Project Quality Management Lectures 4,5,6

Document Sample
Project Quality Management Lectures 4,5,6 Powered By Docstoc
					Lectures 4 & 5
Quality Managing Tools

 Helps to solve problems

 Helps identify reasons for problems

 Narrows down your observations

 Makes decision making easy

 Brings rationality to your claims
Quality Managing Tools
Basic Steps to Solve Problems:

 Define the problem and establish an improvement goal

 Collect data

 Analyze the problem

 Generate potential solutions

 Choose a solution

 Implement the solution

 Monitor the solution to see if it accomplishes the goal
Quality Managing Tools
There are 07 Basic Tools of Quality identified as being most helpful in
troubleshooting quality issues. They are called basic because they are
suitable for people with little formal training in statistics. These are :

     Flow Chart

     Cause & Effect Diagram

     Check Sheet

     Pareto Chart

     Histogram

     Scatter Plot

     Control Chart
Flow Charts
It visually represent relationships among the activities and tasks that make
up a process.

                                       A Flowchart may:
                                       • Have a logical start and an end.

                                       • Have Inputs and outputs.

                                       • Indicate resources involved in the process.

                                       • Mention sequence of activities.

                                       • Show controlling points.

                                       • Mention activities responsible.
Symbols in Flowcharting
Following standard symbols are used to create process maps:

   Terminal          Process Step          Decision             Report

    Input/              On-page             Page
    Output             Connector          Connector

                                             Delay             Manual
Types of Flow Charts
Three (03) types of flow diagrams can be used to describe a process,
depending upon the information to be shared. These are:

High-Level Flowchart
A first-level or top-down flowchart shows the major steps in a process. It
illustrates a "birds-eye view" of a process.
Types of Flow Charts
Detailed Flowchart
It maps all the steps and activities that occur in the process including
decision points, waiting periods, documents and feedback loops etc.
Types of Flow Charts
Deployment or Matrix Flowchart
It maps out the process in terms of who is doing what and how in a
process. It is in the form of a matrix, showing the various participants
and the flow of steps among these participants.
Creating a Flow Chart

 Define the process steps by observing the process

 Sort the steps into the order of their occurrence in the process

 Place the steps in appropriate flow chart symbols

 Add the decision points & controlling points

 Create the chart

 Get it peer-reviewed

 Modify if required

 Get approval and implement for intended purpose
Flow Charts
Draw a process map showing the sequence, flow and interaction of
activities involved in the process of selection of a GD pilot for Pakistan Air
Force with the below mentioned activities:

•   Advertisement in newspaper
•   Applications receiving & scrutiny
•   Welcoming applicants at recruitment center
•   Admission
•   Conducting preliminary test
•   Preliminary Test results announcement
•   Arrangements for ISSB tests
•   Conducting ISSB protocol
•   ISSB results declaration
•   Call for interview
•   Interview conduct
•   Selection formalities completion
Cause & Effect Diagram
• Also termed as Ishikawa, Fishbone and Cause & Effect Diagram.
• It visually represents the causes of a problem or effect and help you
  determine the ultimate source of the problem — the root cause.
• It is used at the beginning of root cause analysis and planning.

           4              5             6


          3            2              1
Cause & Effect Diagram
                         Draw Spine
    Mark Categories
                                         Define Problem

                                      Highlight issues
Draw a fishbone diagram for investigating the reasons for higher turnover of employees

                                        No perks
Check Sheet
It is a simple document that is used for collecting data in real-time and at the location
where the data is generated. This document is typically a blank form that is designed for
the quick, easy, and efficient recording of the desired information

                                              Problem       Frequency         Total

                                           Hard to drive
                                                         IIII                  4
                                                            IIIII              6
                                           Low Salary       IIIIIIIIIIIIII     13

                                           Lesser Perks     IIIIIIIIIII        9

                                                            IIIIIIIIIIIIIII    15
                                           getting higher
                                           High market
                                                       IIIII                   6
                                           Flexibility in
                                                          III                  3

                                                                    TOTAL:     56
Pareto Chart
It is a simple bar graph that ranks problems in order of magnitude to determine the priorities
for improvement activities. Often called the 80-20 rule, the Pareto’s Principle is a way of
separating the “vital few from the trivial many”.
How to construct a Pareto Chart
1. Select the parameter to be studied
2. Frequency of parameter to be arranged in descending order
3. Percentage of each contributor to be calculated (Individual & Cumulative frequency)

                                     3, 4, 6, 6, 9 13, 15

                                       No of
                                                   %age of total   Cumm. Total
               Issues Categories     complaints
                                                     (%age)          (%age)
         Salaries Getting higher         15             27             27
         Low Salary                      13             23             50
         Lesser Perks                     9             16             66
         High Market Demand               6             11             77
         Office Location                  6             11             88
         Hard to drive to                 4                 7          95
         Flexibility In Management        3                 5         100
                      TOTAL              56            100
Pareto Chart
Scatter Plot
A scatter plot is a classic statistical diagram that lets you visualize the relationship
between numeric variables. For instance, if you have a table of data on cities, you could
use a scatter plot to see if there is a relationship between population and crime levels.

 • If the points cluster in a band running from lower left to upper right, there is a
   positive correlation (if x increases, y increases).
 • If the points cluster in a band from upper left to lower right, there is a negative
   correlation (if x increases, y decreases).
Scatter Plot

   Scatter Plot
Draw a scatter plot for the below given data:

  Height     Weight
 (inches)     (lbs.)

