Saturday, April 22, 2023

Measuring stuff

There's a lot of stuff to measure if you're running a PMO.
And all that stuff shares these characteristics:
  • Measurable (attributes can be represented on a calibrated scale)
  • Calculable (numbers from the scale can be handled with arithmetic)
  • Estimable (enough is known about the entity that a credible numerical forecast can be made)
  • Determinable (essentially, not random, and thus not requiring statistical methods)
And, why do we care?
Enter: risk management, for one thing. But also we measure, calculate, and estimate in deterministic methods cost, schedule duration, and quality characteristics.

What about apples and oranges?
Apples can be measured; oranges can be measured
Can they be compared, one with the other?
Some characteristics, like weight and density are comparable
Some characteristics, like susceptibility to damage if dropped are really not comparable. It's apples and oranges after all. They are dissimilar in certain ways that require they be separated for analysis.

That latter idea, that dissimilarity is a separator for analysis brings us to risk management. 
To compare two dissimilar risks violates the rule that risks to be compared must be similarly mensurable.

In a posting during the COVID 19 period, Matthew Squair, writing at 'critical uncertainties' makes the point that early on ....
(and I quote Squair)

".... lockdown sceptics were pointing out that your risk of drowning in a pool, in California, was much higher than that of dying from Covid 19 so why to worry? if you feel this is intuitively wrong, in fact wronger [sic] than wrong, you're right.

One of these risks is based on an independent probability. That is if I drown in a pool it's not going to have an affect on the probability of my neighbour drowning. But, on the other hand if I have Covid 19 you'll find the probability of my neighbour having Covid 19 is dependent on that; that is, the probabilities are dependent.

In one we truck along with a base rate of events unaffected by each other, in the other the events can affect each other and the risk can suddenly blow up.

To be very clear the two risks are immensurable and not directly comparable."

He goes to point out that many such immensurable comparisons were being made in the Covid space, such as the risk of getting Covid itself compared, incorrectly, to the risk of blood clot from a vaccine, etc.

Like this blog? You'll like my books also! Buy them at any online book retailer!