Académique Documents
Professionnel Documents
Culture Documents
"As much as 95% of quality related problems in the factory can be solved with seven fundamental quantitative tools." - Kaoru Ishikawa
By Zaipul Anwar Business & Advanced Technology Centre, Universiti Teknologi Malaysia
Fishbone Diagrams Histograms Pareto Analysis Flowcharts Scatter Plots Run Charts Control Charts
The Basic Seven Tools made statistical analysis less complicated for the average person
Good Visual Aids make statistical and quality control more comprehendible.
No statistics involved Maps out a process/problem Makes improvement easier Looks like a Fish Skeleton
Definition
Uses Ishikawa
benefits
Steps 1-9
Example
Service example
Ham Industries
Exercise
Resembles skeleton of a fish Focus on causes rather than symptoms of a problem Emphasizes group communication and brainstorming Stimulates discussion
One of Seven basic tools of Japanese Quality Leads to increased understanding of complex problems Visual and presentational tool
Typically done on paper or chalkboard Recently some computer programs have been created to make Fishbone Diagrams
Ishikawa Environment
Use in Organizations (1 of 2)
Use in Organizations (2 of 2)
As a group:
group
3.
5. Brainstorm secondary causes for each of the major causes 6. Connect these secondary causes to their respective major causes 7. Repeat steps 5 & 6 for sub-causes dividing with increased specificity
- usually four or five levels
Example (1 of 4)
Step 1 & 2:
(backbone)
Example (2 of 4)
Step 3 & 4:
Appearance Responsiveness
Poor Service
Attention
Reliability
Example (3 of 4)
Step 5, 6, & 7:
Appearance equipment personnel Responsiveness time
facility
Poor Service accuracy One on one service dependability Reliability
courtesy
Attention
Example (4 of 4)
Step 8 & 9:
Pareto diagrams, charts, and graphs Statistical analysis for causes in processes Use fishbone diagram, analysis and evaluations to find causes that can be fixed Take action to eliminate and fix problem causes
Summary (1 of 3)
Fishbone Diagrams
- visual diagram - resembles fish skeleton - identifies the causes of a problem (effect), and their relationships
- created by Kaoru Ishikawa for Quality Management
Summary (2 of 3)
Organizational Uses
Increases communication about problems Used to improve any product, process, or service Important part of quality management
Summary (3 of 3)
Exercise
Create a Fishbone (cause and effect, Ishikawa) Diagram for the following:
Management at Ham Industries has noticed that the productivity of its workers is well below the standard. After interviewing its employees, it was noticed that a vast majority felt dissatisfied and unhappy with their work. Your boss has asked you and a group of your peers to find the causes of worker dissatisfaction . Include all possible causes to at least the secondary level.
Bibliography
//home.t-online.de/home/kfmaas/q_ishika.html www.zi.unizh.ch/software/unix/statmath/sas/sasdoc/qc /chap17/sect1.htm www.dti.gov.uk/mbp/bpgt/m9ja00001/m9ja0000110.ht ml Foster, S. Thomas. Managing Quality: An Integrative Approach. 2001, Prentice-Hall
Overview
1) 2)
3)
4) 5)
6)
What is a Histogram? What are some possible uses for a Histogram? Where did the Histogram come from? How do Histograms work? A real world example. An exercise.
What is a Histogram?
A Histogram is a variation of a bar chart in which data values are grouped together and put into different classes. This grouping allows you see how frequently data in each class occur in the data set.
Higher bars represent more data values in a class. Lower bars represent fewer data values in a class. On the next slide is an example of what a Histogram looks like.
Example of a Histogram
The Histogram was first implemented by Kaoru Isikawa, one of Japans most renowned experts on quality improvement.
Isikawa spent his life trying to improve quality in Japan.
His major contributions to quality improvement are known as the basic seven tools of quality. Included in his basic seven tools of quality is the Histogram.
First, you need need to pick a process to analyze. Next, you need a large amount of data, at least 100 data values so that patterns can become visible. Then, you need to assemble a table of the data values that you collected with regards to frequency of data values.
Next, you need to calculate some statistics for the Histogram, including: mean, minimum, maximum, standard deviation, class width, number of classes, skewness, and kurtosis. Then, you actually create the Histogram using these statistics.