    67         155

    72         220

    77         240

    74         195

    69         175
Run Charts
A run chart is a line graph of data plotted over time. By collecting and charting data over
time, you can find trends or patterns in the process
Run Charts
Draw a run chart for a pizza oven whose temperature is measured after every hour to see
whether the required temperature is maintained or otherwise

           Noted Temp.
                                                    Temperature Monitoring
1200 Hrs      280        350
1300 Hrs      285        300          285           285           275                         280                  290
1400 Hrs      270        250    280          270           280                         285           275
1500 Hrs      285                                                        220
1600 Hrs      280
                         150                                                                                             Temp
1700 Hrs      275
1800 Hrs      220        100

1900 Hrs      275         50
2000 Hrs      285          0
2100 Hrs      280
2200 Hrs      275
2300 Hrs      290
 Types of Data
• There are different types of data which are required to be
  differentiated based upon the type of tool to be used:

    Attribute Data (whole numbers)
    Variable Data (measurements points)

It is important to know what type of data you will collect so you can
determine what type of control chart to construct. Different charts
will give different information.
 Attribute Data
• These types of data are often referred to as discrete data. There
  are two kinds of attributes data:

    Yes/No Data
    Counting Data

• Mail delivery was on time or not?
• Is the submitted invoice correct or not
• Is process under control or otherwise?

• Number of defects in product
• Number or items shipped incorrectly
• Number of accidents per month
 Continuous Data
• These types of data are often referred to as variable data and the
  observation can be measured to any decimal place you want if
  your measurement system allows it.

• Some examples of variables data are sales in dollars, amount of
  time to make a delivery, height, weight, and costs etc.
Statistical Concepts
Arithmetic Mean (X)
the average of data

the middle value when the figures are arranged according to size
For example, for the data 10, 13, 15, 20, 27, 34, 37, the median is 20. In case
of even number of data, the median is the average of central two values

the value which occurs most often in data
For example, for a data series 12, 14, 18, 18, 22, 22, 22, 25, 30, 30, the mode
is 22

The difference between maximum and minimum values in data

The square root of standard deviation, i.e., variance s = sqrt of s
        or s² = s
Statistical Concepts
Standard Deviation

                                   (                )
Square of variance; formula is:
                       xi - x
              s     =√ n
      X =         mean of values of distribution
       n =        No. of values used to calculate standard deviation
       xi =       value of x for each item in distribution
Standard Deviation
• Shows amount of variation or "dispersion" from the average
  (mean, or expected value).
• A low standard deviation indicates that the data points tend to be
  very close to the mean, whereas:
• High standard deviation indicates that the data points are spread
  out over a large range of values.
 Control Charts
• Control charts present the results of a process over time
• They are used to determine if the process is under control
• Can be used to monitor:

   Cost and Schedule variances
   Errors in process
Control Chart- a typical illustartion
Out of Control Process
Out of Control Process
The Rule of Seven in Control Charts
Out of Control Process – Rule of Seven
• A histogram is a type of bar graph for showing frequency distribution, or how often
  individual data points occur across the range of the data from low to high.

• It represents frequency distribution by means of rectangles whose widths represent
  class intervals and whose areas are proportional to the corresponding frequencies
How to draw a histogram
• SELECT the measures to be examined. For example, you need to study things like time,
  weight, dimensions and speed etc.

• COLLECT the data (use a check sheet)

• PREPARE the frequency table in a sequential form

• DESIGN the histogram (class interval and class width finalization)

• DRAW the histogram in a graphical display (using bar graph)

• INTERPRET the data and draw your observations
Example - Evaluating contract finalization time periods
                                    Contracts Processing Time
  Days    Contracts   Days   Contracts Days Contracts Days         Contracts   Days   Contracts
   16        1         26       0         36         1        46      0         56       0
   17        0         27       0         37         0        47      0         57       0
   18        0         28       1         38         2        48      2         58       1
   19        0         29       0         39         0        49      0         59       0
   20        1         30       1         40         4        50      0         60       0
   21        0         31       0         41         0        51      1         61       0
   22        0         32       2         42         2        52      0         62       0
   23        0         33       0         43         0        53      0         63       0
   24        1         34       1         44         0        54      3         64       0
   25        0         35       0         45         0        55      0         65       1

 Range:               65-16 = 49

 Class Interval:      5

 Class Interval:      49/5 = 9.2 (10)
Example - Evaluating contract finalization time periods
 Range:            65-16 = 49

 Class Interval:   5

 Class Width:      49/5 = 9.2 (10)
Interpretation of Histogram
Interpretation of Histogram
Statistical Process Control (SPC)
To achieve the best results, start by (1) drawing up a process
map, so you understand the process flow. Next, (2) analyze the
process flows for the primary causes of problems and develop
your cause-effect diagram. Then, (3) collect data using check
sheets and (4) plot your data using a Pareto chart and/or (5)
a histogram. Next, (6) determine the relationship of various
variables in your cause-effect chain using a scatter chart. Once
you have solved your problem, (7) use a control chart to ensure
that the process is staying within process control limits —
demonstrate process control.

Shared By:
Description: Project Quality Management Lecture, Audit, inspection, QA, QC, Assurance, Control, Quality control