1. MAHARASHTRA INSTITUTE OF TECHNOLOGY,
AURANGABAD
(PLASTICS AND POLYMER ENGINEERING DEPT.)
PRESENTATION ON:-
STRATIFICATION : A PROBLEM SOLVING TECHNIQUE
NAME-ANSHUL GAUTAMPURKAR
CLASS- T.Y.
ROLL NO.-T3715
2. What is a “Problem “?
“Problem is an undesirable event” or ..
Any Gap between what is expected and what is obtained , can be called as a
Problem, and any effort to reduce this gap can be called as “Problem Solving ”
Expected
(Gap ?) A Problem!
Obtained
3. A problem can be solved by two techniques:-
Old Tools New Tools
Tally Affinity
Sheet/Check Diagram
Sheet
Pareto Relation
Diagram Diagram
Cause and Tree
Effect Diagram
Diagram
Graphs/Hist Process
ograms Decision
Program
Stratification Chart
Arrow
Diagram
Scatter
Diagram Matrix Data
Analysis
Diagram
Control Brain
Chart storming
Flow Chart
4. Manufacturer, buyer, brand, place of production, purchase
1. By material
date, lot received, production lot, components, purity, size,
parts, time stored, storage place, etc.
2. By machine, Machine type , number, model, performance, and age: by
equipment, or tool factory, line, tool, and die.
3. By operator Individual, team, group, age, experiences, gender, etc.
4. By operating procedure Temperature, pressure, speed, rational frequency, line
and by operating speed,location of operation, illumination, air temperature,
conditions humidity,weather, operating procedure, etc.
5. By measurement and Instrument, measurement procedure, place of measurement.
inspection Person making the measurement, inspection tools, inspection
procedures, place of inspection, inspector, etc.
Time, morning, afternoon, night, day, week, month, period
6. By time
season, etc: just before starting and just after finishing the
operation.
5. 7. By environment Air temperature, humidity, clear, cloudy, rainy, windy,
and weather snowy, rainy season, dry season, sound, illumination, etc.
New vs.. previous product, unit product vs.. continuously
8. Others
produced product, good product vs.. defective product,
packing method and transportation method etc.
6. Stratification
Definition
• Stratification is a technique used in combination with other data
analysis tools. When data from a variety of sources or categories have
been lumped together, the meaning of the data can be impossible to
see. This technique separates the data so that patterns can be seen.
• Classification of a mass of data (obtained from research or survey)
into categories and sub-categories on the basis of one or more
chosen criteria.
• Hierarchical arrangement of a society into different layers (strata) on
the basis of a distinguishing characteristic such as age, gender, life
style, race, status.
7. Stratification
When to use ?
• Before collecting data.
• When data comes from several sources or conditions, such as
shifts, days of the week, suppliers or population groups.
• When data analysis may require separating different sources or
conditions.
8. Stratification
Purpose
The reason to stratify the data is to make it easier to find patterns. If
there is a small problem on one day of the week and all the data is
mixed together it may well not be noticable. By stratifying the data
the data of interest can be made more visisble (of course that
requires stratifying by the right characteristic)
9. Stratification
Procedure
• Before collecting data, consider which information about the sources of the
data might have an effect on the results. Set up the data collection so that
you collect that information as well.
• When plotting or graphing the collected data on a scatter diagram, control
chart, histogram or other analysis tool, use different marks or colors to
distinguish data from various sources. Data that are distinguished in this
way are said to be “stratified.”
• Analyze the subsets of stratified data separately. For example, on a scatter
diagram where data are stratified into data from source 1 and data from
source 2, draw quadrants, count points and determine the critical value
only for the data from source 1, then only for the data from source 2.
10. Stratification
Considerations
• Here are examples of different sources that might require data to
be stratified:
– Equipment
– Shifts
– Departments
– Materials
– Suppliers
– Days of the week
– Time of a day
– Products
• Survey data usually gets benefitted if stratification is used.
• Always consider before collecting data whether stratification might
be needed during analysis. Plan to collect stratification
information. After the data is collected it might be too late.
• On your graph or chart, include a legend that identifies the marks
or colors used.
11. Diagrammatic representation of
Stratification of a simple reactor:-
• Bar graph
6
5
4
3
2
1 Reactor 1
Reactor 2
0
Reactor 3
Category 1 Category 2 Category 3 Category 4
17. Stratification
Method
To sum up
Usage Result
Grouping by •Used to observe variations
•Allows observation
day, time, place, wo among strata.
of variations among
rker, or process •Used to identify the
strata.
relationship between cause
•By performing a
Number of Units
and effect.
cause analysis using
X ★★★★★★★ •Used to identify a purpose
the stratified
Y △△△△ and means to serve the
data, the following
purpose
Z ○○○
[Used during phases to monitor
can be accomplished.
the situation, analyze 1.Identification and control of a
causes, review effectiveness of an problem
action, perform 2.“Division of data (obtained by
standardization, and implement a using each QC tool) into several
selected control measure.] groups”
17