DataCollectionPlanv1.ppt

© 2012 International Institute for Learning, Inc.

Ds-624 Quality Management

© 2014 International Institute for Learning, Inc.
3-*
IIL-LSSGB

Learning Objectives
Articulate the purpose of a Data Collection Plan

List the steps to create a Data Collection Plan

Explain the importance of Operational Definitions

Identify key characteristics of data

Explain how selected graphical analysis tools are used

Measure Phase

COPQ
Data
Collection
Plan
MSA
Capability
Define
We
have a problem
Measure

How bad is it?
Analyze
Find the
Root Cause
Improve
Fix it- Eliminate
Root Cause
Control
Make it
stay fixed

Measure Phase

Data
Collection
Plan

Data Collection Plan
Data collection must be carefully planned and organized.
Data should seek factual answers to questions.
The amount of data might be constrained by time, resources or budget.
The data generated is only as good as the system used to collect it.

Data Collection Plan Steps
What questions does the team has about the process?
List the data needed to answer the questions
Identify the characteristics of the each data element
Identify the graphical tools that will be used to analyze the data

Data Collection Plan

Step 1: What do you want to know?
Make a list of questions you need answered
How do you make a list of questions?

Observe the process before you measure it.

Get input from the people involved in the process.
If possible, watch the process. If not, review up-to-date process maps.
Warning: Collecting data adds cost so you’ll want to make sure it adds value

What will the answer look like?
How it will be formatted for analysis.
Lean Six Sigma Green Belt
Introduction to Define
3-*
IIL-LSSGB

Data Collection Plan

Step1: What do you want to know?
Stratification Factors are:
Categories you want to group the data in later

Not necessarily causes themselves, but they give you important hints on where to look for cause(s)

Opportunities to “slice and dice” the data

Factor Example

When Date: year, month, week, day
To the beginning of a shift to the end?

Where Geo: Country, region, city
Work place, computer, machine

Who Individual
Customer/customer segment

What Type of complaint
Type of defect

Example: What do you Want to know?
Date: Month and Year
What type of picture generates the most likes, views, comments?
Selfie or no-selfie
Family/friends, Food, Art, Nature
Tag or no-tag
# or no-#
Funny or not funny
Background light or dark

Data Collection Plan

Step 2: List the data needed to answer the questions
What is the average time to deliver a pizza?
What data do you need to answer that question:
Order received time stamp
Delivery completed time stamp
Number of deliveries

Create Operational Definition

A clear and unambiguous description of what and how to measure
Missing operational definition is the main cause of useless data.
Data Collection Plan

Step 2: List the data needed to answer the questions

Lean Six Sigma Green Belt
Data Collection
.
4-01-*
IIL-LSSGB

For Example…
When do we start measuring delivery time? When the phone starts to ring when they connect to a live agent?

Data Collection Plan

Step 2: List the data needed to answer the questions
Where do we measure size of the item? In the center or on the edges?

Lean Six Sigma Green Belt
Data Collection
These are examples of things you’ll want to consider when creating clear operational definitions.
4-01-*
IIL-LSSGB

Picture background: light or dark
Data Collection Plan

Step 2: List the data needed to answer the questions

Lean Six Sigma Green Belt
Data Collection

4-01-*
IIL-LSSGB

Data Collection Plan

Step 3: Identify the characteristics of the each data element
Is data element and input or and output of the process?

Data Collection Plan

Step 3: Id the characteristics of the each data element and measure
Discrete/ Attribute
Continuous/Variable
Data
Is countable (integers), cannot be meaningfully subdivided, e.g.,

Counts of characteristics or “attributes” (types of customer, loan types, gender)

Counts of defects (number of errors, late deliveries, complaints)…

Can be measured on an infinitely divisible scale, e.g.,

Length of time (speed, age)

Size (length, height, weight)

Dollars (costs, sales revenue, profits)

Number of late calls
90 on time service calls 10 late call
Proportion = 10%
Proportion
Count
Data
Discrete/ Attribute
Data Collection Plan

Step 3: Id the characteristics of the each data element and measure

Lean Six Sigma Green Belt
Data Collection
Discrete Count data can be reported as a Rate (# occurrences per unit of time/space). For example, # calls per hour, or # scratches per square foot.
Rates are different than proportions in that proportions range between 0-1, while rates can be any non-negative number. Sometimes rates can look like a proportion (e.g., 4 flaws per 100 ft of wire-> .04) – that’s why you need to understand fundamental data types.
4-01-*
IIL-LSSGB

