3. Statistical Process Control (SPC)
How do we know if the change is an
improvement?
Measured Change Tools
Data Report
4. When to use SPC
SPC is a practical statistical approach to
resolving problems. This is the tool to use, for
any type of measurement to help gather
information.
Did the
Where are we
project make
now?
a difference?
5. How to use SPC
SPC is a type of charting that tells us about the
variation that exists in the systems that we are
looking to improve.
7. Issues that could be encountered
When creating SPC charts
Aggregate
Available data
data
Measurement
New controls
fallacy
8. Role in PPE compliance
SPC is frequently applied the control of manufacturing
lines, but it applies equally well to any process that has
a measurable output
ie. Compliance of Health Professionals to correct PPE
guidelines as set by the institution
The advantage of SPC in comparison to other quality
methods such as inspection, is that the process of
detecting and correcting the problems occurs after the
events themselves happen
ie. Non/Compliance has occured which becomes part of
the data, as a point. After which, the point can be
viewed within a larger data pool (on the SPC) and the
pattern/trend, can be identified.
Editor's Notes
The ‘Study’ section entails-Completing the analysis of the data -Comparison of the data to predictions-Summarising what was learned-------------------------------------------Image sourced from:http://www.institute.nhs.uk/quality_and_service_improvement_tools/quality_and_service_improvement_tools/plan_do_study_act.html
How do we know if the change is an improvement?Outcomes need to be measured, an example of this would be such as- the reduction in the time a patient has to wait. If a change is made, this should affect the measures and demonstrate over time whether the change has led to sustainable improvement. The measures in this model are tools for learning and demonstrating improvement, and are non-judgemental.Each project/initiative needs to have the data collected to demonstrate whether changes result in improvement.Improvement progress should be reported periodically (ie. weekly, biweekly, monthly) on time series graphs known as ‘run charts' or statistical process control charts (SPC). -------------------------------------------------Information adapted from:NHS Institute for Innovation and Improvement. (n.d.). Plan, Do, Study, Act (PDSA). Retrieved January 9, 2012, from NHS Institute for Innovation and Improvement : http://www.institute.nhs.uk/quality_and_service_improvement_tools/quality_and_service_improvement_tools/plan_do_study_act.html
SPC is a practical statistical approach to resolving problems.This is the tool to use, for any type of measurement to help gather information. SPC can be used throughout the cycle of PDSA, but I will only be focusing on the areas that address the questions of- Where are we now? Did the project make a difference?-----------------------------Information adapted from:NHS Institute for Innovation and Improvement. (2008). Statistical Process Control (SPC). Retrieved January 9, 2012, from NHS Institute for Innovation and Improvement : http://www.institute.nhs.uk/quality_and_service_improvement_tools/quality_and_service_improvement_tools/statistical_process_control.html
SPC is a type of charting that tells us about the variation that exists in the systems that we are looking to improve. S - Statistical, as statistical concepts are used to help understand processes P - Process, as the work is delivered through processes. i.e. how things are doneC - Control, meaning predictability-------------------------------------------Information adapted from:NHS Institute for Innovation and Improvement. (2008). Statistical Process Control (SPC). Retrieved January 9, 2012, from NHS Institute for Innovation and Improvement : http://www.institute.nhs.uk/quality_and_service_improvement_tools/quality_and_service_improvement_tools/statistical_process_control.htmlPicture sourced from:NHS Institute for Innovation and Improvement. (2008). Statistical Process Control (SPC). Retrieved January 9, 2012, from NHS Institute for Innovation and Improvement : http://www.institute.nhs.uk/quality_and_service_improvement_tools/quality_and_service_improvement_tools/statistical_process_control.html
When interpreting the SPC charts there are four rules that help in identifying what the system is doing. If one of the rules are broken, it means that an uncontrolled variation is present in the system. It is also normal for a process to show no signs of such an uncontrolled variation. This means that only a controlled variation is present.Rule 1-Any point outside one of the control limitsRule 2-A run of seven points all above or all below the centre line, or all increasing/decreasingRule 3-Any unusual pattern or trends within the control limitsRule 4-The number of points within the middle third of the region between the control limits differs markedly from two -thirds of the total number of points a more efficient system, you need to reduce the variation. Controlled and uncontrolled causes of variation indicate the need for two different types of improvement, to achieve the necessary outcome. If controlled variation is displayed in the SPC chart, the process is stable and predictable, which means that the variation is inherent in the process. ----------------------------------------------Information adapted from:NHS Institute for Innovation and Improvement. (2008). Statistical Process Control (SPC). Retrieved January 9, 2012, from NHS Institute for Innovation and Improvement : http://www.institute.nhs.uk/quality_and_service_improvement_tools/quality_and_service_improvement_tools/statistical_process_control.htmlPictures sourced from:NHS Institute for Innovation and Improvement. (2008). Statistical Process Control (SPC). Retrieved January 9, 2012, from NHS Institute for Innovation and Improvement : http://www.institute.nhs.uk/quality_and_service_improvement_tools/quality_and_service_improvement_tools/statistical_process_control.html
Some issues you may encounter when creating your own SPC charts: Available data - you may need to collect the data for analysis as it may not be available already. To be statistically rigorous, the number of observations (the points you are measuring) are important. The more frequently they’re recorded,the better: daily/weekly is more efficient than monthly.Aggregate data is discouraged (ie the use of percentages, as this often hides the pattern of the data) The problem being observed may be the means by which it is beingmeasured, and not what is happening. Sometimes it is better not to act if the ‘problem’ within the current process isn’t clear. It is better to invest the time that would be spent discovering a mistake in this step to further investigate in ‘Plan’ stage. It is important to note that when something in the process has been changed, the data points after the change, will be from a new system. When there is a trend of points that break a rule, it is necessary to recalculate the control limits of the chart for any improvement to be evident.--------------------------------------------Information adapted from:NHS Institute for Innovation and Improvement. (2008). Statistical Process Control (SPC). Retrieved January 9, 2012, from NHS Institute for Innovation and Improvement : http://www.institute.nhs.uk/quality_and_service_improvement_tools/quality_and_service_improvement_tools/statistical_process_control.html
SPC is frequently applied the control of manufacturing lines, but it applies equally well to any process that has a measurable output ie. Compliance of Health Professionals to correct PPE guidelines as set by the institutionThe advantage of SPC in comparison to other quality methods such as inspection, is that the process of detecting and correcting the problems occurs after the events themselves happenie. Non/Compliance has occured which becomes part of the data, as a point. After which, the point can be viewed within a larger data pool (on the SPC) and the pattern/trend, can be identified.-----------------------------------------------------Information adapted from:Deng, H; Runger, G; Tuv, Eugene (2011). System monitoring with real-time contrasts, Journal of Quality Technology. forthcoming.Wheeler, D J & Chambers, D S (1992) Understanding Statistical Process ControlISBN 0-945320-13-2