BU283 Lecture Notes - Lecture 4: Expected Value Of Perfect Information
Document Summary
Knowledge of sample/survey information can be used to revise probability estimates for states of nature (outcomes) Prior to obtaining information, p(states of nature) are called prior probabilities. With knowledge of conditional probabilities for outcomes (indicators) of the sample or survey, prior probabilities can be revised by bayes" theorem. Outcomes of this analysis are posterior probabilities. For each state of nature, multiply prior prob. by conditional prob. for indicator -- gives joint probabilities for states & indicator. Sum joint probabilities over all states -- gives marginal probability for indicator. For each state, divide joint prob. by marginal prob. of indicator -- gives posterior prob. dist. Improvement in the expected value of the decision strategy with the sample information: (evsi) expected value of sample information = expected value with sample information expected value without sample information. Efficiency = evsi/evpi: or if you want percentage efficiency = 100*evsi/evpi.
