The use of Bayes and causal modelling in decision making, uncertainty and risk

The most sophisticated commonly used methods of risk assessment (used especially in the financial sector) involve building statistical models from historical data. Yet such approaches are inadequate when risks are rare or novel because there is insufficient relevant data. Less sophisticated commonlyFigure 1 Causal view of evide34Visit toAsia?sm。ker?HasHas lungHastuberculosiscancerbronchitisPositive x-rayDyspnoea?Yes.01Smoker? Yes N0.990.60.3N0.40.75VIsIt toVisit toAsia?Smoker?Asia?Sm。ker?Scenario:ncHas bronchiTisHas lung cancas bronchitis15%5%yes >4Positive xDyspnoea?Positive x-y?Dyson。earScenarIo1: yesVisit toVisit tAsiaSmoker?Asla?Smoker?e3n01:r0Scenario:/esI las bronchitisHas tuberculosHas bronchitis54%4:.5%Posltlve xPositive xDyspnoea?raDyspnoea?scen arlo 1: yesario 1 yesScenano 1: yes I67Table 1 Fatal automobile crashes per monthMonthTotalAveragenthlycrashes temperature(F)450430410N=2.144XT+243.55corr=0.869◆Tota| fatal crash330Linear(Total fetal290crashe270250535.05.0750Temperature(Fahrenheit),T89Drvng canditions (D)INumber af accidentsNimber of miles(n)10