Trend in a Set of Means with Standard Deviations

Unknown but Assumed Equal

Summary

Selected Bibliography

Tests and Confidence Intervals for Standard Deviations

Computation and Understanding s and σ

Chi-Square Test for σ in a Normal Distribution

F-Test for σ/σ for Normal Distributions

M-Test for Homogeneity of Variances

Summary

Selected Bibliography

Tests of Distributions and Means

Underlying Distribution Analysis

Methods of Testing for Underlying Distributions

Probability Plotting

Selected Tests

Summary

References

Selected Bibliography

Understanding and Planning the Experiment and Analysis of Variance

Understanding the Fundamentals of Experimentation

Planning the Process

Data Analysis versus Statistical Analysis

Analysis of Variance

Hypothesis Testing

Calculating the F-Ratio

Multiple-Comparison Procedures

Interactions

How Can You Test the Null Hypothesis that Several Population

Means Are Equal?

Special Considerations

Types of Analysis of Variance

Taguchi Approach to Design of Experiments

Summary

References

Selected Bibliography

Newer Sources

Fitting Functions

Selecting Dependent Variables

Selecting Independent Variables

Correlation Analysis

Regression

Step Regression

General Linear Model

Discriminant Analysis

Log-Linear Models

Logistic Regression

Factor Analysis

Cluster Analysis

Testing Hypothesis About Many Means

Conjoint Analysis

Multiple Regression

Partial Regression

After Regression

Summary

References

Selected Bibliography

Typical Sampling Techniques

Notation and Formula for the Hypergeometric Distribution

Binomial Experiment

Notation and Formula

Binomial Distribution

Cumulative Binomial Probability

Types of Acceptance Plans

Definitions of Basic Acceptance Plans

The Final Choice Is a Tradeoff Analysis

MIL STD (D and )

Stratified Sampling

Proportionate Versus Disproportionate Stratification

Surveys

Quality of Survey Results

Sample Design

Simple Random Sampling

Cluster Sampling

The Difference between Strata and Clusters

How to Choose the Best Sampling Method

Quality-Control Charts and Sampling

Attributes or Variables

Choice of Plan

Inspection Level

Summary

Selected Bibliography

Understanding Computer Programs for Design and Estimating Design Power

Examples of ANOVA and ANCOVA Models

Key to types of statistical models

Strong Recommendations

Summary

References

Epilogue

Appendix A: Minitab Computer Usage

Appendix B: Formulae Based on Statistical Categories

Appendix C: General Statistical Formulae

Appendix D: Hypothesis Testing Road Map

Appendix E: Test indicators

Appendix F: Hypothesis Testing—Selected Explanations and Examples

Appendix G: When to Use Quality Tools—A Selected List

Glossary

Selected Bibliography

Name: Essential Statistical Concepts for the Quality Professional (Hardback)CRC Press 
Description: By D. H. Stamatis. The essence of any root cause analysis in our modern quality thinking is to go beyond the actual problem. This means not only do we have to fix the problem at hand but we also have to identify why the failure occurred and what was the opportunity to...
Categories: Quality Control & Reliability, SPC/Reliability/Quality Control, Manufacturing Engineering