You are on page 1of 46

Series A

TQM Training Module on


Histogram
Doc. No. A-07.02.20180603
Revision 02; 03rd June 2018
Authors: Pankaj Lochan

For further clarifications, write to Pankaj.lochan@jsw.in


© Total Quality Management, JSW Group
TQM Training Series: 6 series with 66 training modules
This is training module: Histogram(A-07)
Series-A Series-C Series-D Series-F
Basic Problem Solving Tools Quality Management Basics Productivity & Efficiency Tools Advanced Statistical Tools
A-01 Flow Charts C-01 Quality Mgmt. Basics D-01 Value Stream Mapping (VSM) F-01 Sampling & Distribution
A-02 Cause & Effects Diagram C-02 Basic Statistics D-02 Time & Motion Study F-02 Hypothesis Testing
A-03 Stratification C-03 Statistical Process Control D-03 SMED F-03 Regression
A-04 Scatter Diagram C-04 KPI Drill Down D-04 Wrench Time Analysis F-04 Basics of DoE
A-05 Control Charts C-05 KPI Benchmarking D-05 Queuing Theory F-05 Factorial DoE
A-06 Check Sheets C-06 Strategic Analysis Tools D-06 Inventory Management F-06 Principal Component Analysis
A-07 Histogram C-07 Policy Management D-07 Linear Programming Problem F-07 Cluster Analysis
C-08 Policy Diagnosis F-08 Conjoint Analysis
A-08 Pareto Charts D-08 Game Theory
C-09 Daily Management F-09 Discriminant Analysis
A-09 Graphs D-09 OEE
C-10 Daily Mgmt. in Maintenance F-10 Factor Analysis
D-10 PERT & CPM
C-11 Cross Functional Mgmt.
Series-B F-11 Response Surface Method
C-12 Quality Assurance Basics
Basic Management Tools F-12 Taguchi DoE
C-13 MSA
B-01 Brainstorming F-13 Weibull Analysis
C-14 PFD, FMEA, Control Plan Series-E
B-02 Affinity Diagram Decision-making Tools
C-15 Cost of Poor Quality (COPQ)
B-03 Arrow Diagram C-16 Improvement Fundamentals E-01 Quality Function Deployment
B-04 Tree Diagram C-17 4i Methodology E-02 Fault Tree Analysis
B-05 PDPC C-18 5S E-03 AHP & Paired Analysis
B-06 Matrix Diagram C-19 Quality Circles E-04 Pugh Matrix
B-07 Matrix Data Analysis C-20 QC Story Approach E-05 Time Motion Series
B-08 Relation Diagram C-21 Kaizen, OPL, Poka Yoke
FLOW OF THE TRAINING DOCUMENT

1 Introduction to Histogram

2 Steps of Histogram Construction

3 Examples from our Plant

4 Making a Histogram in MS-Excel


DISCRETE AND CONTINUOUS DATA

Discrete Data

A set of data is said to be discrete if the values / observations belonging to it are


distinct and separate, i.e. they can be counted. It is also a set of data that cannot
take decimal values.

Example: Number of good or bad parts in a lot, Number of students in a class etc.

Continuous Data

A set of data is said to be continuous if the values / observations belonging to it


may take on any value within a finite or infinite interval. You can count, order and
measure continuous data. So continuous data can take decimal values and still
make a sense.

Example: height, weight, temperature, the amount of carbon percentage in hot


metal, the time required to complete one heat.
HISTOGRAM: AN INTRODUCTION

 Histogram is a tool for graphically portraying a frequency distribution. It enables


the user to obtain useful information about the shape and dispersion (spread) of
a set of data.
 The histogram enables a very concise portrayal of a KPI data / other data /
information in a bar chart format and helps understand / characterise data.
Difference between Histogram and Pareto Diagram
Histogram Pareto Diagram

Histogram is a tool that illustrates the


Pareto diagram is a tool for
Purpose frequency of occurrence of an
prioritizing data
event, using height of bar as indicator

Used for both continuous and


Type of data Used only continuous data
discrete data

Used to analyse Location (Mean), Used for identify vital few causes
Application Spread (variation or Std. Deviation) that contribute to majority of effects
and Shape (distribution) of Data by using the Pareto 80/20 rule
HISTOGRAM: AN INTRODUCTION

A graphical representation, similar to a


bar chart in structure, that organizes a
group of data points into user-specified

Frequency
ranges. The histogram condenses a data
series into an easily interpreted visual by
taking many data points and grouping
them into logical ranges or bins.
Etymology:
Derived from the Greek words - Histos –
Any thing set upright, Gamma- Drawing Class interval

record writing
It is also said, Karl Pearson introduced
the term histogram in 1891, derived the
name from “Historical Diagram”.
HISTOGRAM OVERVIEW

Location

Histogram speaks about:

Frequency
Shape
Location The mean or
average value, of a set of
data.

