Scribd
Upload
67 views15 pages

Statistical Methods For Quality Control: Matt Levy - ISDS 2001

This document summarizes various statistical quality control methods including total quality management, the Malcolm Baldridge National Quality Award, ISO 9000 standards, and Six Sigma. It also describes control charts for monitoring statistical process control, including x-bar, R, p, and np charts. Control charts contain limits to distinguish between common cause variation (in control) and assignable causes (out of control) that require corrective action. Understanding these quality control frameworks and tools is important for evaluating and improving organizational processes.

Uploaded by

jolaak
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
67 views15 pages

Statistical Methods For Quality Control: Matt Levy - ISDS 2001

This document summarizes various statistical quality control methods including total quality management, the Malcolm Baldridge National Quality Award, ISO 9000 standards, and Six Sigma. It also describes control charts for monitoring statistical process control, including x-bar, R, p, and np charts. Control charts contain limits to distinguish between common cause variation (in control) and assignable causes (out of control) that require corrective action. Understanding these quality control frameworks and tools is important for evaluating and improving organizational processes.

Uploaded by

jolaak
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 15

Chapter 20

Statistical Methods for Quality Control

Matt Levy - ISDS 2001


Total Quality
A people focused management system that aims for continual
increase in customer satisfaction, at a continually lower real cost.

Broad concept implemented differently in every organization.

Has three fundamental principles:


Focus on Customers and Stakeholders.
Participation and Teamwork throughout the organization.
Focus on continuous improvement and continuous learning.

Three quality management frameworks to talk about:


Malcolm Baldridge Nat'l Quality Award
ISO 9000
Six Sigma
Malcolm Baldridge Nat'l Quality Award

Introduced by Congress to reward U.S. based companies for


quality and performance.
Malcolm Baldridge - U.S. Commerce Secretary 1981-1987
Interesting note about your teacher -- dad worked directly under M.B. as an
Econometricist for the D.O.C.

Award based on seven key areas:


leadership
strategic planning
customer and market focus
measurement, analysis, and knowledge management
human resource focus
process management
business results
ISO 9000

ISO - International Standards Organization


Series of 5 international standards
The standards describe what is needed maintain
effective quality conformance systems.
For example: ensuring measurement and testing
equipment is calibrated correctly.
And for maintaining things like adequate record
keeping.
Six Sigma

Another quality assurance methodology

Came from motorola (3.4 defects per million opportunities)


Any error that is passes on to the customer is considered a defect.

An organization may undertake 2 kinds of Six Sigma projects:


DMAIC (Define, Measure, Analyze, Improve, and Control) to
help redesign existing processes.
DFSS (Design for Six Sigma) to design new products,
processes, or services.
Other Important Concepts of Six Sigma

Quality Assurance - The entire system of policies, procedures, and


guidelines established by the org. to maintain quality.

Quality Engineering - To include quality in the design of products and


processes and to identify quality problems prior to production.

Quality Control - Series of inspections and measurements to


determine if quality standards are being met.
Statistical Process Control

This section considers quality control procedures for a production


process where goods are manufactured continuously.

There can be different causes for quality degradation:

Assignable Causes - for example tools wearing out, poor quality of


raw materials, or operator error.
In this case the process should be corrected or adjusted ASAP.

Common Causes - Randomly occurring variations in materials. For


example temperature, humdity, etc.
This is something that cannot be readily controlled through process
refinement.
Statistical Process Control

When assignable causes are detected, we conclude the process is out


of control

When only common causes are detected, we conclude the process


is in control or in statistical control.
Control Charts
Provides a basis for deciding whether variation in output is due to common causes (in
control) or assignable causes (out of control)

Control Charts are classified by the type of data they contain. Examples are: Sample
Mean Chart, R Chart, p Chart and np Chart.

Control Charts are pretty simple.

They contain an upper control limit (UCL), a Lower Control Limit (LCL), a center
line (process mean) and progress in sequentially in time.
Sample Mean (x-bar) Chart
To build the sample mean chart, remember the sampling distribution
of x-bar. Specifically that the standard error = σ/√n

The sampling distribution of x-bar is used to determine if the process


is in control.

Also recall from our study on normal probability distributions that


99.7% of the values of a normally distributed random variable are
within ± 3 deviations of the mean. This sets our upper and lower
control limits:

If the process mean and standard deviation are unknown we can get
our Process mean from the overall sample mean, and our CL's from
the Average Range (see Figures 20.4 - 20.8)
R Chart

Similarly to how we do a chart centered around the mean, we can also


do one centered around the range.

In this case, the range of a sample can be thought of as a random


variable with it's own mean and standard deviation.

The average range (R-bar) provides an estimate of the mean.

The estimate of the standard deviation of the range can be derived


from R-bar and a standard control chart (20.3).

See Figures 20.10 - 20.15 to understand how this was derived.


p Chart

Usually used when output quality is measured in defective or non-


defective items.

p stands for proportion, and we use p-bar, the proportion of defective


items found in a sample.

The sampling distribution of p-bar is the same as in Ch.7. Please


review this as well as Figures 20.16 and the ≥ 5 rule for determining
large sample size.

Control Limits for a p Chart:


np Chart

Usually when measuring the number of defective items in a sample.

n is the sample size.

p is the probability of observing a defective item when the process is


in control.

The same ≥ 5 rule applies as in the p chart.

Control Limits for a np chart:


Interpretation of Control Charts

The location and pattern of points on a control chart enable us to


determine with a small probability of error whether our process is in
statistical control.

Any data point outside the control limits is a primary indication our
process is out of control -- corrective action should be taken ASAP.

Also look for points that are on one side of the center line, and/or
gradual shifts or trends over time.
Summary

Make sure you read through Chapter 20 Section 2.

Make sure you attempt the homework, we'll work through them on
Wednesday.

You might also like