an introduction to statistical process control charts (spc)

45

Upload: dean

Post on 22-Feb-2016

76 views

Category:

Documents


0 download

DESCRIPTION

An Introduction to Statistical Process Control Charts (SPC). Steve Harrison Monday 15 th July 2013 12 – 1pm Room 6 R Floor RHH. Topics. Variation – A Quick Recap An introduction to SPC Charts Interpretation Quiz Application in Improvement work. Variation. Common Cause Variation. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: An Introduction to Statistical Process Control Charts (SPC)
Page 2: An Introduction to Statistical Process Control Charts (SPC)

An Introduction to Statistical Process Control Charts (SPC)

Steve HarrisonMonday 15th July 2013 12 – 1pmRoom 6 R Floor RHH

Page 3: An Introduction to Statistical Process Control Charts (SPC)

Topics• Variation – A Quick Recap• An introduction to SPC Charts• Interpretation• Quiz• Application in Improvement work

Page 4: An Introduction to Statistical Process Control Charts (SPC)

Variation

Page 5: An Introduction to Statistical Process Control Charts (SPC)

Common Cause Variation• Typically due to a large number of small

sources of variation • Example: Variation in work commute due to traffic lights, pedestrian traffic, parking issues• Usually requires a deep understanding of the

process to minimise the variation

5

Page 6: An Introduction to Statistical Process Control Charts (SPC)

Special Cause Variation

• Are not part of the normal process. Arises from special circumstances

• Example: Variation in work commute impacted by flat tire, road closure, ice-storm.• Usually best uncovered when monitoring

data in real time (or close to that)

6

Page 7: An Introduction to Statistical Process Control Charts (SPC)

0

20

40

60

80

100

120

Consecutive trips

Min.

Special Cause - My trip to work

Mean

Upper process limit

Lower process limit

Page 8: An Introduction to Statistical Process Control Charts (SPC)

Two Types of Variation

Special Cause: • assignable cause• signal

Common Cause: • chance cause• noise

Statistically significant (not good or bad)

8

Page 9: An Introduction to Statistical Process Control Charts (SPC)

SPC Charts

9

Page 10: An Introduction to Statistical Process Control Charts (SPC)

SPC, Statistical Process Control or The Control Chart

Elements

1. Chart/graph showing data, running record, time order sequence2. A line showing the mean3. 2 lines showing the upper and lower process ‘control’ limits

• You only need 25 data points to set up a control chart, but 50 are better if available

Page 11: An Introduction to Statistical Process Control Charts (SPC)

The Anatomy of an SPC or Control Chart

0

10

20

30

40

50

60

70

80

F M A M J J A S O N D J F M A M J J A S O N D

Upper process control limit

Mean

Lower process control limit

Page 12: An Introduction to Statistical Process Control Charts (SPC)

Measures of Central Tendency• Mean = Average – SPC Chart• Median = Central or Middle Value – Run

Chart• Mode = Most frequently occurring value

12

Page 13: An Introduction to Statistical Process Control Charts (SPC)

Standard Deviation or σ

In statistics, standard deviation shows how much variation exists from the mean.A low standard deviation indicates that the data points tend to be very close to the mean; high standard deviation indicates that the data points are spread out over a large range of values.

Page 14: An Introduction to Statistical Process Control Charts (SPC)

Standard Deviation and a normal distribution

Page 15: An Introduction to Statistical Process Control Charts (SPC)

PRACTICAL INTERPRETATION OF THE STANDARD DEVIATION

Mean Mean + 3s

Mean - 3s

99.6% will be within 3 s

0.4% will be outside 6s in a normal distribution

Page 16: An Introduction to Statistical Process Control Charts (SPC)

3s AND THE CONTROL CHART

6s

3s

3s

UCL

LCL

Mean

Page 17: An Introduction to Statistical Process Control Charts (SPC)

Run Charts vs. SPC ChartsRun Chart• Simple• Easy to create in Excel• Less Sensitive• Only need 10 data

points

SPC• More Powerful• Control lines show the

degree of variation• Need Special Software• Need 25+ data points

17

0

10

20

30

40

50

60

70

80

4-Ap

r

6-Ap

r

8-Ap

r

12-A

pr

14-A

pr

18-A

pr

20-A

pr

22-A

pr

3-M

ay

5-M

ay

9-M

ay

11-M

ay

13-M

ay

15-M

ay

% D

aily

TTO

s C

ompl

eted

by

Noo

n

Ward x– % of total TTOs completed by 12 noon April 4 - May 15, 2012

Page 18: An Introduction to Statistical Process Control Charts (SPC)

Special cause variation

0102030405060708090

F M A M J J A S O N D J F M A M J J A S O N D

Page 19: An Introduction to Statistical Process Control Charts (SPC)

Point above Upper Control Limit (UCL)

SPECIAL CAUSES - RULE 1

MEAN

LCL

UCL

Page 20: An Introduction to Statistical Process Control Charts (SPC)

Or point below Lower Control Limit (LCL)

