Sundaram - Clayton Ltd Sundaram - Clayton Ltd 7 7 QC tools QC tools
Nov 11, 2014
7
QC tools
Sundaram - Clayton Ltd
Seven QC ToolsScatter Diagram
StratificationHistogram
Graph & Control ChartCause & Effect Diagram Pareto Diagram
Check Sheet
Sundaram - Clayton Ltd
Sl.No1 2 3
ToolsCheck Sheet / Data Sheet Pareto Daigram Cause & Effect Diagram Graph & Control Chart Histogram Stratification Scatter Diagram
FunctionTo Collect the data in a simple manner and to prevent omitting the checks To pick up the important few problems from the trivial many. To reorganise the factors (causes)which are influencing the problem Presentation of data in a pictorial form for better understanding and see if the process is under stable conditions. To see the distribution pattern compared against the standard values. To segregate data according to contributing sources.(Suppliers,machines,operators etc) To see relation between two sets of data
4
5 6 7
Sundaram - Clayton Ltd
Check SheetSolder Bath TemperatureChecked by : Raised by : Take reading of temperature nearest to degree. Time Temp (0C) Time Temp (0C) 0800 60 1300 61 0900 62 1400 58 1000 59 1500 63 1100 58 1600 63 1200 59 1700 59 Note : Power failure from 12.00 to 12.15 Hours
Sundaram - Clayton Ltd
What is Check Sheet ?A Check sheet is a paper form on which item to be
checked have been printed already so that data can becollected easily and concisely. Its main purposes are two-fold :
1) To make data-gathering easy ;2) To arrange data automatically so that they can be used easily later on
Two Types of Data :1. Measurement data or Variable data. 2. Attribute data.
Sundaram - Clayton Ltd
Check sheets are of following types :a) Check sheet for production process distribution. b) Defective item check sheet. c) Defect location check sheet. d) Defect cause check sheet.
Sundaram - Clayton Ltd
Check Sheet for Production Process Distribution :Deviation -10 -9 -8 -7 -6 -5 -4 -3 -2 -1 0 1 2 3 4 5 6 7 8 9 10 Total Checks 5 10 15 20 Frequency
Specification
8.300
1 2 4 6 9 11 8 7 3 2 1 1
Specification
55
Sundaram - Clayton Ltd
Defective Item Check Sheet :Product :
Date :Section : Inspectors name :
Manufacturing stage: Final inspType of defect: Scar,incomplete crack,misshapen. Total no.inspected : 1525 Remarks : All items inspected.TypeSurface scars Cracks Incomplete Mishappen Others IIII IIII IIII III IIII IIII IIII IIII I IIII IIII
Lot no :Order no :ChecksII
Subtotal17 11
IIII
IIII
I
26 3 5
Total : Total rejects
62 42
Sundaram - Clayton Ltd
Defect Location Check SheetA1 A B C D 2 1 12 10 15 11 1 3 4
B
C
D 1 2
3
From the location matrix it is clear that most of the blow holes
4
are occupied in the segment B2,B3,C2 & C3.
Defect Location Matrix For Blowholes (50 Defective Components)
Sundaram - Clayton Ltd
Defect Cause Check Sheet.Mon Equipment Operator AM PM AM PM AM PM AM PM AM PM AM PM Tue Wed Thu Fri Sat
1 A 2
oo ox x
ooo xx
ooo xxx
xx oo xx
oo xxxx oo
oo
xxx
1 B 2
oo
xx
xx
oo x Blowhole Poor finish Crack Others
o Damage
Sundaram - Clayton Ltd
Points to remembered while making check sheets Easy to use & understanding. Information should be true & accurate.
Decide objective by involving all the members. Use 5W & 1H principle. Who will collect the data ? When will the data be collected ? Where will the data be collected ? How will data be collected ? Check sheets should be displayed on visible area.
Sundaram - Clayton Ltd
Benefits of Check SheetsData Collection have the following benefits : Right decision can be made.
Errors due to subjective feeling or personal bias are avoided. Agreement on decisions necessary rather than different or
subjective opinion. Measurement understandable to all.