After you have created a Histogram, it will take one of five shapes:
Normal Distribution:
Positively Skewed:
Negatively Skewed:
Bi-Modal Distribution:
Multi-Modal Distribution:
Once your Histogram is complete, you can analyze its shape, as well as the statistics that you came up with.
This analysis will help you to make better decisions toward quality improvements.
Constructing a Histogram
From a set of data compute sum mean (x) Max Min Range (max-min)
Constructing a Histogram
Use range to estimate beginning and end Calculate the width of each column by dividing the range by the number of columns
Range
# of Columns
= Width
Lets say the owner wants a distribution of Acmes Thursday Night Sales
02122413121224341432232122122142212122121212121 21222121211222314223222123224224412223221224212 421721223121121222122121222424
Range/Columns=7/7=1 slice
Slices of Pizza
Constructing a Histogram
How is this helpful to Acme? 2 slices of pizza most common order placed Distribution of sales useful for forecasting next Thursdays late night demand If you were an Acme manager how could you apply this information?
Very similar to Histograms Use of the 80/20 rule Use of percentages to show importance
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.
70 60 50 40 30 20 10 0 1 2 2
3 4
4 3
5 7
6 5
7 6
Slices of Pizza
Critical Thinking How does the Pareto Analysis differ from the Histogram? How can this be a useful tool to the Acme boss?
Percent
50
Count
60 40 20
40 30 20 10 0
t en on mp Co
0
ild Bu er Oth
Design Faults
100
Defect
Count Percent Cum %
n s ig De
57 75.0 75.0
13 17.1 92.1
4 5.3 97.4
2 2.6 100.0
50 80 40
Percent
t ec nn Co le du Mo rs oto eM rqu To t uc tar sd ld S Tran Co le du Mo er IC AS n atio libr Ca IOP n Imo
Count
60 40 20 0
30 20 10 0
Defect
Count Percent Cum %
21 36.8 36.8
10 17.5 54.4
8 14.0 68.4
8 14.0 82.5
5 8.8 91.2
3 5.3 96.5
2 3.5 100.0
Process
Flowcharts
Dont Forget to:
Define symbols before beginning Stay consistent Check that process is accurate
no
Lockup Put More in
Oven 2 Pies
Get Pizza
yes
noAvailable?
yes
Time to close?
no
Take to Customer
yes
How can we use the flowchart to analyze improvement ideas from the Histogram?
Window (start) Take Customer Order
Money?
no
Lockup Put More in
Oven 2 Pies
Get Pizza
yes
noAvailable?
Time to close?
yes
no
Take to Customer
yes
Taking a shower Cooking dinner Driving a car Having a party Creating a Flowchart
In this simple example, you can find the existing relationship without much difficulty but
Scatter Diagrams
Easier to see direct relationship
25 20 15 10 5 0 0 20 40 60 80
Scatter Diagrams
As a quality tool What does this tell Acme management about their processes? Improvements?
25 20 15 10 5 0 0 20 40 60 80
Run Charts
Slices/hour
8 9 10 11 12 1 2 3 4
8 9 10 11 12 1 2 3 4 8 9 10 11 12 1 2 3 4
Time
PM- AM
Thursday Week 1
PM- AM
Thursday Week 2
PM- AM
Thursday Week 3
Range
Control Charts
Upper Limit
Control Charts
Acme Pizza Management wants to get in on the control chart action
Average Diameter = 16 inches Upper Limit = 17 inches
17 inches
16 inches= X
Lower Limit 15 Inches
Small Pie
Flow Chart
Check Sheet
Histograms
Pareto Analysis
Scatter Diagrams
Control Charts
Summary
Basic Seven Tools of Quality Measuring data Quality Analysis Democratized statistics
Bibliography
Foster, Thomas. Managing Quality. An IntegrativeApproach. Upper Saddle River : Prentice Hall, 2001. Stevenson, William. Supercharging Your Pareto Analysis. Quality Progress October 2000: 51-55. Dr Kaoru Ishikawa. Internet http://www.dti.gov.uk/mbp/bpgt/m9ja00001/m9ja0000110.html. 16 February 2001. Chemical and Process Engineering. Internet. http://lorien.ncl.ac.uk/ming/spc/spc8.htm. 17 February 2001.