Shape The type of Data


Distribution. µ-3σ µ-2σ µ-σ µ µ+σ µ+2σ µ+3σ

Spread
Spread The total amount of µ - Average or mean value
variation or deviation
from the mean value. σ - Standard deviation or
variation
HISTOGRAM – TYPES

Typical Histogram Shapes and What They Mean

1. Normal. A common pattern is the bell–shaped


curve known as the “normal distribution.” Here,
points are as likely to occur on one side of the
average similar to the other side.

2. Skewed. The skewed distribution is asymmetrical


because a natural limit prevents outcomes on one
side. The distribution’s peak is off centre toward
the limit and a tail stretches away from it.

3. Comb. In a comb distribution, the bars are


alternately tall and short. This distribution often
results from rounded-off data and / or an
incorrectly constructed histogram

4. Dog food. The dog food distribution is missing


something—results near the average.
HISTOGRAM – TYPES

Typical Histogram Shapes and What They Mean

5. Double-peaked or bimodal. The outcomes of


two processes with different distributions are
combined in one set of data.

6. Plateau. The plateau might be called a


“multimodal distribution.” Several processes with
normal distributions are combined.

7. Edge peak. The edge peak distribution looks like


the normal distribution except that it has a large
peak at one tail. Usually this is caused by faulty
construction of the histogram, with data lumped
together into a group labelled “greater than…”

8. Truncated or heart-cut. The truncated


distribution looks like a normal distribution with
the tails cut off.
FLOW OF THE TRAINING DOCUMENT

1 Introduction to Histogram

2 Steps of Histogram Construction

3 Examples from our Plant

4 Making a Histogram in MS-Excel


STEPS OF CONSTRUCTION

Standard Table for Class


Intervals
Collect Data, Minimum Hundred data points Number of Data Recommended
1
Points Number of
Classes
Determine Max value, Min value & calculate range 20 - 50 06
2
Range = Maximum value – Minimum value
51 - 100 07

Determine number of classes, by referring standard table or by 101 – 200 08


3
taking square root of number of observations
201 – 500 09
501 – 1000 10
Determine the width of class interval (W)
4
W = Range/Total number of classes Above 1000 11 - 20

5 Construct Frequency distribution table

Construct Histogram ,class interval as


6
X – axis and frequency as Y - axis
ILLUSTRATIVE EXAMPLE
EXAMPLE-1

Hundreds of people are struck by lightning every year in the U.S., problem of satellite
launching was a main concern as many satellite’s failed, being hit by lightening. A collection
of lightning data for a few years ended up with huge number of data points, so they decided
to use Histogram

1 Collect Data, Minimum 100 data points

First Lightning time


8 9 7:15 8:22 12:01 1:05 12:32 12:45 12:01 1:04 1:34 11:32 11:43 11:23 11:32 11:16 11:23 1:05 1:12 1:32 2:12 2:13 2:32 2:10 3:45
am am am am am pm pm pm pm pm pm am am am am am am pm pm pm pm pm pm pm pm

3:43 3:23 3:15 3:01 4:44 4:42 4:21 4:16 4:12 6:12 6:12 6:15 6:34 6:23 11:12 11:13 11:01 11:23 11:24 1:02 1:04 2:04 10:22 11:23 12:23
pm pm pm pm pm pm pm pm pm am am am am pm am am am am am pm pm pm am am pm

8 9 7:15 8:22 12:01 1:05 12:32 12:45 12:01 1:04 1:34 11:32 11:43 11:23 11:32 11:16 11:23 1:05 1:12 1:32 2:12 2:13 2:32 2:10 3:45
am am am am am pm pm pm pm pm pm am am am am am am pm pm pm pm pm pm pm pm