Assessments of magnitude of improvements. Discovery of causes affecting quality and productivity.
Sundaram - Clayton Ltd
Pareto DiagramNo of Components250 200156 85.28 91.53 96.75 100
100
150105
6050.98
100 50
40 2020 16 9
0 Cold shut oil shot Damage Chip off Bad app
0
Types of Defects
Sundaram - Clayton Ltd
% Cumulative
80
What is Pareto Diagram ?Pareto diagrams are presentation technique used toshow facts and they help us to separate the vital few.
Pareto diagram was first thought out by an Italian economist,Pareto (1848 - 1923),when he used it as a method for national
income analysis to show that a large proportion of the wealthwas centered around a small minority of people.
After that,an American Quality Control Authority,Mr.Juran usedit in the field of Quality Control.
Sundaram - Clayton Ltd
Steps to make the pareto diagrams : Decide what problems are to be investigated and how to collect the data.
Design a data tally sheet listing the items,with space to recordtheir totals.
Fill out the tally sheet and calculate the totals (Example-1) Make the pareto diagram data sheet listing the items,their individual totals,cumulative totals,percentages of overall total, and cumulative percentages (Example-2)
Sundaram - Clayton Ltd
Steps to make the pareto diagrams : Arrange the items in the order of quantity,and fill out the data sheet.
Draw two vertical axes and a horizontal axis. Construct a bar diagram.
Draw the cumulative curve (Pareto curve). Write any necessary items on the diagram. 1) Items concerning the diagram. 2) Items concerning the data.
Sundaram - Clayton Ltd
Data Tally Sheet - Example -1Type of DefectCrack Scratch Stain Strain Gap Pinhole Others Total IIII IIII IIII IIII IIII IIII IIII IIII IIII IIII IIII IIII IIII IIII I IIII IIII IIII . IIII IIII IIII IIII . IIII II
Tally
Total10 42 6 104 4 20 14 200
Sundaram - Clayton Ltd
Data Sheet for Pareto Diagram - Example - 2Type of Defect Strain Scratch Pinhole Crack Stain Gap Others Total Number of Defect 104 42 20 10 6 4 14 200 Cumulative Total 104 146 166 176 182 186 200 Percentage of Overall Total 52 21 10 5 3 2 7 100 Cumulative Percentage 52 73 83 88 91 93 100
-
-
Sundaram - Clayton Ltd
Parteo Diagram by Defective Items :April 1 - June 30200
100 91 93100
160 140 120 100 80 60 40 20 0 D
73 52
80 70 60 50
104 42 20 10A
40 30 20
6C
4E
14Others
10 0
B
F
A : Crack, B : Scratch, C : Stain, D : Strain, E : Gap, F : Pinhole.
Sundaram - Clayton Ltd
Number of Units Investigated : 5,000
Cumulative Percentage
No of Defective Units
180
83
88
90
Cause & Effect DiagramMan Machine
Characteristics
Material
Method
Sundaram - Clayton Ltd
What is Cause & Effect Diagram ?Any defect in a component,a product or service could be due to one or more causes.To find out the relationship between
the causes and effect,a diagram is drawn systematically bymapping out all the probable causes influencing the effect. This is called a Cause & Effect Diagram Cause & effect diagram was introduced by Dr.K.Ishikawa. He used it in Kawasaki Iron Works in 1943. Since final diagram looks like a fish bone it is also called as Fish Bone Diagram.
Sundaram - Clayton Ltd
Format of a Cause and Effect DiagramMain Cause Main Cause A Level 3 Cause Level 2 Cause
Level 1 CauseCharacteristics
Main Cause
Main Cause
Above diagram depicts the basic format of Cause and Effect diagram. There is a hierarchical relationship of the effect to the main causes and their subsequent relationship to the subcauses.
Sundaram - Clayton Ltd
Procedure for Making Cause-and-effect Diagrams for Identifying Causes : Determine the quality characteristics. Choose one quality characteristics and write it on the righthand side of a sheet of paper,draw in the backbone form left to right,and enclose the characteristic in a square.Next, write the primary causes which affect the quality characteristics
as big bones also enclosed by squares.