SPECIAL CAUSES - RULE 1

MEAN

LCL

UCL

Page 21: An Introduction to Statistical Process Control Charts (SPC)

MEAN

Eight points above centre line

SPECIAL CAUSES - RULE 2

LCL

UCL

A 1 in 256 chance or 0.3906%

Page 22: An Introduction to Statistical Process Control Charts (SPC)

MEAN

SPECIAL CAUSES - RULE 2

LCL

UCL Or eight points below centre line

A 1 in 256 chance or 0.3906%

Page 23: An Introduction to Statistical Process Control Charts (SPC)

MEAN

Six points in a downward direction

SPECIAL CAUSES - RULE 3

LCL

UCL

Page 24: An Introduction to Statistical Process Control Charts (SPC)

MEAN

SPECIAL CAUSES - RULE 3

LCL

Or six points in an upward direction

UCL

Page 25: An Introduction to Statistical Process Control Charts (SPC)

Considerably less than 2/3 of all the points fall in this zone

LCL

UCLSPECIAL CAUSES - RULE 4

MEAN

Page 26: An Introduction to Statistical Process Control Charts (SPC)

SPECIAL CAUSES - RULE 4

Or considerably more than 2/3 of all the points fall in this zone

MEAN

UCL

LCL

Page 27: An Introduction to Statistical Process Control Charts (SPC)

Quiz – 1. Does the chart show

A. Special Cause Variation?

B.Common Cause Variation?

C.Both of the above

D.No Variation

Specia

l Cause Varia

tion?

Common Cause Varia

tion?

Intentional V

ariation

All of t

he above

No Variation

0%

100%

0%0%0%

Page 28: An Introduction to Statistical Process Control Charts (SPC)

2. How many special cause signals are present on this chart?A. 0B.1C.2D.3E. 16

0 1 2 3 16

10%

90%

0%0%0%

Page 29: An Introduction to Statistical Process Control Charts (SPC)

3. How many special cause signals are present on this chart?A. 0B.1C.2D.3E. 16

0 1 2 3 16

0%

10%

0%0%

90%

Page 30: An Introduction to Statistical Process Control Charts (SPC)

4. How many special cause signals are present on this chart?A. 0B.1C.2D.3E. 16

0 1 2 3 16

0%

20%

0%

70%

10%

Page 31: An Introduction to Statistical Process Control Charts (SPC)

What use is this?

• Evaluate and improve underlying process• Is the process stable? • Use data to make predictions and help

planning• Recognise variation• Prove/disprove assumptions and

(mis)conceptions• Help drive improvement – identify statistically

significant change

Page 32: An Introduction to Statistical Process Control Charts (SPC)

Example

Page 33: An Introduction to Statistical Process Control Charts (SPC)

Annotated SPC Charts• One of the most powerful tools for

improvement• Describe a process captured over time (as

opposed to being a single sample)• Reveal any trends a process might be

experiencing• When combined with careful annotation they

track the impact of change

Page 34: An Introduction to Statistical Process Control Charts (SPC)

Why We Want to Annotate Our Charts…

I @:@ -1 : - f, I I .

'And this is the period when the cat was away. '

Page 35: An Introduction to Statistical Process Control Charts (SPC)

Example – Renal DT247J

PDSA 1 PDSA 2

Page 36: An Introduction to Statistical Process Control Charts (SPC)

Application – Responding to Variation

36

Page 37: An Introduction to Statistical Process Control Charts (SPC)

Responding to Special Cause Variation

• Identify the cause: • If positive then can it be replicated or standardised. • If negative then cause needs to be eliminated

37

Page 38: An Introduction to Statistical Process Control Charts (SPC)

Responding to Common Cause Variation

1. Reduce variation: make the process even more predictable or reliable (and/or)

2. Not satisfied with result: redesign process to get a better result

38

Page 39: An Introduction to Statistical Process Control Charts (SPC)

Process with common cause

variation

Reduce variation: make the process even more reliableNot satisfied with result: redesign process to get a better result

Process with special cause

variation

Identify the cause:if positive then can it be replicated or standardized. If negative then cause needs to be eliminated

39

Page 40: An Introduction to Statistical Process Control Charts (SPC)

DISCUSSION

Page 41: An Introduction to Statistical Process Control Charts (SPC)

Evaluation1. Absolute Rubbish2. Terrible3. Fairly Bad4. Not that Great5. Alright6. Quite Good7. Really Quite Good8. Very Good9. Excellent10. Amazing!

41Abso

lute Rubbish

Terrible

Fairly

Bad

Not that

Great

Alright

Quite Good

Really Q

uite Good

Very Good

Excelle

nt

Amazing!

0% 0% 0% 0% 0%

40%

50%

10%

0%0%

Page 42: An Introduction to Statistical Process Control Charts (SPC)

THANKS!

Page 43: An Introduction to Statistical Process Control Charts (SPC)
Page 44: An Introduction to Statistical Process Control Charts (SPC)

1

2

Page 45: An Introduction to Statistical Process Control Charts (SPC)

45

3 4