How to Measure Anything: 8 key ideas
The core ideas of How to Measure Anything, each in under a minute, written in our own words. Want the full depth? Get the book.
- IDEA 1 OF 8
Anything can be measured
Hubbard argues that many things people consider impossible to measure, such as quality, risk or value, can in fact be measured.
The key is to understand what measurement really means.
- IDEA 2 OF 8
Measurement reduces uncertainty
Hubbard defines measurement as reducing uncertainty, not achieving perfect certainty.
Even rough measurements can improve decisions. If a rough measure tells you something you did not know, it is already useful, because it helps you make a better choice.
- IDEA 3 OF 8
Estimate like Fermi
Hubbard describes Fermi estimation, breaking a problem into smaller parts that can be estimated.
Physicist Enrico Fermi used this to make surprisingly accurate guesses. Such rough estimates are often close enough to guide a decision.
- IDEA 4 OF 8
Train your estimates
Hubbard describes calibration training, helping people make estimates with accurate confidence.
Calibrated estimators know how uncertain they are. For example, a person who says they are ninety percent sure should be right about nine times in ten.
- IDEA 5 OF 8
Measure what matters
Hubbard argues that people should measure things that affect decisions.
The value of information shows which measurements are worth making. If a measurement cannot change what you would decide, it is probably not worth the time and money.
- IDEA 6 OF 8
Small samples tell a lot
Hubbard describes the rule of five: a sample of just five can give useful information about a population's median.
Small samples are more informative than expected. This surprised many people who assumed big samples were always necessary.
- IDEA 7 OF 8
Avoid measurement myths
Hubbard challenges beliefs that some things are too complex or intangible to measure.
Clear definitions make measurement possible. Hubbard says if something matters, it shows up in the world somehow, and so there are ways to observe it.
- IDEA 8 OF 8
Decisions drive measurement
Hubbard concludes that measurement should serve decisions.
Knowing what decision you face guides what to measure. Measuring things just because they are easy to count wastes effort, while measuring what changes the choice is worth the trouble.
Get one idea like this every daySwipe through ideas, go deeper on any of them, and save the ones that matter. Free.
Read How to Measure Anything in the app