Sundaram - Clayton Ltd
Procedure for Making Cause-and-effect Diagrams for Identifying Causes : Write the causes (Secondary causes) which affect the big bones (primary causes) as medium-sized bones,and write the causes (tertiary causes) which affect the medium-sized bones as small bones.
Assign an importance to each factor,and mark the particularlyimportant factor that seem to have a significant effect on the
quality characteristics. Record any necessary information.
Sundaram - Clayton Ltd
Example of Cause-and-Effect Diagram :HealthRelaxation Rest Amusement Time Sleep Quantity Nutrition Calories Meal Patience Carefulness Concentration Confidence Power Motion Speed Cooperation Schedule Exercise Quality Quantity Advice Form Repetition
Spirit
EncouragementPride Fighting spirit
Devotion CalmnessComposure
DepthInformation Theory Planning Rules Common sense Study of opponent Analysis
Defeat in a sports match
Observation
TeamworkFunction
Judgement of situation Experience of matches
Model
Strategy
Sundaram - Clayton Ltd
Technique
Example of Cause-and-Effect Diagram :MANWrong assembly Milling Depth under size M/c condition not ok High variation in the process
MACHINE
New operatorImportance not know to operator Hole location not taken during assembly No Poka yoke In adequate Fixture design
Gap less at suction side
Valve Plate Projecting out of cyl.head in 94 dia cylinder head assembly WHY?Hole position shifted
In adequate design
Valve plate outer dimn. oversize
METHOD
MATERIAL
Improper blanking
Sundaram - Clayton Ltd
Points to remembered. Once Cause & Effect diagram is made check for itscompleteness if required reviewed from the experts. A good Cause & Effect diagram gives an excellent understanding of a complex problem in a simple way. Cause & Effect diagram is not an answer of the problem. Main cause to be found out by collecting data or on collective experience. Less educated persons and with poor knowledge about process can be benefited by this.
Sundaram - Clayton Ltd
Graph & Control ChartUCL C/L LCL
Sundaram - Clayton Ltd
What is Graph :Graph is a pictorial representation of data which is easily
understandable at a glance.It is a visual representation of datamade up of points,lines,letters,words,numbers,shades etc.
Sundaram - Clayton Ltd
Types of Graphs :Line graph Bar chart / graph Pie chart or Circle graph Radar chart Compound graphs - bar and line Gantt chart
Sundaram - Clayton Ltd
Line Graph :709 700Qty Produced
662
550 376 275 250 Jan'03 Feb Mar Month Apr May June 273
400
330
Production detailsSundaram - Clayton Ltd
Bar Chart / Graph :10 9 8 7 6
7
6.3 4
Hrs
5 4 3 2 1 0 Jan'01 Feb'01
3.4
4 3
Mar'01
Apr'01
May'01
Jun'01
HMC Machine BreakdownSundaram - Clayton Ltd
Pie chart or Circle graph :Unwanted - 61 Tags removed - 59
Easy to CLI - 855 Tags removed - 850
Leakage - 845 Tags removed - 825
Electrical - 332 Tags removed - 325 Damage & Broken - 340 Tags removed - 334
Missing - 385 Tags removed - 380 Loose - 393 Tags removed - 390
Classification of abnormality tags.Sundaram - Clayton Ltd
Radar chartPlant performance : 2001-2002unit1100% 100%
50%
unit50.85 0%
unit280%
unit4
60%
unit390%
Sundaram - Clayton Ltd
Compound graph - Bar and Line
10 9 8 7 6 5 4 3 2 1 0 Jan'01 Feb'01 Mar'01
9.25 8.75 7 4.75 3 3 5 4 3.5 4 4.75 7
Frequency Hours
Apr'01
May'01
