Evolution of Quality Historically Proactive Quality “ Create process that will produce less or no defects” Contemporary Reactive Quality Quality Checks (QC) - Taking the defectives out of what is produced
Segments in Quality Methodologies Standards Capability Models
ISO 9000, ISO 14000 etc.
Scientific way to improve capability? Sharing Benchmarked practices- “Standardizing” Best practices to build capability
The term “sigma” is used to designate the distribution or spread about the mean (average) of any process or procedure.
For a process, the sigma capability (z-value) is a metric that indicates how well that process is performing. The higher the sigma capability, the better. Sigma capability measures the capability of the process to produce defect-free outputs. A defect is anything that results in customer dissatisfaction.
Two Meanings of Sigma
Path to Six Sigma Sigma levels and Defects per million opportunities (DPMO) 4 Sigma 6,210 Defects 2 Sigma 308,537 Defects 3 Sigma 66,807 Defects 5 Sigma 233 Defects 6 Sigma 3.4 Defects
What it means to be @ Six Sigma Example quoted from GE Book of Knowledge - copyright GE Is 99% (3.8 ) good enough? 99.99966% Good – At 6 20,000 lost mails per hour 7 lost mails per hour Unsafe drinking water almost 15 minutes each day One minute of unsafe drinking water every seven months 5,000 incorrect surgical operations per week 1.7 incorrect surgical operations per week 2 short or long landings at most major airports daily One short or long landing at major airports every five years 200,000 wrong drug prescriptions each year 68 wrong drug prescriptions each year
To understand the process; it’s mission, flow and scope
To know the customers and their expectations
To identify, monitor and improve correct performance measures for the process
The Need of BPMS
The Methodology Define purpose of the process, its goal and its boundaries Identify Critical to Quality and Critical to process Visual representation of performance Map process steps, identify input/ output measures MSA, DCP, indicators and monitors Service excellence and process excellence The DMAIC cycle Define Process Mission Map Process VOC and VOP Build PMS Develop Dashboards Identify Improvement Opportunities
A logical and structured approach to problem solving and process improvement
An iterative process (continuous improvement)
A quality tool with focus on change management
What is DMAIC ? E Effectiveness = Q Quality Improvement x A Acceptance
The Approach Practical Problem Statistical Problem Statistical Solution Practical Solution
D Define M Measure A Analyze I Improve C Control Identify and state the practical problem Validate the practical problem by collecting data Convert the practical problem to a statistical one, define statistical goal and identify potential statistical solution Confirm and test the statistical solution Convert the statistical solution to a practical solution Methodology
VoC - Who wants the project and why ? The scope of project / improvement Key team members / resources for the project Critical milestones and stakeholder review Budget allocation Define D Define M Measure A Analyze I Improve C Control
Ensure measurement system reliability Prepare data collection plan Collect data - Is tool used to measure the output variable flawed ? - Do all operators interpret the tool reading in the same way ?
- How many data points do you need to collect ?
How many days do you need to collect data for ?
What is the sampling strategy ?
Who will collect data and how will data get stored ?
What could the potential drivers of variation be ?
Measure D Define M Measure A Analyze I Improve C Control
Understand statistical problem Baseline current process capability Define statistical improvement goal Identify drivers of variation (significant factors) Analyze D Define M Measure A Analyze I Improve C Control
A visual tool that helps in separating the vital few from the trivial many
Control Impact Analyze – Identify Drivers of Variation Trivial Many Low Control – Low Impact Cost Ineffective High Control – Low Impact Cost Ineffective Low Control – High Impact Vital Few High Control – High Impact
A statistical tool used to validate if two samples are different or whether a sample belongs to a given population
Null Hypothesis (H o ) is the statement of the status quo
Alternate Hypothesis (H a ) is the statement of difference
Analyze – Identify Drivers of Variation One way ANOVA Regression Homogeneity of Variance Moods Median Chi-Square
Map improved process Pilot solution Identify operating tolerance on significant factors Improve D Define M Measure A Analyze I Improve C Control
Ensure measurement system reliability for significant factors Improved process capability Sustenance Plan - Is tool used to measure the input / process variables flawed ? - Do all operators interpret the tool reading in the same way ? - Statistical Process Control - Mistake Proofing - Control Plan Control D Define M Measure A Analyze I Improve C Control