Seven QC Tools for Process Quality Improvement

Seven Major Tools

1) 2) 3) 4) 5) 6) 7) Flowchart or process mapping Check Sheet Histogram Pareto Chart Cause and Effect Diagram Scatter Diagram Control Chart

Flowcharts or Run chart

Used to explore if there is a process A Flow Diagram, also known as a flow chart, is a diagramatic technique to document a procedure, within a role or department. "Structured" flow diagrams are created using a single entry (with inputs), a single exit (with outputs), and a combination of three building structures:

Building structures
sequence - any series of 1-n sequential steps can be represented as a single step

choice - a decision between two or more paths (structured subpaths) [e.g., ifthen, case/select] loop - a structured subpath (single entry and single exit) that is executed 0-n times

Check Sheets
Also called: defect concentration diagram
A check sheet is a structured, prepared form for collecting and analyzing data. This is a generic tool that can be adapted for a wide variety of purposes.

Example : The figure below shows a check sheet used to collect data on telephone interruptions. The tick marks were added as data was collected over several weeks.

Source: http://www.hci.com.au/hcisite3/tool kit/data.htm

Data organizing tools

Once collected, raw data is typically summarized (reduced, or compacted) this can be done in several ways
Histograms

The Frequency Distribution and Histogram

A frequency distribution shows how often each different value in a set of data occurs. A histogram is the most commonly used graph to show frequency distributions. It looks very much like a bar chart, but there are important differences between them.

Histogram

Parts of a Histogram
F R E Q U E N C Y
100

Days of operation prior to failure for an HF receiver

80

60

40

20

0 0 5 10 15 20 25 30 35 40 45 50 55 60

1. Title , 2. Horizontal / X -axis , 3. Bars, 4. Vertical / Y -axis

Histogram

EXERCISE 1: The source of data for the first exercise is the following scenario.A list of the data collected follows this description

Recorded are the percentages of code defects for 80 personnel during development of s/w application.These are the data collected:

EXERCISE 1:

Histogram

PERCENT defects RECORDED

11 4 8 23 24 11 14 17

22 14 11 12 10 20 20 11

15 11 23 10 16 15 11 15

7 16 14 16 18 13 19 11

13 18 16 17 22 9 10 15

20 32 10 24 15 18 17 16

25 10 5 11 13 22 15 12

12 16 21 20 19 16 12 28

16 17 26 9 15 18 17 14

19 10 10 13 24 9 11 13

Histogram

Step 1 -Count number of data points

ANS : Total - 80

Step2 -Summarize on a tally sheet

Step3 -Compute the range Largest value = XY Percent defect Smallest value = XY Percent defect

Range of values = xyz Percent defect

EXERCISE 1: Step 1 Count number of data points

Histogram

PERCENT Defects RECORDED

11 4 8 23 24 11 14 17

22 14 11 12 10 20 20 11

15 11 23 10 16 15 11 15

7 16 14 16 18 13 19 11

13 18 16 17 22 9 10 15

20 32 10 24 15 18 17 16

25 10 5 11 13 22 15 12

12 16 21 20 19 16 12 28

16 17 26 9 15 18 17 14

19 10 10 13 24 9 11 13

ANS : Total - 80

EXERCISE 1: Step 1 Summarize the data on a tally sheet

%Deft No.Of.Pers 0 0 1 2 3 4 5 6 7 8 9 10 0 0 0 1 1 0 1 1 3 7

%Deft No.Of.Pers 11 9 12 13 14 15 16 17 18 19 20 21 4 5 4 7 8 5 4 3 4 1

%Deft No.Of.Pers 22 3 23 24 25 26 27 28 29 30 31 32 2 3 1 1 0 1 0 0 0 1

Histogram

Step3 -Compute the range

Largest value = 32 Percent Defects Smallest value = 4 Percent Defects Range of values = 28 Percent Defects

Histogram

Step 4 -Determine number of intervals

IF YOU HAVE THIS MANY DATA POINTS Less than 50 50 to 99 100 to 250 More than 250

USE THIS NUMBER OF INTERVALS: 5 to 7 intervals 6 to 10 intervals 7 to 12 intervals 10 to 20 intervals

ANS : Select 6 to 10 intervals - 8

Histogram

Step 5 -Compute interval width

Range Interval Width = Number of Intervals =

28 = 8 3.5

Use 8 for the number of intervals Round up to next whole number

Histogram

Step6 -Determine the starting point of each interval Step7 -Count the number of points in each interval
INTERVAL NUMBER STARTING VALUE INTERVAL WIDTH ENDING VALUE
NUMBER OF COUNTS

1 2 3

4 8 12

+4 +4 +4

8 12 16

3 20 20

4
5 6 7 8

16
20 24 28 32

+4
+4 +4 +4 +4

20
24 28 32 36

20
10 5 1 1

Histogram

Step8 -Plot the data Step9 -Add the title and legend

Critical Defects

20 18 16 14 12

10
8 6 4 2

0
0 4 8 12 16 20 24 28 32 36 PERCENT Defect

The Frequency Distribution and Histogram

Frequency Distribution Arrangement of data by magnitude More compact than a stem-and-leaf display Graphs of observed frequencies are called histograms.