Jun'01
HMC Machine BreakdownSundaram - Clayton Ltd
Gantt chartT PM MA S T ER PL A NY E AR 1 9 98OV N T OC
TPM Master plan2 0 01 2 0 02R MA R MA Y MA OV N Y MA OV N T OC T OC G U A G U A N JA FEB PR A N JU EC D FEB PR A N JU EC D SEP SEP L JU L JU
1 9 99R MA Y MA OV N T OC G U A N JA FEB PR A N JU EC D SEP L JU
2 0 00R MA Y MA OV N T OC G U A N JA FEB PR A N JU EC D SEP L JU
2 0 03R MA Y MA OV N T OC G U A N JA FEB PR A N JU EC D SEP L JU
2 0 04R MA Y MA OV N OV N T OC G U A N JA FEB PR A N JU EC D EC D SEP SEP L JU
STA G E De c la ra tio n of T PM by M D T PM ins t ruc to r's c o urs e tr a ining in J IPM C om p a ny w ide 1 S, 2 S A c tiv ity T PM a w a r e ne s s pr ogra m to c ov e r a ll e m p loy e e s Se le c t M o de l m a c hine s a nd im pl e m e nt T PM TP M Kic k -o ff by M D
I n tro d u c ti o n s tag e
I mp l e me n ta ti o n s tag e
F u l l s ta g e d e ve l o p me n t
N JA
S Sttea ead dy ya ap pp pll ii c ca ati tio o n ns stag tage e
Le ve l 1 t ra i n i ng Le v el 2 t ra i n i ng
S e l ec t 4 m ac hi n es o ne f rom ea c h u n i t
Le v el 3 t ra i n i ng
F o r A ra n k m ac h i n e s - 10 m ac hi n es S t e p 1 , 2, 3 Ste p 4 Ho ri zo nt a l rep l i c at i o n a s i n A ra n k m ac hi n es
J IS H U H O ZEN AC TIVI TY P LAN
F o r B ra n k m ac h i n e s - 10 m ac hi n es S t e p 1 , 2, 3 Ste p 4 Ho H ori ri zo zont na t al l rep repl li c cat i ai t io on na assi in nB B ra rannkkm mac achi hinnes es
F o r A ra n k m ac h i n e s - 10 m ac hi n es E l i mi n at e sc rap S u st a i n ze ro sc rap
Ho ri zo nt a l rep l i c at i o n a s i n A ra n k m ac hi n es
HIN SH ITS U H O ZEN AC TIVI TY P LAN
F o r B ra n k m ac h i n e s - 10 m ac hi n es E l i mi n at e sc rap S u st a i n ze ro sc rap Ho H ori ri zo zont na t al l rep repl li c cat i ai t io on na assi in nB B ra ran nkkm mac achi hin nes es F o r A ra n k m ac h i n e s - 10 m ac hi n es I mp ro ve OE E t o 8 5 % Ho ri zo nt a l rep l i c at i o n a s i n A ra n k m ac hi n es
KO B ETS U KA IZEN AC TIVI TY P LAN
F o r B ra n k m ac h i n e s - 10 m ac hi n es I mp ro ve OE E t o 8 5 % Ho H ori ri zo zont na t al l rep repl li c cat i ai t io on na assi in nB B ra ran nkkm m ac achi hin nes es
F or A ra nk m ac hi n es - 10 m ac hi n es Eli m i na t e b re ak do wn S us t ai n ze ro b re ak do wn b y i nt ro du c i ng T BM H ri ori zo li c io n t in ra ac es Ho zo ntn atlal rerep pl ic ata i on aa ss in AAra nn kk mm ac hihi nn es F or B ra nk m ac hi n es - 10 m ac hi n es Eli m i na t e b re ak do wn S us t ai n ze ro b re ak do wn b y i nt ro du c i ng T BM H ri ori zont nat lal li cat a io n t in ra mac ac es Ho zo rerep pl ic i on aa ss in BBra nn kk m hihi nn es
P LA NN ED M A INT EN AN C E AC TIVIT Y P LAN
IN ITIA L FL OW C ON TR O L O FFIC E T PM S AF ETY & H Y GIE N E AC TIVIT Y P LAN ED UC A TIO N & TR AIN IN G A C TIVIT Y P LAN PR EL IM INA R Y AU D IT FI NA L AU D ITR MA R MA R MAR MA R MA R MA
Y MA
OV N
Y MA
OV N
Y MA
OV N
OV N
OV N
OV N
Y MA
Y MA
Y MA
T OC
T OC
T OC
T OC
T OC
T OC
G U A
G U A
LEGEND
Sundaram - Clayton Ltd START MILESTONE PLANNED
1 9 98
1 9 99
2 0 00
2 0 01
2 0 02
2 0 03
2 0 04
PLANNED FINISH
G U A
G U A
G U A
G U A
N JA
FEB
PR A
N JU
EC D
N JA
FEB
PR A
N JU
EC D
N JA
FEB
PR A
N JU
N JA
FEB
PR A
N JU
EC D
N JA
FEB
PR A
N JU
EC D
N JA
FEB
PR A
