Six Sigma Prelims

Define

Identify and state the practical problem

Measure

Validate the practical problem by collecting data

Analyze

Convert the practical problem to a statistical one

Improve

confirm and test the statistical solution

Control

convert the statistical solution to a practical solution

Define

Objectives: Identify Opportunities

Tasks: Identify focus areas, Set-up project and deploy teams, Define key process output variable,

Measure

Objectives: Determine Capability

Tasks: Develop data collection plan, Determine current process capability

Analyze

Objectives: Investigate causes

Tasks: Brainstorm all possible causes, Shortlist major suspected causes, Verify actual causes

Improve

Objectives: Find solutions

Tasks: Identify and evaluate possible improvements solutions, Plan improvement actions

Control

Objectives: Sustain improvements

Tasks: Standardize improvement actions, Document and close the project

Measure Phase

to gather data that describes the nature and extent of the problem

Value Added Flow Analysis

combines two powerful tools into one.

Value Analysis

differentiates steps that add value in the eyes of the customer from those that do not

Flow Analysis

calculates the time spent on each step.

Data Collection Plan

is a roadmap for identifying what data you need, the ways in which you'll collect it, and how you'll analyze it.

Statistics

science that deals with the collection, classification, analysis, and interpretation of numerical facts and data.

statistical analysis

is a critical skill in quality improvement and problem solving

Man

Machine

Method

Material

Measurement

Mother Nature

Most causes of process variation can be categorized into one of the following groups:

Population

entire set of measurement of interest

Parameter

computed values using all the data of a population

Sample

subset of data pulled from the population

Statistics

computed values using the data from the extracted samples

Response (y)

dependent variable; variable under investigation is described in terms of other variables

Predictor (x)

independent variable; variable is used in conjunction with other variables to describe a given response

Discrete Data

obtained by counting; whole number

Continuous Data

obtained by measuring; contains decimal

Descriptive Statistics

Concerned with collecting and describing a set of data so as to yield meaningful information

Inferential Statistics

Concerned with the analysis of sample data and generalizing results back to the larger population, i.e. draw predictions or inferences about the entire population

Measure of Location

Central Tendency; where does the data point typically concentrated

Measure of Dispersion

Variation; how wide or small the data points are scattered

Measure of Shape

Distribution; what shape do the data take

variance

The measure of how far the set of data is dispersed from their mean value

Standard deviation

the statistical measure that quantifies the amount of variation or spread in a dataset

Positive skewness

implies an asymmetric tail (the longer tail) extending

towards higher values.

Negative skewness

implies an asymmetric tail extending towards lower

values.

Kurtosis

characterizes the relative peakness or flatness of a

distribution compared to a normal (mesokurtic) distribution.

Positive kurtosis

indicates a “sharper peak” (leptokurtic) distribution

Negative kurtosis

indicates a “flatter peak” (platykurtic) distribution

compared to the normal distribution.

Interquartile Range

measures the spread of the middle half of the data. It is the range for the middle 50% of the sample. It is used to assess the variability where most of the values lie. This is also used to identify the outliers among data.

Recording Check Sheet

Tally Sheet

check marks are used to count events, often in the form of “five-barred- gates".

Location Plot

Concentration Diagram

a picture of the item being examined is drawn and the location of problems are marked on the diagram.

Process Distribution Check Sheet

performance of the process building up as you are using the sheet, without having to wait for later analysis.

box plot

is a graphical representation used to summarize

the distribution of a dataset.

run chart

is a graph that displays observed data in a time

sequence.

Define

first phase of the Lean Six Sigma improvement process. It contains defining the problem, the goal, the process and the customer

Project Charter

Voice of the Customer

End to End Current Process

outputs of Define Phase

Problem

the gap between the Current Situation and the Ideal Situation

what is wrong

how long

where did it happen

what is the impact

Structure of a Problem Statement

Voice of the customer

states the requirements and feedback of the customers

Quality

aspect of your product or service which the customers most wants

Internal Customers

may include process owners, downstream processes, other departments, business leaders, etc.

External Customers

may include members, companies, providers, facilities, regulatory bodies, government agencies, etc.

identify the customer

VOC data

Determine CTQ

VOC Process

SIPOC

Value Stream Map

Swimlane

Types of Process Maps

Swimlane Process Map

A process mapping tool that provides a visual view of how work flows through a process.

Quantitative Benefit

can be converted in terms of monetary or cost savings

Qualitative Benefit

Cannot be measured in terms of monetary or cost savings but has significant business impact

Pick Matrix

A lean six sigma tool used to categorize and prioritize process improvement ideas in terms of their potential impact vs. ease of implementation

Possible

high impact but more difficult to implement; evaluate further

ideal

high impact and easy to implement; definitely go ahead

Consider

low impact but easy to implement; implement if time permits

Kill

don’t bother