Pareto Chart
A Pareto chart is a bar graph. The lengths of the bars represent frequency or cost (time or money), and are arranged with longest bars on the left and the shortest to the right. In this way the chart visually depicts which situations are more significant.

Pareto Chart
The Pareto chart is a frequency distribution (or histogram) of attribute data arranged by category. Plot the frequency of occurrence of each defect type against the various defect types. Also called: Pareto diagram, Pareto analysis Variations: weighted Pareto chart, comparative Pareto charts

Why use Pareto chart

Pareto

Breaks big problem into smaller pieces Identifies most significant factors Shows where to focus efforts Allows better use of limited resources

Pareto

Example
Individual category 45 40 35 30 25 20 15 10 5 0 Cumulative Cost 40 28 66.02 15 38.83 12 8

Pareto
120.00 92.23 80.58 100.00 100.00 80.00 60.00 40.00 20.00 0.00
Cumluative Cost

Cost Amount $$

Product Quality

Documents

Category of Cost

Packages

Delivery

Others

Example

Pareto

Figure 2 takes the largest category, documents, from Figure 1, breaks it down into six categories of document-related complaints, and shows cumulative values. If all complaints cause equal distress to the customer, working on eliminating document-related complaints would have the most impact, and of those, working on quality certificates should be most fruitful..
Individual cause Cum cause Pareto

Version problem

35 30 25 20 15 10 5 0

32 90.70 79.07 61.63 37.21 15 10 8

120.00
21

80.00 60.00 40.00 20.00 0.00

Training

OD errors

PMP error

Category of Cause

not approved

Cum u value of Costs

Values in cost

100.00 100.00

Cause and Effect Diagram

A Cause-and-Effect Diagram is a tool that helps dentify,sort,and display possible causes of a specific problem or quality characteristic (Viewgraph 1).It graphically illustrates the relationship between a given outcome and all the factors that influence the outcome.
This type of diagram is sometimes called an "Ishikawa diagram because it was invented by Kaoru Ishikawa,or a "fishbone diagram"because of the way it looks.

Cause and Effect Diagram

Cause and Effect

Variations: cause enumeration diagram, process fishbone, time-delay fishbone, CEDAC (cause-andeffect diagram with the addition of cards), desiredresult fishbone, reverse fishbone diagram
The fishbone diagram identifies many possible causes for an effect or problem. It can be used to structure a brainstorming session. It immediately sorts ideas into useful categories.

When should a team use a Cause-And-Effect Diagram?

Cause and Effect

Identify the possible root causes ,the basic reasons,for a specific effect, problem,or condition. Sort out and relate some of the interactions among the factors affecting a particular process or effect. Analyze existing problems so that corrective action can be taken.

Why should we use a Cause-and-Effect Diagram?

Cause and Effect

Helps determine the root causes of a problem or quality characteristic using a structured approach. Encourages group participation and utilizes group knowledge of the process. Uses an orderly,easy-to-read format to diagram cause-andeffect relationships. Indicates possible causes of variation in a process. Increases knowledge of the process by helping everyone to learn more about the factors at work and how they relate. Identifies areas where data should be collected for further study.

Benefits of Using a Cause-and-Effect Diagram

Cause and Effect

Helps determine root causes Encourages group participation Uses an orderly,easy-to-read format Indicates possible causes of variation Increases process knowledge Identifies areas for collecting data

Cause and Effect

Step 1- Identify and Define the Effect

Decide on the effect to examine

Use Operational Definitions

Phrase effect as
>positive (an objective)or

>negative (a problem)

Cause and Effect

Step 2
1. Brainstorm the major categories of causes of the problem. If this is difficult use generic headings:
Methods Machines (equipment) People (manpower) Materials Measurement Environment

Step 3
1.

Cause and Effect

Write the categories of causes as branches from the main arrow.