N JU
EC D
SEP
SEP
SEP
SEP
SEP
L JU
L JU
L JU
L JU
L JU
L JU
Y E AR
T OC
What is Control Chart :Control chart is a graphical device to aid in process control. It consist of a graph with a central line denoting the target value and two limit lines on either side of the central line called Upper control limit & Limit control limit.Quality measured periodically is plotted on the chart and status of control assessed. The control chart was first proposed by Dr.Walter A Shewhart,an engineer in the Bell Telephone Laboratories,USA with a view to eliminate abnormal variation.
Sundaram - Clayton Ltd
Two Types of Variations :1. Chance Causes. 2. Assignable Causes. 1. Chance Causes :
Which are uncontrollable and comprising very smalldifferences in raw materials in the same batch or machines, actual conditions etc. 2. Assignable Causes : Such as different settings of a machine,different raw material batches,changes in operators,operator errors etc.
Sundaram - Clayton Ltd
Types of Control ChartCharacteristic Value Continuous value x chart (measured value) pn chart (number of defective units) p chart (fraction defective) Discrete value c chart (number of defects) u chart (number of defects per unit) Name x - R Chart (average value and range)
Sundaram - Clayton Ltd
Types of Control Chart :x - R ChartIt is used for controlling and analyzing a process using
continuous values of product quality such as length,weight orconcentration and this provides the larger amount of information
on the process. x represents an average value of a subgroupand R represents the range of the subgroup. An R chart is used usually in combination with an x chart to control the variation within a subgroup.
Sundaram - Clayton Ltd
Procedure to make control charts :x - R Chart Collect the data. Calculate x x = x1 + x2 ++ xn n - Size of a sub group
n Calculate x
x = x1 + x2 ++ xkk
k - Number of subgroups
Sundaram - Clayton Ltd
Procedure to make control charts :x - R Chart Calculate RR = (Maximum value in a subgroup) - (Minimum Value in a subgroup)
Calculate RR = Rx1 + Rx2 ++ Rn k
Sundaram - Clayton Ltd
Procedure to make control charts :x - R Chart Calculate the control lines x Chart Central line : CL = x
Upper control limit :UCL = x + A2R. Lower control limit :
UCL = x - A2R
Sundaram - Clayton Ltd
Procedure to make control charts :x - R Chart Calculate the control lines R Chart Central line : CL = R
Upper control limit :UCL = D4R. Lower control limit :
LCL = D3R
Sundaram - Clayton Ltd
Procedure to make control charts :List of Coefficients for x - R Chart.Size of Subgroup x Chart n A2 2 3 4 5 6 1.88 1.023 0.729 0.577 0.483 R Chart D3 ----------D4 3.267 2.575 2.282 2.115 2.004 d2 1.128 1.693 2.059 2.326 2.534
Sundaram - Clayton Ltd
Procedure to make control charts :x - R Chart Draw the control lines. Plot the points. Write the necessary items.
Sundaram - Clayton Ltd
Examples of Control Chart :UCL C/L LCL Control Chart for Controlled State UCL C/L LCL Control Chart for Uncontrolled State
Sundaram - Clayton Ltd
Examples of Control Chart :Average chart (X)READINGS 52.043 USL LSL Xdbar 52.035 52.031 1 3 5 7 9 11 13 15 17 19 21 23 25 Samples UCL XBAR LCL XBAR
Readings
52.039
1 1 1 1 1 1
Range chart (R)0.015 0.01
0.005
Sundaram - Clayton Ltd
How to Read Control Charts : Out of control limits. Run.
