Posted by Phil WisemanFeb 15, 2018 3:28:04 PM
4 minutes to read
This is not a new question. In fact, mathematicians have been pondering this question for hundreds of years. In fact, it was given a name. The Secretary Problem.
It is also known as the marriage problem, sultan's dowry problem, and best choice problem. Simply put: What is the optimal stopping time. The application of optimal stopping is very relevant today as many ISO standards have shifted back to the basic roots of quality- The PDCA cycle. Plan. Do.Check.Act. They all are focused on risk-based thinking. You no longer have a simple checklist. You are looking down the road to your next accreditation cycle. You know when you must meet the new standard. You know how many days you have to prepare.
How do you allocate the time? Why does this have to be so stressful?
When Do You Stop Planning?
The foundation of this problem is simple. When do I have enough information to make the best decision? We have all been a part of this problem. Let's look at the secretary problem. You are interviewing candidates. Does it make sense to hire the first applicant for your interview? Should you interview 5? Will you get a better pool of candidates if you interview 100?
The second candidate has a 50% chance of being the best you have interviewed. The third candidate has a 33.33% chance of being the right candidate. The fifth candidate has a 20% chance of being the best candidate....and so on. With those odds, you might as well stop at the second candidate and make a decision because the odds are in your favor!
This problem has been studied and solved and is often referred to as optimal stopping.
This chart shows clearly that there is a point of diminishing returns. 37%.
Interviewing 1,000 candidates will not provide statistically significantly better results than 30 candidates.
This is often referred to as The 37% Rule.
While more pragmatic than romantic, let's apply the 37% rule to marriage. You decide you want to be married by age 30. You are currently 20. That is a ten-year difference. 37% of 10 is 3.7 years. You need to propose to the best "candidate" by age 24. Just thought we would throw that in case anyone was looking-LOL.
Let's apply this to the PDCA cycle in preparation for your compliance to a new standard.
You have 100 days to meet the new standard.
Applying the 37% rule you should stop the planning phase after 37 days.
You now have 63 days remaining.
Do the changes for 23 days and measure for effectiveness.
You now have 40 days left.
Now take 15 days to check(analyze) your results.
You now have 25 days left.
Take 9 days to Act on the lessons learned.
This approach lends itself to an Agile approach versus traditional waterfall/cascading project management. This approach will require you to be time-bound.
While it is true that this approach will compress time frames, I think this is a positive. How many times have you been involved in a project where you got lost in the weeds in the planning phase looking for a "better" approach or more data. Even after you leaped that hurdle, you gathered data and gathered data and eventually lost sight of what the end goal was because there were no time boundaries.
To help you plan for your next audit, we are providing a FREE calibration Audit Checklist.
Phil Wiseman is Chief Marketing Officer at Alliance Calibration. He earned a B.S. in Chemical Physics from Centre College. Phil is an ASQ Certified Quality Auditor and ASQ Certified Manager of Quality/Organizational Excellence.
Grow your business more quickly with our solutions for inbound and ecommerce
Discover a new digital growth model that attracts visitors, converts them into leads, transforms them into customers and then follows them in the after-sales phase, managed with traditional trade methods or with ecommerce.