




版權(quán)說(shuō)明:本文檔由用戶提供并上傳,收益歸屬內(nèi)容提供方,若內(nèi)容存在侵權(quán),請(qǐng)進(jìn)行舉報(bào)或認(rèn)領(lǐng)
文檔簡(jiǎn)介
管理科學(xué)決策分析Chapter12-DecisionAnalysis1第一頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
2ComponentsofDecisionMakingDecisionMakingwithoutProbabilitiesDecisionMakingwithProbabilitiesDecisionAnalysiswithAdditionalInformationUtilityChapterTopics第二頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
3Table12.1PayoffTableAstateofnatureisanactualeventthatmayoccurinthefuture.Apayofftableisameansoforganizingadecisionsituation,presentingthepayoffsfromdifferentdecisionsgiventhevariousstatesofnature.DecisionAnalysisComponentsofDecisionMaking第三頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
4Decisionsituation:Decision-MakingCriteria:maximax,maximin,minimax,minimaxregret,Hurwicz,andequallikelihood
Table12.2PayoffTablefortheRealEstateInvestmentsDecisionAnalysisDecisionMakingwithoutProbabilities第四頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
5Table12.3PayoffTableIllustratingaMaximaxDecisionInthemaximaxcriterionthedecisionmakerselectsthedecisionthatwillresultinthemaximumofmaximumpayoffs;anoptimisticcriterion.DecisionMakingwithoutProbabilitiesMaximaxCriterion第五頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
6Table12.4PayoffTableIllustratingaMaximinDecisionInthemaximincriterionthedecisionmakerselectsthedecisionthatwillreflectthemaximumoftheminimumpayoffs;apessimisticcriterion.DecisionMakingwithoutProbabilitiesMaximinCriterion第六頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
7Table12.6
RegretTableIllustratingtheMinimaxRegretDecisionRegretisthedifferencebetweenthepayofffromthebestdecisionandallotherdecisionpayoffs.Thedecisionmakerattemptstoavoidregretbyselectingthedecisionalternativethatminimizesthemaximumregret.DecisionMakingwithoutProbabilitiesMinimaxRegretCriterion第七頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
8TheHurwiczcriterionisacompromisebetweenthemaximaxandmaximincriterion.Acoefficientofoptimism,,isameasureofthedecisionmaker’soptimism.TheHurwiczcriterionmultipliesthebestpayoffbyandtheworstpayoffby1-.,foreachdecision,andthebestresultisselected.
Decision
Values
Apartmentbuilding$50,000(.4)+30,000(.6)=38,000 Officebuilding$100,000(.4)-40,000(.6)=16,000 Warehouse$30,000(.4)+10,000(.6)=18,000DecisionMakingwithoutProbabilitiesHurwiczCriterion第八頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
9Theequallikelihood(orLaplace)criterionmultipliesthedecisionpayoffforeachstateofnaturebyanequalweight,thusassumingthatthestatesofnatureareequallylikelytooccur.
Decision
Values
Apartmentbuilding$50,000(.5)+30,000(.5)=40,000 Officebuilding$100,000(.5)-40,000(.5)=30,000 Warehouse$30,000(.5)+10,000(.5)=20,000DecisionMakingwithoutProbabilitiesEqualLikelihoodCriterion第九頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
10Adominantdecisionisonethathasabetterpayoffthananotherdecisionundereachstateofnature.Theappropriatecriterionisdependentonthe“risk”personalityandphilosophyofthedecisionmaker.
Criterion
Decision(Purchase) Maximax Officebuilding Maximin Apartmentbuilding Minimaxregret Apartmentbuilding Hurwicz Apartmentbuilding Equallikelihood ApartmentbuildingDecisionMakingwithoutProbabilitiesSummaryofCriteriaResults第十頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
11Exhibit12.1DecisionMakingwithoutProbabilitiesSolutionwithQMforWindows(1of3)第十一頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
12Exhibit12.2DecisionMakingwithoutProbabilitiesSolutionwithQMforWindows(2of3)第十二頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
13Exhibit12.3DecisionMakingwithoutProbabilitiesSolutionwithQMforWindows(3of3)第十三頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
14Expectedvalueiscomputedbymultiplyingeachdecisionoutcomeundereachstateofnaturebytheprobabilityofitsoccurrence. EV(Apartment)=$50,000(.6)+30,000(.4)=42,000 EV(Office)=$100,000(.6)-40,000(.4)=44,000 EV(Warehouse)=$30,000(.6)+10,000(.4)=22,000Table12.7PayofftablewithProbabilitiesforStatesofNatureDecisionMakingwithProbabilitiesExpectedValue第十四頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
15Theexpectedopportunitylossistheexpectedvalueoftheregretforeachdecision.Theexpectedvalueandexpectedopportunitylosscriterionresultinthesamedecision.