CAUSE A

CAUSE C

EFFORT

CAUSE B

CAUSE D

Computational problem
Divide by zero
Uninitialized variable Square root of a negative number

Hardware problems
Insufficient disk space Power outage Spurious interrupts Disconnected / dismounted Timeout Insufficient precision Over flow / underflow Empty data file Incorrect delimiters Non-numeric in numeric field Non-ASCII Extraneous data

I/O and file problems

File does not exist File permissions incorrect

Library-function problem
Standard libraries not available Standard libraries modified Incorrect return code from external function Incorrect parameters passed to external function

File corrupted File moved Invalid filename Output file already exists File locked by another program

Type mismatch

Corrupt memory Crash Transient errors

Failure to handle error return code

Incorrect command line arguments Erroneous response to prompt

Exception Failure
Illegal access Buffer overflow Corrupt memory Non- allocated memory accessed Insufficient memory

Values of arguments invalid

Missing data
Data values outside of range Missing end of File

Wrong number of argument

Wrong type of arguments

Later response to prompt

No response to prompt

Memory allocation error Array boundary violation

Invalid pointer dereferenced

Data-input problem

Return-value problem function/procedure call

External user / client problem

Null pointer and memory problems

Scatter Diagram
The scatter diagram is a plot of two variables that can be used to identify any potential relationship between the variables
The shape of the scatter diagram often indicates what type of relationship may exist The scatter diagram graphs pairs of numerical data, with one variable on each axis, to look for a relationship between them. If the variables are correlated, the points will fall along a line or curve. The better the correlation, the tighter the points will hug the line.

Also called: scatter plot, XY graph

Scatter plot for relationship between apartment size and its rent (n=25)

Scatter

2500 2300 2100 1900 1700 1500 1300 1100 900 700 500 500

Rent

700

900

1100

1300
Size

1500

1700

1900

2100

Scatter plot suggests that there is a positive, linear relationship between Rent and Size

Scatter

Example
If there are 24 data points. To test for a relationship, they calculate: A = points in upper left + points in lower right = 8 + 9 = 17 B = points in upper right + points in lower left = 4 + 3 = 7 Q = the smaller of A and B = the smaller of 7 and 17 = 7 N = A + B = 7 + 17 = 24

Then they look up the limit for N on the trend test table. For N = 24, the limit is 6.
Q is greater than the limit. Therefore, the pattern could have occurred from random chance, and no relationship is demonstrated.

Control Chart
The control chart is a graph used to study how a process changes over time. Data are plotted in time order. A control chart always has a central line for the average, an upper line for the upper control limit and a lower line for the lower control limit. These lines are determined from historical data. By comparing current data to these lines, you can draw conclusions about whether the process variation is consistent (in control) or is unpredictable (out of control, affected by special causes of variation).
Control charts for variable data are used in pairs. The top chart monitors the average, or the centering of the distribution of data from the process. The bottom chart monitors the range, or the width of the distribution. If your data were shots in target practice, the average is where the shots are clustering, and the range is how tightly they are clustered. Control charts for attribute data are used singly.

Control Chart

What is control chart

A statistical tool used to distinguish between process variation resulting from common causes and variation resulting from special causes.

Analyzing Process Performance

Why Control Charts?

Notice what the control charts dothey seek to identify if the process is behaving one way or another. This, in effect, is the same as asking if the process exists as a well-defined entity, where the past can be used to predict the future, or if the process is so ill-defined and unpredictable that the past gives little clue to the future. Donald J. Wheeler, 1995

Control Chart

Variations
Different types of control charts can be used, depending upon the type of data. The two broadest groupings are for variable data and attribute data.
Variable data are measured on a continuous scale. For example: time, weight, distance or temperature can be measured in fractions or decimals. The possibility of measuring to greater precision defines variable data. Attribute data are counted and cannot have fractions or decimals. Attribute data arise when you are determining only the presence or absence of something: success or failure, accept or reject, correct or not correct. For example, a report can have four errors or five errors, but it cannot have four and a half errors.

Variables charts

Control Chart

X and R chart (also called averages and range chart) X and s chart chart of individuals (also called X chart, X-R chart, IXMR chart, Xm R chart, moving range chart) moving averagemoving range chart (also called MA MR chart) target charts (also called difference charts, deviation charts and nominal charts) CUSUM (also called cumulative sum chart) EWMA (also called exponentially weighted moving average chart) multivariate chart (also called Hotelling T2)

Attributes charts
p chart (also called proportion chart) np chart c chart (also called count chart) u chart

Control Chart

Charts for either kind of data

short run charts (also called stabilized charts or Z charts) group charts (also called multiple characteristic charts)

Why should teams use Control Charts?

Control Chart

Monitor process variation over time. Differentiate between special cause and common cause variation. Assess the effectiveness of changes to improve a process. Communicate how a process performed during a specific period.

Control Chart

Why to use
Monitor process variation over time Differentiate between special cause and common cause variation Assess effectiveness of changes Communicate process performance

When controlling ongoing processes by finding and correcting problems as they occur.
When predicting the expected range of outcomes from a process. When determining whether a process is stable (in statistical control). When analyzing patterns of process variation from special causes (nonroutine events) or common causes (built into the process). When determining whether your quality improvement project should aim to prevent specific problems or to make fundamental changes to the process

Control Chart

What are the types of Control Charts?