Seven-point length of run is abnormal.
Ten out of 11 consecutive points occurring on one side is abnormal.
RunSundaram - Clayton Ltd
How to Read Control Charts :TrendSeven upward points Drastic downward trend
Sundaram - Clayton Ltd
How to Read Control Charts :Approach to the control limits (2 out of 3 points)3-sigma line 2-sigma line
2-sigma line 3-sigma line
Sundaram - Clayton Ltd
How to Read Control Charts :Approach to the central line.3-sigma line 1.5-sigma line
Sundaram - Clayton Ltd
How to Read Control Charts :Periodicity
Sundaram - Clayton Ltd
Histogram40 34 38 35 30
25
20
15 9 9.9
10 4 0 0 4
5
4.5 2.5 2.5
0
3.3 3.35 3.4 3.45 3.5 3.55 3.6 3.65 3.7
Sundaram - Clayton Ltd
What is Histogram :Histogram is a graphical representation of a frequency distribution which is a summary of variation in a product or process.
Sundaram - Clayton Ltd
Steps to construct the Histogram : Collect 100 reading. Find out lowest & highest value of reading row wise.
Find out lowest & highest from all the rows. Compute the range . R = Max - Min. Follow standard table for no of classes.No of Observations No of Classes ( k ) < 50 6 51 - 100 7 101 - 200 8 201 - 500 9 501 - 1000 10
Sundaram - Clayton Ltd
Graph to Determine K
20 18 16 14
k
12 10 8 6 4 2 0 1 2 3 4 5 678 10 20 50 200 500 1,000
n Sundaram - Clayton Ltd n - Numbers of Measurements.
Steps to construct the Histogram : Calculate the approximate width of class with the help offormula ( R + W ) / K
Where R is the range. W is accuracy in the observation& K is no.of classes.Make the frequency table and then draw the histogram. Note Classes should be continuous.i.e 1-5,5-10,10-15 etc. All classes should have same width.
Sundaram - Clayton Ltd
Histogram data sheet1 2 3 4 5 6 7 8 9 10 104.1 104.4 104.3 104.5 104.4 104.3 104.2 104.5 104.3 104.5 11 12 13 14 15 16 17 18 19 20 104.5 104.3 104.4 104.5 104.4 104.5 104.2 104.4 104.3 104.4 21 22 23 24 25 26 27 28 29 30 104.4 104.5 104.4 104.3 104.2 104.4 104.6 104.4 104.3 104.1 31 32 33 34 35 36 37 38 39 40 104.4 104.3 104.4 104.7 104.2 104.4 104.3 104.5 104.4 104.3 41 42 43 44 45 46 47 48 49 50 104.6 104.4 104.6 104.7 104.3 104.5 104.2 104.5 104.4 104.3
Sundaram - Clayton Ltd
Tally Data Sheet104.1 - // 104.2 - //// 104.3 - //// //// // 104.4 - //// //// //// / 104.5 - //// ////
104.6 - ///104.7 - //Sundaram - Clayton Ltd
Examples of Histogram :20 16 15 10 5 5 0 104.1 104.2 104.3 104.4 104.5 104.6 104.7 in mm 2 3 2 12 10
Sundaram - Clayton Ltd
Interpretation of HistogramMinimum Limit1
Maximum Limit
Minimum Limit4
Maximum Limit
2
5
6 3
Sundaram - Clayton Ltd
Types of Histogram :
a) General type
b) Comb type
c) Positively skew type
d) Lefthand precipice type
Sundaram - Clayton Ltd
Types of Histogram :
e) Plateau type
f) Twinpeak type
g) Isolatedpeak type
Sundaram - Clayton Ltd
Uses of Histogram : To know the pattern of variation. To assess states of control To assess conformance to specifications To assess spread or variation with reference to specification. To assess process capability.