EOL(Apartment)=$50,000(.6)+0(.4)=30,000 EOL(Office)=$0(.6)+70,000(.4)=28,000 EOL(Warehouse)=$70,000(.6)+20,000(.4)=50,000Table12.8Regret(OpportunityLoss)TablewithProbabilitiesforStatesofNatureDecisionMakingwithProbabilitiesExpectedOpportunityLoss第十五頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
16Exhibit12.4ExpectedValueProblemsSolutionwithQMforWindows第十六頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
17Exhibit12.5ExpectedValueProblemsSolutionwithExcelandExcelQM(1of2)第十七頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
18Exhibit12.6ExpectedValueProblemsSolutionwithExcelandExcelQM(2of2)第十八頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
19Theexpectedvalueofperfectinformation(EVPI)isthemaximumamountadecisionmakerwouldpayforadditionalinformation.EVPIequalstheexpectedvaluegivenperfectinformationminustheexpectedvaluewithoutperfectinformation.EVPIequalstheexpectedopportunityloss(EOL)forthebestdecision.DecisionMakingwithProbabilitiesExpectedValueofPerfectInformation第十九頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
20Table12.9PayoffTablewithDecisions,GivenPerfectInformationDecisionMakingwithProbabilitiesEVPIExample(1of2)第二十頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
21Decisionwithperfectinformation: $100,000(.60)+30,000(.40)=$72,000Decisionwithoutperfectinformation: EV(office)=$100,000(.60)-40,000(.40)=$44,000
EVPI=$72,000-44,000=$28,000 EOL(office)=$0(.60)+70,000(.4)=$28,000DecisionMakingwithProbabilitiesEVPIExample(2of2)第二十一頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
22Exhibit12.7DecisionMakingwithProbabilitiesEVPIwithQMforWindows第二十二頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
23Adecisiontreeisadiagramconsistingofdecisionnodes(representedassquares),probabilitynodes(circles),anddecisionalternatives(branches). Table12.10PayoffTableforRealEstateInvestmentExampleDecisionMakingwithProbabilitiesDecisionTrees(1of4)第二十三頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
24Figure12.1DecisionTreeforRealEstateInvestmentExampleDecisionMakingwithProbabilitiesDecisionTrees(2of4)第二十四頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
25Theexpectedvalueiscomputedateachprobabilitynode: EV(node2)=.60($50,000)+.40(30,000)=$42,000 EV(node3)=.60($100,000)+.40(-40,000)=$44,000 EV(node4)=.60($30,000)+.40(10,000)=$22,000Brancheswiththegreatestexpectedvalueareselected.DecisionMakingwithProbabilitiesDecisionTrees(3of4)第二十五頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
26Figure12.2DecisionTreewithExpectedValueatProbabilityNodesDecisionMakingwithProbabilitiesDecisionTrees(4of4)第二十六頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
27Exhibit12.8DecisionMakingwithProbabilitiesDecisionTreeswithQMforWindows第二十七頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
28Exhibit12.9DecisionMakingwithProbabilitiesDecisionTreeswithExcelandTreePlan(1of4)第二十八頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
29Exhibit12.10DecisionMakingwithProbabilitiesDecisionTreeswithExcelandTreePlan(2of4)第二十九頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
30Exhibit12.11DecisionMakingwithProbabilitiesDecisionTreeswithExcelandTreePlan(3of4)第三十頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
31Exhibit12.12DecisionMakingwithProbabilitiesDecisionTreeswithExcelandTreePlan(4of4)第三十一頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
32DecisionMakingwithProbabilitiesSequentialDecisionTrees(1of4)Asequentialdecisiontreeisusedtoillustrateasituationrequiringaseriesofdecisions.Usedwhereapayofftable,limitedtoasingledecision,cannotbeused.Realestateinvestmentexamplemodifiedtoencompassaten-yearperiodinwhichseveraldecisionsmustbemade:
第三十二頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
33Figure12.3SequentialDecisionTreeDecisionMakingwithProbabilitiesSequentialDecisionTrees(2of4)第三十三頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
34DecisionMakingwithProbabilitiesSequentialDecisionTrees(3of4)Decisionistopurchaseland;highestnetexpectedvalue($1,160,000).Payoffofthedecisionis$1,160,000.
第三十四頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
35Figure12.4SequentialDecisionTreewithNodalExpectedValuesDecisionMakingwithProbabilitiesSequentialDecisionTrees(4of4)第三十五頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
36Exhibit12.13SequentialDecisionTreeAnalysisSolutionwithQMforWindows第三十六頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
37Exhibit12.14SequentialDecisionTreeAnalysisSolutionwithExcelandTreePlan第三十七頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
38Bayesiananalysisusesadditionalinformationtoalterthemarginalprobabilityoftheoccurrenceofanevent.Inrealestateinvestmentexample,usingexpectedvaluecriterion,bestdecisionwastopurchaseofficebuildingwithexpectedvalueof$444,000,andEVPIof$28,000.
