basictools-paretoanalysis

7
Pareto Analysis v2.ppt 1 Pareto Analysis What it is Pareto Analysis is used to record and analyse data relating to a problem in such a way as to highlight the most significant areas, inputs or issues. Pareto Analysis often reveals that a small number of failures are responsible for the bulk of quality costs, a phenomenon called the ‘Pareto Principle.’ This pattern is also called the ‘80/20 rule’ and shows itself in many ways. For example: 80% of sales are generated by 20% of customers. 80% of Quality costs are caused by 20% of the problems. 20% of stock lines will account for 80% of the value of the stock. A Pareto diagram allows data to be displayed as a bar chart and enables the main contributors to a problem to be highlighted. As a basic Quality Improvement tool, Pareto Analysis can: define categories of defects which cause a particular output (product, service, unit) to be defective; count the frequency of occurrence of each defect; display graphically as a bar chart, sorted in descending order, by frequency of defect; use a second y axis to show the cumulative % of defects .

Upload: faisal-abbas

Post on 09-Nov-2014

6 views

Category:

Documents


2 download

TRANSCRIPT

Page 1: BasicTools-ParetoAnalysis

Pareto Analysis v2.ppt1

Pareto AnalysisWhat it is

Pareto Analysis is used to record and analyse data relating to a problem in such a way as to highlight the most significant areas, inputs or issues. Pareto Analysis often reveals that a small number of failures are responsible for the bulk of quality costs, a phenomenon called the ‘Pareto Principle.’

This pattern is also called the ‘80/20 rule’ and shows itself in many ways. For example:

• 80% of sales are generated by 20% of customers.• 80% of Quality costs are caused by 20% of the problems.• 20% of stock lines will account for 80% of the value of the stock.

A Pareto diagram allows data to be displayed as a bar chart and enables the main contributors to a problem to be highlighted.

As a basic Quality Improvement tool, Pareto Analysis can:

• define categories of defects which cause a particular output (product, service, unit) to be defective;

• count the frequency of occurrence of each defect;• display graphically as a bar chart, sorted in descending order, by

frequency of defect;• use a second y axis to show the cumulative % of defects .

Page 2: BasicTools-ParetoAnalysis

Pareto Analysis v2.ppt2

Pareto AnalysisHow to use it

1. Gather facts about the problem, using Check Sheets or Brainstorming, depending on the availability of information.

2. Rank the contributions to the problem in order of frequency.

3. Draw the value (errors, facts, etc) as a bar chart.

4. It can also be helpful to add a line showing the cumulative percentage of errors as each category is added. This helps to identify the categories contributing to 80% of the problem.

5. Review the chart – if an 80/20 combination is not obvious, you may need to redefine your classifications and go back to Stage 1 or 2.

Examples

• When possible, use Minitab’s version, as an industry standard, rather than creating one in Excel - refer to Example 1 in this section

• Use a series of Pareto charts to drill down to more detail - Example 2

• Recognise the 80: 20 principle but if the original Pareto is very flat be prepared to cut the defects in a different way, say 40:60 - Example 3

• Minitab gives an extra dimension to Pareto Analysis - Example 4

Page 3: BasicTools-ParetoAnalysis

Pareto Analysis v2.ppt3

Pareto AnalysisExamples• Example 1 : Minitab’s version of Pareto is used as an industry standard.

It gives summary information and starts the cumulative % count at the top of the first bar:

Cmpt Damaged

Component Faulty

Cmpt Missing

Wrong Comp. Fitted

Cmpt not Meet Elect. Spec.

Deformed Joint

Joints not Soldered

Cmpt Touching Heatplane

Component Misfitted

Legs not through Board

Long Leads

Link Wire Missf itte

d

Beyond Economic Repair

Precautionary Removal

Thiokol Problem

Solder Short

Faulty Connector

Contamination

Others

141 139 69 52 22 20 20 17 17 17 16 13 10 10 10 8 6 5 29

23 22 11 8 4 3 3 3 3 3 3 2 2 2 2 1 1 1 5

23 45 56 65 68 71 75 77 80 83 85 87 89 91 92 94 95 95 100

0

100

200

300

400

500

600

0

20

40

60

80

100

Defect

CountPercentCum %

Perc

ent

Cou

nt

Pareto of D3 Small Engine Card Faults

Page 4: BasicTools-ParetoAnalysis

Pareto Analysis v2.ppt4

Pareto Analysis

• Example 2 : a series of Pareto charts drill down to more detail:

Design

ComponentBuild

Other

57 13 4 275.0 17.1 5.3 2.6

75.0 92.1 97.4 100.0

0

10

20

30

40

50

60

70

0

20

40

60

80

100

Defect

CountPercentCum %

Per

cent

Cou

nt

Fault by Main Cause

Connect Module

Torque Motors

Cold Start

Transducer Module

ASIC CalibrationIOP Imon

21 10 8 8 5 3 236.8 17.5 14.0 14.0 8.8 5.3 3.5

36.8 54.4 68.4 82.5 91.2 96.5 100.0

0

10

20

30

40

50

0

20

40

60

80

100

Defect

CountPercentCum %

Perc

ent

Cou

nt

Design Faults

1st level Analysis gives “Design” as main cause of failure

2nd level Analysis gives breakdown of “Design”

Examples

Page 5: BasicTools-ParetoAnalysis

Pareto Analysis v2.ppt5

Pareto Analysis

• Example 3 : if the original Pareto is very flat, be prepared to cut the defects in a different way, here, it is 40:60

KDCC788

KDCC646

KDCC777

KDCC780

KDCC782

KDCC795

40-564-8116-10

40-666-7823

40-564-7274-47E

Others

18 13 11 11 11 10 9 9 8 138 7.6 5.5 4.6 4.6 4.6 4.2 3.8 3.8 3.4 58.0

7.6 13.0 17.6 22.3 26.9 31.1 34.9 38.7 42.0 100.0

0

100

200

0

20

40

60

80

100

Defect

CountPercentCum %

Per

cent

Cou

nt

Pareto Chart for Child11

At first glance, this looks unhelpful. But of 238 data points, most were counts of 1 or 2. A full Pareto would be very flat.

Therefore after the first cumulative 42% of defects (100) , the balance of defects (138) are blocked together as “others”.

This enables us to see that a “top 9” of defects can be analysed - most are “S-clip” problems (links between ICs and PCB)

Examples

Page 6: BasicTools-ParetoAnalysis

Pareto Analysis v2.ppt6

Pareto Analysis

• Example 4 : an extra dimension to Pareto charts - cut defects across another variable - eg work shift:

0

5

10

15

Day

Coun

t

0

5

10

15

EveningCo

unt

0

5

10

15

Night

Cou

nt

0

5

10

15

Weekend

Cou

nt

Smudge

Other

Peel

Scratch

Pareto Chart for Flaws

Examples

Page 7: BasicTools-ParetoAnalysis

Pareto Analysis v2.ppt7

Pareto Analysis

References• ASG aTQ training module 7.4 : Measure /Analyse - Pareto & Cause-

Effect Revisited

How it helps

Pareto Analysis is a useful tool to:

• identify and prioritise major problem areas based on frequency of occurrence;

• separate the ‘vital few’ from the ‘useful many’ things to do;

• identify major causes and effects.

The technique is often used in conjunction with Brainstorming and Cause and Effect Analysis.

HINT !The most frequent is not

always the most important! Beaware of the impact of other

causes on Customers or goals.