3:43 3:23 3:15 3:01 4:44 4:42 4:21 4:16 4:12 6:12 6:12 6:15 6:34 6:23 11:12 11:13 11:01 11:23 11:24 1:02 1:04 2:04 10:22 11:23 12:23
pm pm Pm pm pm pm pm pm pm am am am am am am am am am am pm pm pm am am pm
ILLUSTRATIVE EXAMPLE
EXAMPLE-1

2 Calculate Range Standard Table for Class Intervals


Range = Maximum value – Minimum value
Number of Data Recommended
Range = 4:44pm – 06:12am
Points Number of Classes
Range = 10hrs 32 min’s.
20 - 50 06
3 Determine number of classes 51 - 100 07
Referring Standard Table, For Hundred data 101 – 200 08
points 201 – 500 09
Number of Classes should be Seven 501 – 1000 10
4 Above 1000 11 - 20
Determine the width of class interval
(W)
W = Range/Total number of classes
W = 10.5hrs/07
W = 1.5hrs, for convenience taken as 2 hrs
ILLUSTRATIVE EXAMPLE
EXAMPLE-1

5 Construct Frequency distribution table

Sl.No Class Interval Frequency


01 12pm - 2 am 0.00
02 2am -4am 0.00
03 4am - 6am 0.00
04 6am - 8am 8.00
05 8am - 10am 12.00
06 10am - 12pm 26.00
07 12pm - 2pm 24.00
08 2pm - 4pm 20.00
09 4pm - 6pm 10.00
10 6pm -8pm 0.00
ILLUSTRATIVE EXAMPLE
EXAMPLE-1

6 Construct Histogram ,class interval as X – axis and frequency


as Y - axis 11 pm
30.00
26.00
25.00 24.00
Frequenc

20.00
20.00
y

15.00
12.00
10.00
10.00 8.00

5.00
0.00 0.00 0.00 0.00
0.00
12pm - 2 2am - 4am - 6am - 8am - 10am - 12pm - 2pm - 4pm - 6pm -
am 4am 6am 8am 10am 12pm 2pm 4pm 6pm 8pm

Time Period
ILLUSTRATIVE EXAMPLE
EXAMPLE-1

Inference from the Histogram

By observing the Histogram created in Step No. 6,

The first Lightning Strikes varies between 6am to 6pm.

The maximum Number of first lightning strikes occurs between


10am to 12pm.

Hence we conclude that:


Any Satellite Launching activities should be carried out before
6am in the morning or after 6pm in the evening to avoid
damage of satellite by lightning.
FLOW OF THE TRAINING DOCUMENT

1 Introduction to Histogram

2 Steps of Histogram Construction

3 Examples from our Plant

4 Making a Histogram in MS-Excel


OUR PLANT
EXAMPLE
PLANT EXAMPLE 1 – HOT STRIP MILLS

The problem of load variation of rolling is seen frequently in Hot strip mills,
analyse the roughing mill temperature sample data using Histogram tool and
Infer.
1 Collect Data, Minimum 100 data points

Roughing mill temperature (0C)


106 107 107 108 107 105 106 108 106 109 107 108 107 103 106 108 107 106 108 106 109 104 105 105 106
6 4 6 1 2 9 9 2 5 3 2 0 8 7 8 2 3 3 1 9 2 6 2 2 2

107 107 106 106 107 107 106 106 109 107 107 109 109 107 106 107 106 107 105 107 105 106 104 106 107
5 5 7 9 4 1 2 2 7 2 0 3 0 0 5 4 3 1 7 5 4 3 6 5 2

107 107 103 104 105 106 106 107 106 107 106 107 107 105 107 106 107 107 106 105 107 107 104 108 103
8 8 4 6 5 7 6 6 9 1 7 2 0 4 7 0 1 5 7 3 4 1 7 5 8

105 108 105 108 108 108 107 106 106 107 106 106 106 108 107 107 107 107 103 106 106 106 104 107 104
8 3 5 6 3 2 7 8 7 1 8 7 3 2 3 7 8 1 9 9 7 2 8 7 6
OUR PLANT
EXAMPLE
PLANT EXAMPLE 1 – HOT STRIP MILLS