There are two main categories of Control Charts,those that display attribute data ,and those that display variables data .

While these two categories encompass a number of different types of Control Charts, there are three types that will work for the majority of the data analysis cases you will encounter. In this module,we will study the construction and application in these three types of Control Charts: X-Bar and R Chart Individual X and Moving Range Chart for Variables Data Individual X and Moving Range Chart for Attribute Data

Control Chart

Chart types studied in this module:

X-Bar and R Chart Individual X and Moving Range Chart

-For Variables Data -For Attribute Data Other Control Chart types: X-Bar and S Chart u Chart Median X and R Chart p Chart c Chart np Chart

Analyzing Process Performance

Analyzing Process Performance

Analyzing Process Performance

Detecting Signals
The simplest rule for detecting a signal (possible assignable cause): a point outside the 3-sigma control limits. Many other sets of detection rules proposed. makes the control chart more sensitive to signals also leads to more false alarms decision on detection rules should be based on economic trade-offs

Analyzing Process Performance

Stability Concepts Stable process = Process In Statistical Control

= Sources of Variability Due to Common Causes only

Analyzing Process Performance

Control Charts
Two broad classes of control charts variable data, which is continuous attribute data, which is discrete Choice of what control chart to use should be based on knowing the right assumptions! Use the correct formulas for the kind of control chart selected!

Analyzing Process Performance

The Distinction Between Variables Data and Attributes Data Variables data (sometimes called measurement data) are usually measurements of continuous phenomena. Examples: measurements of length, weight, height, volume, voltage, horsepower, torque, efficiency, speed, and viscosity. Software examples: elapsed time, effort expended, years of experience, memory utilization, CPU utilization, and cost of rework.

Analyzing Process Performance

The Distinction Between Variables Data and Attributes Data Attributes data occur when information is recorded only about whether an item conforms or fails to conform to a specified criterion or set of criteria. Attributes data almost always originate as counts. Examples: the number of defects found, the number of defective items found, the number of source statements of a given type, the number of lines of comments in a module of n lines, the number of people with certain skills or experience on a project or team, and the percent of projects using formal code inspections.

Analyzing Process Performance

Average - Range Control Charts

Control Limits for Mean:

where X =

X
number of samples

X A2 R

R =

R
number of samples

Control Limits for Range:

D3 R and D4 R

Sample Size d2 A2 D3 D4 -----------------------------------------------------------------2 1.128 1.880 0 3.267 3 1.693 1.023 0 2.575 4 2.059 0.729 0 2.282 5 2.326 0.577 0 2.116 6 2.534 0.483 0 2.004 10 3.078 0.308 0.233 1.777 15 3.472 0.223 0.348 1.652 20 3.735 0.180 0.414 1.586 25 3.931 0.153 0.459 1.541

UCL
MEANS CL LCL RANGES UCL CL LCL 0 1 2 3 4 5 6 7 8 9 Sample Number 10

Analyzing Process Performance

Detecting Instabilities and Out-ofControl Situations

To test for instabilities in processes, we examine control charts for instances and patterns that signal nonrandom behavior. Values falling outside the control limits and unusual patterns within the running record suggest that assignable causes exist.

Analyzing Process Performance

Detecting Instabilities and Out-ofControl Situations

Test 1: A single point falls outside the 3-sigma control limits. Test 2: At least two of three successive values fall on the same side of, and more than two sigma units away from, the center line. Test 3: At least four out of five successive values fall on the same side of, and more than one sigma unit away from, the center line. Test 4: At least eight successive values fall on the same side of the center line.

Useful Control Charts

Most likely to be of value for software processes

u-chart
XmR chart

XmR Chart
When measurements are spaced widely in time or when each measurement is used by itself to evaluate or control a process, a time-sequenced plot of individual values, rather than averages, may be all that is possible.

XmR Chart
Control limits for Individuals Chart:
X-bar 3(MR-bar/d2)

Upper limit for Moving Range Chart: D4 MR-bar

Week
First Quarter Second Quarter

1 19 20 20

2 27 22 15

3 20 19 27

4 16 16 25

5 18 22 17

6 25 19 19

7 22 25 28

8 24 22

9 17 18

10 25 20

11 15 16

12 17 17

Third quarter

Each week, a system test organization reports the number of critical problems that remain unresolved. There is concern that week 31 value of 28 is higher than would have been expected. A control chart is constructed to investigate this possibility.

Calculation of Rework Effort :

Percentage of rework effort against development effort = Rework Effort in Person min ________________________ Actual Effort in Person min