Ch 13: Statistical Quality Control

the quantitative aspects of quality management

statistical quality control (SQC)

variation that is caused by factors that can be identified and managed

assignable variation

variation that is inherent in the process itself

common variation

What variation can be controlled

assignable variation

What variation is also called random variation

common variation

the center points of a set of numbers (average) 

mean (x-bar) 

a measure of how much individual observations deviate from the mean (spread)

standard deviation (sigma)

the maximum acceptable value for a characteristic

upper specification

the minimum acceptable value for a characteristic

lower specification

the ability of a process to consistently produce a good/deliver a service with a low probability of generating a defect 

process capability 

range of variation that is considered acceptable by the designer or customer

specification limits

range of variation that a process is able to maintain with a high degree of certainty

process capability

ratio of the range of values allowed divided by the range of values produced; shows how well the parts being produced fit into the range specified by the design specifications

process capability index (Cpk)

Cpk larger than one means:

the process is capable

When the two numbers of the Cpk are not close, it means: 

the mean has shifted 

If both Cpk are under one it means:

the distribution is TOO wide

testing a sample of output to determine if the process is producing items within a preselected range

statistical process control

quality characteristics that are classified as either conforming or not conforming

attributes

characteristics that are measured using an actual value 

variable 

what is the average of p hat?

p bar

p bar=

Total # defective units from all samples / (# samples x sample size)

UCL = 

p bar + zSp

LCL= 

p bar - zSp

How do you create a p chart? (5 steps)

Calc sample proportions for each sample (p)
Calc avg of sample proportions (p bar) 
Calc the stand dev of sample proportion (Sp)
Calculate the control limits (UCL and LCL) 
Plot the individual sample proportions, avg of proportions, and control limits 

p charts are used when: 

an item or service is either food or bad (yes no decision) 

c charts are used when:

an item or service may have multiple defects

c bar =

avg number of defects per unit

x bar charts show 

aim target value 

r bar charts show

range

for x bar and r charts, size of sample should be around:

5 units

for x bar and r charts, number of samples should be around:

25 samples 

for x bar and r charts, frequency of samples should be around:

trade off between cost of sampling and benefit of adjusting system 

for x bar and r charts, control limits should be around:

z=3 (unless told otherwise)

performed on goods that already exist to determine what percent of the products conform to specifications; determines quality level and ensure quality is within predetermined level; executed through sampling plan

acceptance sampling

What are the three results possible from acceptance sampling?

Accept
Reject
Retest

What are the disadvantages of acceptance sampling? 

Risk of accepting bad lots and rejecting good lots 
Added planning and documentation
Sample provides less info than 100 percent inspection

What are the advantages of acceptance sampling?

Economy
Less handling damage
Fewer inspectors
Upgrading of the inspection job
Applicability to destructive testing
Entire lot rejection (motivation for improvement)

maximum acceptable percentage of defectives defined by producer

acceptable quality level (AQL)

percent of defectives that defines consumers rejection point

lot tolerance percent defective (LTPD)

the probabiility of rejecting a good lot 

producer risk (alpha) 

The probability of accepting a bad lot

consumer risk (beta)

the AQL in Six sigma states that ___ defective parts out of every 1,000,000 parts might slip through the system

3.4