2 Calculate Range Standard Table for Class Intervals


Range = Maximum value – Minimum value
Number of Data Recommended
Range = 1097 - 1034
Points Number of Classes
Range = 63
20 - 50 06
3 Determine number of classes 51 - 100 07
Referring Standard Table, For Hundred data 101 – 200 08
points 201 – 500 09
Number of Classes should be Seven 501 – 1000 10
4 Above 1000 11 - 20
Determine the width of class
interval (W)
W = Range/Total number of classes
W = 63/07
W=9
OUR PLANT
EXAMPLE
PLANT EXAMPLE 1 – HOT STRIP MILLS

5 Construct Frequency distribution table

Sl.No Class Interval Frequency


01 1034 - 1043 4
02 1043 - 1052 8
03 1052 - 1061 9
04 1061 - 1070 31
05 1070 - 1079 32
06 1079 - 1088 11
07 1088 - 1097 5
OUR PLANT
EXAMPLE
PLANT EXAMPLE 1 – HOT STRIP MILLS

6 Construct Histogram ,class interval as X – axis and frequency


as Y - axis 1068.3
4
35 32
Inference from the
30 Histogram
31
Frequenc

25  The Roughing mill temp


20 varies between 10340C to
y

10970C.
15  Mean value of
11
10 8 9 temperature is around
4 5 1068.340C.
5
0
1034 - 1043 - 1052 - 1061 - 1070 - 1079 - 1088 -
1043 1052 1061 1070 1079 1088 1097

Temperature in
0C
OUR PLANT
EXAMPLE
PLANT EXAMPLE 2 – BLAST FURNACES

The problem of silicon variation in hot metal is seen frequently in Blast Furnaces;
Purpose: Analyse the silicon content in hot metal sample data using Histogram tool
and Infer.

1 Collect Data, Minimum 100 data points

Silicon Content in Hot Metal (%)

0.74 0.53 0.30 0.38 0.52 0.38 0.53 0.50 0.45 0.68 0.66 0.67 0.64 0.68 0.57 0.58 0.61 0.58 0.72 0.73 0.61 0.90 0.85 0.72 0.66

0.75 0.66 0.68 0.74 0.67 0.72 0.75 0.70 0.70 0.60 0.57 0.53 0.56 0.71 0.67 0.58 0.59 0.67 0.53 0.53 0.53 0.84 0.74 0.73 0.83

0.76 0.55 0.68 0.57 0.54 0.45 0.55 0.49 0.33 0.47 0.77 0.76 0.55 0.54 0.58 0.53 0.53 0.57 0.52 0.53 0.51 0.46 0.59 0.61 0.60

0.49 0.62 0.60 0.61 0.69 0.60 0.60 0.68 0.47 0.49 0.51 0.51 0.94 0.95 0.76 0.60 0.60 0.60 0.59 0.61 0.48 0.76 0.59 0.58 0.70
OUR PLANT
EXAMPLE
PLANT EXAMPLE 2 – BLAST FURNACES

2 Calculate Range Standard Table for Class Intervals


Range = Maximum value – Minimum value Number of Data Recommended
Range = 0.95 – 0.3 Points Number of Classes
Range = 0.65 20 - 50 06
3 Determine number of classes 51 - 100 07
101 – 200 08
Referring Standard Table, For Hundred data
points 201 – 500 09
Number of Classes should be Seven 501 – 1000 10
4 Above 1000 11 - 20
Determine the width of class interval
(W)
W = Range/Total number of classes
W = 0.65/07
W = 0.0928
OUR PLANT
EXAMPLE
PLANT EXAMPLE 2 – BLAST FURNACES

5 Construct Frequency distribution table

Sl.No Class Interval Frequency

01 0.3 - 0.39 4

02 0.39 - 0.48 6

03 0.48 - 0.57 28

04 0.57 - 0.66 31

05 0.66 - 0.75 24

06 0.75 - 0.84 4

07 0.84 - 0.93 2

08 0.93 - 1.02 1
OUR PLANT
EXAMPLE
PLANT EXAMPLE 2 – BLAST FURNACES

6 Construct Histogram ,class interval as X – axis and frequency


as Y - axis
0.63%
35 Inference from the Histogram

30  The silicon content in hot metal


31 varies from 0.30% to
25 0.95% .
28
Frequenc

 The Mean value of silicon is


20 24 around 0.63%.
y

15
10
5 2
4 6 4 1
0
0.3 - 0.39 - 0.48 - 0.57 - 0.66 - 0.75 - 0.84 - 0.93 -
0.39 0.48 0.57 0.66 0.75 0.84 0.93 1.02

Silicon in %
FLOW OF THE TRAINING DOCUMENT

1 Introduction to Histogram

2 Steps of Histogram Construction

3 Examples from our Plant

4 Making a Histogram in MS-Excel


CONSTRUCTION OF HISTOGRAM IN EXCEL

The problem of load variation of rolling is seen frequently in Hot strip mills,
analyse the roughing mill temperature sample data using Histogram tool
and Infer.