Table12.11PayoffTablefortheRealEstateInvestmentExampleDecisionAnalysiswithAdditionalInformationBayesianAnalysis(1of3)第三十八頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
39Aconditionalprobabilityistheprobabilitythataneventwilloccurgiventhatanothereventhasalreadyoccurred.Economicanalystprovidesadditionalinformationforrealestateinvestmentdecision,formingconditionalprobabilities: g=goodeconomicconditions p=pooreconomicconditions P=positiveeconomicreport N=negativeeconomicreport P(Pg)=.80 P(NG)=.20 P(Pp)=.10 P(Np)=.90
DecisionAnalysiswithAdditionalInformationBayesianAnalysis(2of3)第三十九頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
40Aposteriaprobabilityisthealteredmarginalprobabilityofaneventbasedonadditionalinformation.Priorprobabilitiesforgoodorpooreconomicconditionsinrealestatedecision: P(g)=.60;P(p)=.40PosteriaprobabilitiesbyBayes’rule: (gP)=P(PG)P(g)/[P(Pg)P(g)+P(Pp)P(p)] =(.80)(.60)/[(.80)(.60)+(.10)(.40)]=.923Posteria(revised)probabilitiesfordecision: P(gN)=.250 P(pP)=.077 P(pN)=.750DecisionAnalysiswithAdditionalInformationBayesianAnalysis(3of3)第四十頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
41DecisionAnalysiswithAdditionalInformationDecisionTreeswithPosteriorProbabilities(1of4)Decisiontreewithposteriorprobabilitiesdifferfromearlierversionsinthat: Twonewbranchesatbeginningoftreerepresentreport outcomes. Probabilitiesofeachstateofnatureareposterior probabilitiesfromBayes’rule.第四十一頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
42Figure12.5DecisionTreewithPosteriorProbabilities
DecisionAnalysiswithAdditionalInformationDecisionTreeswithPosteriorProbabilities(2of4)第四十二頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
43DecisionAnalysiswithAdditionalInformationDecisionTreeswithPosteriorProbabilities(3of4)EV(apartmentbuilding)=$50,000(.923)+30,000(.077) =$48,460EV(strategy)=$89,220(.52)+35,000(.48)=$63,194第四十三頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
44Figure12.6DecisionTreeAnalysisDecisionAnalysiswithAdditionalInformationDecisionTreeswithPosteriorProbabilities(4of4)第四十四頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
45Table12.12ComputationofPosteriorProbabilitiesDecisionAnalysiswithAdditionalInformationComputingPosteriorProbabilitieswithTables第四十五頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
46Theexpectedvalueofsampleinformation(EVSI)isthedifferencebetweentheexpectedvaluewithandwithoutinformation:Forexampleproblem,EVSI=$63,194-44,000=$19,194Theefficiencyofsampleinformationistheratiooftheexpectedvalueofsampleinformationtotheexpectedvalueofperfectinformation:efficiency=EVSI/EVPI=$19,194/28,000=.68DecisionAnalysiswithAdditionalInformationExpectedValueofSampleInformation第四十六頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
47Table12.13PayoffTableforAutoInsuranceExampleDecisionAnalysiswithAdditionalInformationUtility(1of2)第四十七頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
