liveBook · Manning

State of nature

As explained in Statistics Every Programmer Needs

A state of nature is a possible external condition that affects the outcome of a decision but is not controlled by the decision-maker.

A state of nature is an external condition that can affect a decision’s payoff but remains outside the decision-maker’s control. Examples include strong or weak market conditions. section 10.1.1

Use states of nature when structuring a decision:

  • List the possible external conditions. section 10.1.1
  • Record the payoff for each decision alternative under every condition. section 10.1.1
  • Choose a decision method suited to the context, such as Maximax when probabilities are unavailable. section 10.1.1
>>> import pandas as pd
>>> payoff_table = pd.DataFrame({
>>>     'Investment Alternatives': investment_alternatives,
>>>     'Strong Economy': strong_economy,
>>>     'Weak Economy': weak_economy
>>> })
>>> print(payoff_table)
              Investment Alternatives  Strong Economy  Weak Economy
0                        Stock Market          100000       -120000
1            Professional Soccer Club           60000        -20000
2  Stock Market / Soccer Club (50/50)           80000        -70000
3                     Savings Account           35000         35000

A payoff table pairs investment alternatives with strong and weak economic states, making the external conditions explicit. section 10.1.1

How Statistics Every Programmer Needs covers it

How deep it goes
Defines states, places them in payoff tables, and incorporates them into a decision procedure; it stops short of probability estimation.
Examples
Uses strong and weak economic conditions as states for comparing investment alternatives.
What it assumes
Assumes decision alternatives and payoffs; teaches how to identify uncontrollable conditions and pair them with outcomes.
What you can do after
Apply it via payoff tables to structure alternatives and compare outcomes across uncontrollable external conditions.
How it connects
Connects states of nature with decision alternatives, payoffs, payoff tables, and decision-making methods.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Statistics Every Programmer Needs. The section links point to the parts of the book it draws on.