Let us take the same Hot Strip Mill example and try to construct a
Histogram in MS-Excel
Roughing mill temperature (0C)

106 107 107 108 107 105 106 108 106 109 107 108 107 103 106 108 107 106 108 106 109 104 105 105 106
6 4 6 1 2 9 9 2 5 3 2 0 8 7 8 2 3 3 1 9 2 6 2 2 2

107 107 106 106 107 107 106 106 109 107 107 109 109 107 106 107 106 107 105 107 105 106 104 106 107
5 5 7 9 4 1 2 2 7 2 0 3 0 0 5 4 3 1 7 5 4 3 6 5 2

107 107 103 104 105 106 106 107 106 107 106 107 107 105 107 106 107 107 106 105 107 107 104 108 103
8 8 4 6 5 7 6 6 9 1 7 2 0 4 7 0 1 5 7 3 4 1 7 5 8

105 108 105 108 108 108 107 106 106 107 106 106 106 108 107 107 107 107 103 106 106 106 104 107 104
8 3 5 6 3 2 7 8 7 1 8 7 3 2 3 7 8 1 9 9 7 2 8 7 6
1. INSERTING DATA IN EXCEL

1: Insert the
data collected in
excel sheet .
2. SORTING DATA IN EXCEL

2: Select Sort & Filter

2a. Select Sort


Largest to Smallest
3. IDENTIFYING MAXIMUM AND MINIMUM
VALUE

3a: Identify Maximum


Value

3b.Identify
Minimum Value
4 & 5. CALCULATE RANGE AND DETERMINE
WIDTH OF CLASS INTERVAL

5: Determine
width of class
interval(W)
4: Calculate
Range
6. CONSTRUCTION OF FREQUENCY
DISTRIBUTION TABLE

6: Construct
Frequency
Distribution Table
7. SELECT COLUMNS TO PUT HISTOGRAM

7: Select two
columns - Class
interval, Frequency
8 & 9. SELECTION OF COLUMN OPTION

8: Select Insert
option 9: Select Column
10. SELECTION OF 2D COLUMN

10: Select 2-D


Column
11. OBTAIN GRAPH

11: We will get


this graph
12 & 13. FORMAT DATA SERIES

12. Right Click on


the Bar Chart

13. Select ‘Format


Data Series’
option
14,15,16. REDUCING GAP BETWEEN BARS

16. Increase
“Separated” to
“Overlapped”

14. We will get


this dialog box

15. Reduce the


gap to ‘0%’
17 & 18. FORMATTING TYPE OF BORDER

18. Select
“Solid line”
option

17. Select
“Border
Color” option
19. FORMATTING COLOR OF BORDER

19. . Select
“Color” option as
“Black”
20. OBTAIN GRAPH

20. We will get this


graph
21 & 22. ADD DATA LABELS

22. Select
‘Add Data
Labels’
21. Right Click on
option
the Bar Chart
23. FINAL HISTOGRAM

23. Formed is the


Histogram Chart,
by looking at
which we can
identify Location,
Spread and Shape
WHERE TO USE A HISTOGRAMS?

 When you want to see the shape of the data’s distribution - determining
whether the output of a process is distributed approximately normally or not ?

 When analyzing whether a process can meet the customer’s requirements.

 When analyzing what the output from a supplier’s process looks like.

 When seeing whether a process change has occurred from one time period to
another

 Analysing the impact of an improvement action – checking whether the shift in


Mean or Variation has happened or not ?

 When comparing outputs of two processes for their current level of process
capability (Mean, Variance)

 When you wish to communicate the distribution of data quickly and easily to
others.
Please login to:
tqm.jsw.in
to read the training modules
THANK YOU

You might also like