30 January 2011

Meaningless Averages -- Why We Use Probability Distributions

"Average" is a simple concept; we measure a bunch of things, add the measurements, divide by the number of measurements.

Averages are not always that simple.

26 January 2011

How to Create a Scalar DIST in VBA

Whether as a placeholder, or to plug in an actual to replace an estimate, it's useful to replace a DIST with a scalar without recoding every formula that expects it to be a DIST. Here's code to do it.

18 January 2011

Sampo-Zashi

No, it's not yet another mythical Japanese productivity scheme; it's the name of a clever way to join four timbers using elegant Japanese joinery--and an example of risk management in plan design.

Picture a Finicky Joining

One carpenter working alone will carve the most intricate part first, then carve the rest, one at a time, fitting each new part in place, sanding and scraping for a perfect fit.

If you’re in a hurry, but don’t want to sacrifice quality, you could assign a part to each of four carpenters. All four carpenters won’t be as capable as the best carpenter; some will work more slowly to maintain the needed quality. You have to give each one very precise instructions; all the dimensions must be accurate (not merely precise) for a sub-millimeter fit on all the faces and edges. Also, when they’re done, it’s unlikely that all four will be perfect, so there’ll be some extra effort going into the final fit. You hope that any flaws involve too much wood; too much can be sanded down, too little means starting over.

Nonetheless, the concurrent approach is likely to finish sooner than the serial approach, but it will involve more carpenters, and more carpenter-hours.

The choice between one carpenter and four (or two) is a risk management decision. If everything goes well, the single carpenter might finish faster than four unlucky carpenters who run into problems at every turn. It’s a matter of probabilities.

A good plan design needs to take those probabilities into account, and give management choices between higher risk, higher cost and longer time scales.

01 January 2011

DIST Shaper 2

Here's a new version of DIST Shaper. The first version was a little sloppy about keeping the characteristics of the histogram, and the interface was busier than it needed to be.

DIST Shaper 2 solves both of these problems.

Download distshaper.xls

About DIST Shaper