48ExpectedCost(insurance)=.992($500)+.008(500)=$500ExpectedCost(noinsurance)=.992($0)+.008(10,000)=$80Decisionshouldbedonotpurchaseinsurance,butpeoplealmostalwaysdopurchaseinsurance.Utilityisameasureofpersonalsatisfactionderivedfrommoney.Utilesareunitsofsubjectivemeasuresofutility.Riskavertersforgoahighexpectedvaluetoavoidalow-probabilitydisaster.Risktakerstakeachanceforabonanzaonaverylow-probabilityeventinlieuofasurething.DecisionAnalysiswithAdditionalInformationUtility(2of2)第四十八頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
49DecisionAnalysisExampleProblemSolution(1of9)第四十九頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
50DecisionAnalysisExampleProblemSolution(2of9)Determinethebestdecisionwithoutprobabilitiesusingthe5criteriaofthechapter.Determinebestdecisionwithprobabilitiesassuming.70probabilityofgoodconditions,.30ofpoorconditions.Useexpectedvalueandexpectedopportunitylosscriteria.Computeexpectedvalueofperfectinformation.Developadecisiontreewithexpectedvalueatthenodes.Givenfollowing,P(Pg)=.70,P(Ng)=.30,P(Pp)=20,P(Np)=.80,determineposteriaprobabilitiesusingBayes’rule.Performadecisiontreeanalysisusingtheposteriorprobabilityobtainedinparte.第五十頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
51Step1(parta):Determinedecisionswithoutprobabilities.MaximaxDecision:Maintainstatusquo
Decisions
MaximumPayoffs Expand $800,000 Statusquo 1,300,000(maximum) Sell 320,000MaximinDecision:Expand
Decisions
MinimumPayoffs Expand $500,000(maximum) Statusquo -150,000 Sell 320,000DecisionAnalysisExampleProblemSolution(3of9)第五十一頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
52MinimaxRegretDecision:Expand
Decisions
MaximumRegrets Expand $500,000(minimum) Statusquo 650,000 Sell 980,000Hurwicz(=.3)Decision:Expand Expand $800,000(.3)+500,000(.7)=$590,000 Statusquo $1,300,000(.3)-150,000(.7)=$285,000 Sell $320,000(.3)+320,000(.7)=$320,000DecisionAnalysisExampleProblemSolution(4of9)第五十二頁(yè),共五十七頁(yè),編輯于2023年,星期五Chapter12-DecisionAnalysis
53EqualLikelihoodDecision:Expand Ex
溫馨提示
- 1. 本站所有資源如無(wú)特殊說(shuō)明,都需要本地電腦安裝OFFICE2007和PDF閱讀器。圖紙軟件為CAD,CAXA,PROE,UG,SolidWorks等.壓縮文件請(qǐng)下載最新的WinRAR軟件解壓。
- 2. 本站的文檔不包含任何第三方提供的附件圖紙等,如果需要附件,請(qǐng)聯(lián)系上傳者。文件的所有權(quán)益歸上傳用戶所有。
- 3. 本站RAR壓縮包中若帶圖紙,網(wǎng)頁(yè)內(nèi)容里面會(huì)有圖紙預(yù)覽,若沒(méi)有圖紙預(yù)覽就沒(méi)有圖紙。
- 4. 未經(jīng)權(quán)益所有人同意不得將文件中的內(nèi)容挪作商業(yè)或盈利用途。
- 5. 人人文庫(kù)網(wǎng)僅提供信息存儲(chǔ)空間,僅對(duì)用戶上傳內(nèi)容的表現(xiàn)方式做保護(hù)處理,對(duì)用戶上傳分享的文檔內(nèi)容本身不做任何修改或編輯,并不能對(duì)任何下載內(nèi)容負(fù)責(zé)。
- 6. 下載文件中如有侵權(quán)或不適當(dāng)內(nèi)容,請(qǐng)與我們聯(lián)系,我們立即糾正。
- 7. 本站不保證下載資源的準(zhǔn)確性、安全性和完整性, 同時(shí)也不承擔(dān)用戶因使用這些下載資源對(duì)自己和他人造成任何形式的傷害或損失。
最新文檔
- 2025年度餐飲企業(yè)數(shù)字化轉(zhuǎn)型股東合作協(xié)議
- 二零二五年度酒店客房預(yù)訂與商務(wù)洽談與住宿套餐合同
- 二零二五年度婚姻介紹所涉外婚姻服務(wù)合同
- 二零二五餐飲業(yè)商鋪?zhàn)赓U合同附贈(zèng)會(huì)員管理系統(tǒng)合作
- 2025年宜賓貨運(yùn)從業(yè)資格考題
- 《物流系統(tǒng)分析》課件 項(xiàng)目七任務(wù)一 認(rèn)識(shí)物流系統(tǒng)控制
- 村支部書(shū)記發(fā)言稿
- 殘聯(lián)疫情發(fā)言稿
- 高中家長(zhǎng)會(huì):高二下學(xué)期期末家長(zhǎng)會(huì)課件
- 吉安市房屋租賃合同
- 第26課《詩(shī)詞五首》作業(yè)設(shè)計(jì)統(tǒng)編版語(yǔ)文八年級(jí)上冊(cè)
- 內(nèi)分泌科護(hù)理常規(guī)的課件
- 氣管切開(kāi)患者的管理和康復(fù)治療推薦意見(jiàn)(新版)解讀
- 疼痛科營(yíng)銷方案
- 中醫(yī)藥在關(guān)節(jié)病變治療中的價(jià)值
- 《香水知識(shí)》課件
- 公務(wù)員獎(jiǎng)勵(lì)審批表(表格)
- 醫(yī)院污水處理站維保服務(wù)項(xiàng)目
- 裝修項(xiàng)目經(jīng)理的簡(jiǎn)歷樣板
- 供應(yīng)商績(jī)效考核表 (季度)
- Python程序設(shè)計(jì)基礎(chǔ)及實(shí)踐(慕課版)PPT完整全套教學(xué)課件
評(píng)論
0/150
提交評(píng)論