Phlogiston/Risks of Forecasting and Metrics
 | This page is obsolete. It is being retained for archival purposes. It may document extensions or features that are obsolete and/or no longer supported. Do not rely on the information here being up-to-date. |
Things that can go wrong with forecasting
[edit]Some top risks
[edit]- Forecasting can provide a motive to consciously cheat
- Forecasting can trigger unconscious bias that ruins the validity of the metric
- The cost of measurement is not zero.
- Forecasting and measuringin general provides a bias toward doing things that are more easily measured (and against people doing things with less tangible benefits)
Additional Reading
[edit]- The Life Cycles of Failed Projects
- The Costs of Accountability, Jerry Z. Muller
- 'If You Can't Measure It, You Can't Manage It' (False)
- CompStat#Critique
Examples of Systemic Bias in Forecasts
[edit]These articles include examples of charts where a number of forecasts are made over a series of time, such as years and decades, and every single forecast is completely wrong and visibly in conflict with the observable trends.
The International Energy Agency consistently underestimates wind and solar power. Why?
Obamaâs Plans For Withdrawal From Afghanistan Have Changed Again
Transpo Agencies Are Terrible at Predicting Traffic Levels