To get clues for bringing process under control - whether toshift mean or to reduce variation or both. To get clues for possible assignable causes for observed variation - mixture of lots,suppliers,instruments / measurements errors,bias of written results etc.
Sundaram - Clayton Ltd
StratificationQuality Defective (Nos)50 40 30 20 10 0A B C D E
48%
16%
18% 12% 6%
Types of Defect
Sundaram - Clayton Ltd
What is Stratification :Stratification is the process of separation of data into
categories.It is normally done for identifying the categoriescontributing to the problem tackled.
Sundaram - Clayton Ltd
Types of Stratification :Material Based :48%50 40
Defective %
30 20 10 0A B C
16 %
15%
Supplier
Defective Quality - Supplier Wise.Sundaram - Clayton Ltd
Types of Stratification :Quality Based :Quality Defective(Nos)50 40 30 20 10 0A B C D C
48%
16%
18% 12% 6%
Type of Defect
Defects Data For Each Hour in a ShiftSundaram - Clayton Ltd
Types of Stratification :Worker Based :30
No of Defective
25 20 15 10 5 0A
22%
5%
3%B C
Worker
Defective AssembliesSundaram - Clayton Ltd
Types of Stratification :Machine Based :100 90 80 70 60 50 40 30 20 10 0
Production %
57% 43%
A
B
Machine
Production Machine WiseSundaram - Clayton Ltd
Types of Stratification :Processing Based :Power Consumption %50 40
32%30 20
25% 12%
26%
10 0A B C
5%D E
Process Area
Power Consumption Process Area WiseSundaram - Clayton Ltd
Scatter Diagram4.5 4.4
Overall rating of the Session
4.3 4.2 4.1 4 3.9 3.8 3.7 3.6 3.5 3.4 100 150 200 250 300 350 400 450 500 550 600 650
4.0 y axis 430 x axis
Average Experience of Training Team (in days)
Sundaram - Clayton Ltd
What is Scatter Diagram :Scatter diagram is a graphical representation of relationship between two variables.It can be between a Cause & Effect and between causes. In 1837 J.F.W.Herswchal,an Englishman,used scatter diagram. In 1950s Dr.K.Ishikawa popularized the use of scatter diagram.
Sundaram - Clayton Ltd
Steps to draw Scatter Diagram : Collect paired data (x,y) Find the maximum and minimum values for both the x and y. Plot the data. Enter all necessary items.
Sundaram - Clayton Ltd
The horizontal (x axis) and vertical (y axis) lines of the diagram:
The measurement scales generally increase as you move up the vertical axis and to the right on the horizontal axis.
4.5 4.4 4.3 4.2 4.1 4.0 3.9 3.8 3.7 3.6 3.5 150 200 250 300 350 400 450 500 550 600 650 * Looking for relationships not cause & effect Dependent variable (effect)
Independent variable (cause)
Sundaram - Clayton Ltd
Examples of Scatter Diagram :4.5 4.4 4.3 4.2 4.0 y axis 4.1 430 x axis 4 3.9 3.8 3.7 3.6 3.5 3.4 100 150 200 250 300 350 400 450 500 550 600 650
Overall rating of the Session
Average Experience of Training Team (in days)
Sundaram - Clayton Ltd
Possibilities after plotting the pointsa. Positive relationship b. No correlation. c. Negative correlation. d. Positive & Negative correlation.
e. Negative & Positive correlation.
Sundaram - Clayton Ltd
n = 30y 6 4 2 0 0 2 4
r = 0.9y6 4
n = 30
r = 0.6y 6 4 2 0
n = 30
r = 0.0
20 6 x 0 2 4 6 x
0
2
4
6
x
Positive Correlation
Positive Correlation May Be Present
No Correlation
n = 30y 6 4 2 0 0 2 4
r = 0.9y 6 4 2 0 6 x 0
n = 30
r = 0.6
2
4
6
x
Negative Correlation
Negative Correlation May Be Present
Sundaram - Clayton Ltd
Sundaram - Clayton Ltd