Goodwin and Wright (2009) - OK "deck" Flashcards
What is the name of Goodwin and Wright’ss article?
The limits of forecasting methods in anticipating rare events
What are cognitive biases?
Human judgment is often used to estimate
the probabilities of events occurring.
Name 8 of the ways of how to predict?
- Statistical forecasting
- Expert judgement
- Decomposed judgement
- Structured analogies
- Judemental adjustment to statistical forecasts
- Delphi
- Prediction markets
- Scenario planning
2 D, 1 E, 1 J, 1 P och 3 S
What is statistical forecasting? Its prons and cons
Need large reference of data. Reduces cognitive biases. Might have wrong data or measure the wrong thing. We will not find the rare events with statistical forecasting. the 1/1000000000 events or similar.
What is expert judgement? and its pros and cons
When reference of data is smaller - statistical forecasting cannot be used. Experts have shown to be good at forecasting when tit comes to horse racing, card game (bridge), financial interest rates. But Tetlock (an author), collected 82,300 political and economics forecasts for experts asking them to estimate probabilities for various events - They performed worse than chance.
What is decomposed judgement? and its pros and cons
using “trees” in order to decomposed the events in smaller pieces, and using probability on the smaller pieces to see the sum of the probability for that event to occur.
might lessen the cognitive bias, but on the other hand it might be forecasts on historical “event-chains”, which might not be true in the future.
What is Structured analogies? and its pros and cons
tool to improve judgemental forecasting (same as decomposed judgement). Analogi = how experience from similar events/happening can be used in another case.
We use the experience we have gained, and applying it for future events, which might have an effect on our probability to find the rare events.
What is statistical forecasting with judgemental intervention or adjustment?
It is what is sounds like. uses statistical probability and then adjusting it or uses the outcomes as ground to make assumptions. But the tools does not provide efficiency in estimating rare events.
What is Delphi? and its pros and cons
Delphi is a tool in which persons (the more diverse the better) creates prediction of the future, anonymisly, and then uses different steps in order to forecast. often years ahead and often for high-impact events. Numbers are used.
Shown to have great forcastability, but the exchange of elaborated reasoning might be attenuated.
What is Prediction Market? and its pros and cons
Prediction markets (also known as predictive markets, information markets, decision markets, idea futures, event derivatives, or virtual markets) are exchange-traded markets created for the purpose of trading the outcome of events. The market prices can indicate what the crowd thinks the probability of the event is. A prediction market contract trades between 0 and 100%. It is a binary option that will expire at the price of 0 or 100%. Prediction markets can be thought of as belonging to the more general concept of crowdsourcing which is specially designed to aggregate information on particular topics of interest. The main purposes of prediction markets are eliciting aggregating beliefs over an unknown future outcome. Traders with different beliefs trade on contracts whose payoff’s are related to the unknown future outcome and the market prices of the contracts are considered as the aggregated belief.
compared with the delphi tool, participants in the prediction market have no room to “rethink” their estimations.
What is Scenario planning? and its pros and cons
we accept that we cannot foretell the future, and best guesses might be wrong as well.
Multiple scenarios create plausible futures in with we can wind-tunnel ideas. One scenario is misleading us, but the range of scenarios helps us, by bounding the uncertainties that are seen to be inherent (naturlig, inneboende) in the future.
Protective strategy
Forecasting is hard when the probability for rare events might be far under 1%. some authors argue that we should create “earthquake safe” strategies (he draw that conclusion by stating that humans have 2 or more of the same organ), or buy insurances for rare events to happen.
Scenarios, how should you think?
You should use the certainties and uncertainties, and then create challenging but plausible scenarios, that has the highest material impact on your business.
Try to use a diverse group of people when designing the narratives and scenarios.
Scenarios are a forecasting model have not been empirically studied.