Data Collection Plan

Step 3: Id the characteristics of the each data element and measure
When you have a choice try to get continuous data
Time to deliver
On-time or Late
Time to capture
Number of s that take more than 2 minutes
Duration system down
Number of times system is down
Budget variance
$ or % Above budget
>10% Over Budget (Y/N)
When you have a choice…

Data Type

Project Continuous Discrete

Timeliness

Data Collection Plan

Step 3: Id the characteristics of the each data element and measure
Date: Month and Year
Likes, views, comments, defects
Selfie or Still-life
Family, friends, Food, art
Tag or not tag
# or no #
Funny or not funny
Background light or dark
Discrete or Continuous?
Input or Output?
D
O
D
I
D
I
D
I
D
I
D
I
D
I
D
I

Data Collection Plan

Step 4: How you are going to analyze the data?

Schedule Variance
Scope Changes

Lean Six Sigma Green Belt
Data Collection
The best tools to identify the vital few Xs and to show variation are the ones on this slide. We’ll go through each one in detail.
4-01-*
IIL-LSSGB

73.unknown

A Pareto Chart…
Categories with the highest frequency (discrete data)
Data Collection Plan
Step 4: How you are going to analyze the data?

This chart is named after the Pareto Principle. In Six Sigma this translates to 80% of the effects (defects) are a result of 20% of the causes.
Our job is to find those 20% (vital few) and fix them!

Lean Six Sigma Green Belt
Data Collection
This is a simple bar graph showing the frequency of occurrence in descending .
4-01-*
IIL-LSSGB

Dot Plot and Histograms Can Tell Us…
How much variability there is in a sample of continuous data – generally used for smaller data sets
Data Collection Plan
Step 4: How you are going to analyze the data?

Each data point is represented by a dot

The shape of the distribution

Lean Six Sigma Green Belt
Data Collection
Use it for small and medium-sized data sets (<200). Multiple dotplots can be constructed for discrete levels of another variable. 4-01-* IIL-LSSGB 74.unknown A Time Series Plot Can Tell Us… If there are patterns over time Data Collection Plan Step 4: How you are going to analyze the data? If there has been a change or shift to the process Lean Six Sigma Green Belt Data Collection 4-01-* IIL-LSSGB A Scatter Plot Can Tell Us… If there are any potential relationships between paired sets of data (X variables and Y outcomes) Data Collection Plan Step 4: How you are going to analyze the data? Paired data is gathered at the same time on each item being measured (minimum of 30 pairs of data) Project Scope Changes Schedule Variance 1 12 18% 2 3 4% 3 10 16% 4 9 15% 30 21 28% Schedule Variance Scope Changes Lean Six Sigma Green Belt Data Collection Scatter plots provide a visual display of the relationship between two variables, showing how one variable increases or decreases as another variable increases or decreases. If changes in one variable are linked to changes in another, they are said to be correlated. Correlation may provide some insight into a possible cause and effect relationship between two variables, although correlation alone does not prove a causal relationship. It is the foundation for a more complete correlation analysis. 4-01-* IIL-LSSGB Learning Objectives Articulate the purpose of a Data Collection Plan List the steps to create a Data Collection Plan Explain the importance of Operational Definitions Identify key characteristics of data Explain how selected graphical analysis tools are used © 2012 International Institute for Learning, Inc. Thank you! © 2014 International Institute for Learning, Inc. 3-* IIL-LSSGB S a l e s 4 5 0 4 0 0 3 5 0 3 0 0 2 5 0 2 0 0 D o t p l o t o f S a l e s C a l l D u r a t i o n F r e q u e n c y 5 0 4 0 3 0 2 0 1 0 6 0 5 0 4 0 3 0 2 0 1 0 0 H i s t o g r a m o f C a l l D u r a t i o n Days Delayed 0 10 20 30 40 50 60 Project 1 Project 2 Project 3 Project 4 Project 5 Project 6 Project 7 Project 8 Project 9 Project 10 Project 11 Project 12 Project 13 Project 14 Project 15 Projects Days