3. Decision Analysis

download 3. Decision Analysis

of 19

Transcript of 3. Decision Analysis

  • 8/6/2019 3. Decision Analysis

    1/19

    OPERATIONSOPERATIONS

    MANAGEMENTMANAGEMENT

    O MPDECISION ANALYSIS

    By:By: --HAKEEMHAKEEMURURREHMANREHMAN

    PCBAPCBAUCPUCP

  • 8/6/2019 3. Decision Analysis

    2/19

    DECISION ANALYSIS / DECISIONTHEORY

    QUANTITATIVE METHODSQUANTITATIVE METHODS

    A set of tools for operations managerA set of tools for operations manager

    DECISION ANALYSISDECISION ANALYSIS

    a set of quantitative decisiona set of quantitative decision--makingmaking

    techniques for decision situations intechniques for decision situations inwhich uncertainty existswhich uncertainty exists

  • 8/6/2019 3. Decision Analysis

    3/19

    DECISION PROCESS

    Fundamental process of management involves 6Fundamental process of management involves 6steps:steps:

    1.1. Specify objectives and the criteria for decisionSpecify objectives and the criteria for decision

    making.making.2.2. Develop Alternatives.Develop Alternatives.

    3.3. Analyze and compare alternatives.Analyze and compare alternatives.

    4.4. Select the best alternativeSelect the best alternative5.5. Implement the chosen alternativeImplement the chosen alternative

    6.6. Monitor the results to ensure that the desiredMonitor the results to ensure that the desiredresults are achieved.results are achieved.

  • 8/6/2019 3. Decision Analysis

    4/19

    DECISION ENVIRONMENTSDECISION ENVIRONMENTS

    There are three scenarios which refer toThere are three scenarios which refer to CERTAINTY,CERTAINTY,RISK & UNCERTAINTYRISK & UNCERTAINTY..

    Certainty:Certainty: You have an order for 3000 units (Demand = 3000 units).You have an order for 3000 units (Demand = 3000 units). Profit per unit is RS. 30Profit per unit is RS. 30

    Risk:Risk: probabilities can be assigned to the occurrence of states ofprobabilities can be assigned to the occurrence of states of

    nature in the futurenature in the future

    There is a 25% chance of 2000 units, 50% chance of 1000 unitsThere is a 25% chance of 2000 units, 50% chance of 1000 units& 25% chance of an order of 500 units.& 25% chance of an order of 500 units.

    Uncertainty:Uncertainty: probabilities can NOT be assigned to the occurrence of states ofprobabilities can NOT be assigned to the occurrence of states of

    nature in the future.nature in the future.

  • 8/6/2019 3. Decision Analysis

    5/19

    STATES OF NATURE:STATES OF NATURE:

    Events that may occur in the futureEvents that may occur in the future

    Examples of states of nature:Examples of states of nature:

    high or low demand for a producthigh or low demand for a product

    good or bad economic conditionsgood or bad economic conditions

    PAYOFF:PAYOFF: Outcome of a decisionOutcome of a decision

    DECISION ENVIRONMENTSDECISION ENVIRONMENTS ------

    CONT.CONT.

  • 8/6/2019 3. Decision Analysis

    6/19

    Payoff table: a method for organizing andPayoff table: a method for organizing andillustrating the payoffs from differentillustrating the payoffs from differentdecisions given various states of nature.decisions given various states of nature.

    States Of NatureStates Of Nature

    DecisionDecision aa bb

    11 Payoff 1aPayoff 1a Payoff 1bPayoff 1b

    22 Payoff 2aPayoff 2a Payoff 2bPayoff 2b

    PAYOFF TABLEPAYOFF TABLE

  • 8/6/2019 3. Decision Analysis

    7/19

    DECISION MAKING CRITERIADECISION MAKING CRITERIA

    UNDER UNCERTAINTYUNDER UNCERTAINTY

    Maximax Maximin

    Minimax regret

    Equal likelihood

  • 8/6/2019 3. Decision Analysis

    8/19

    EXAMPLE:EXAMPLE:SOUTHERN TEXTILE COMPANYSOUTHERN TEXTILE COMPANY

    STATES OF NATURESTATES OF NATURE

    Good ForeignGood Foreign Poor ForeignPoor Foreign

    DECISIONDECISION Competitive ConditionsCompetitive Conditions Competitive ConditionsCompetitive Conditions

    ExpandExpand $ 800,000$ 800,000 $ 500,000$ 500,000

    Maintain status quoMaintain status quo 1,300,0001,300,000 --150,000150,000Sell nowSell now 320,000320,000 320,000320,000

  • 8/6/2019 3. Decision Analysis

    9/19

    MAXIMAXMAXIMAX SOLUTIONSOLUTION

    STATES OF NATURESTATES OF NATURE

    Good ForeignGood Foreign Poor ForeignPoor ForeignDECISIONDECISION Competitive ConditionsCompetitive Conditions Competitive ConditionsCompetitive Conditions

    ExpandExpand $ 800,000$ 800,000 $ 500,000$ 500,000

    Maintain status quoMaintain status quo 1,300,0001,300,000 --150,000150,000

    Sell nowSell now 320,000320,000 320,000320,000

    Expand: $800,000

    Status quo: 1,300,000 n Maximum

    Sell: 320,000

    Decision: Maintain status quo

    MaximaxMaximax (the maximum of the maxima) criterion is very optimistic.(the maximum of the maxima) criterion is very optimistic.

    Choose decision with the maximum of the maximum payoffsChoose decision with the maximum of the maximum payoffs

    MaximaxMaximax determines the best possible outcomedetermines the best possible outcome

  • 8/6/2019 3. Decision Analysis

    10/19

    MAXIMIN SOLUTION

    STATES OF NATURESTATES OF NATURE

    Good ForeignGood Foreign Poor ForeignPoor ForeignDECISIONDECISION Competitive ConditionsCompetitive Conditions Competitive ConditionsCompetitive Conditions

    ExpandExpand $ 800,000$ 800,000 $ 500,000$ 500,000

    Maintain status quoMaintain status quo 1,300,0001,300,000 --150,000150,000

    Sell nowSell now 320,000320,000 320,000320,000

    Expand: $500,000 n

    Maximum Status quo: -150,000

    Sell: 320,000

    Decision: Expand

    TheThe maximinmaximin (the maximum of minima)(the maximum of minima) criterion is pessimisticcriterion is pessimistic

    Choose decision with the maximum of the minimum payoffsChoose decision with the maximum of the minimum payoffs MaximinMaximin determines the worst payoff for each alternative; the operations managerdetermines the worst payoff for each alternative; the operations manager

    chooses the best worst alternative. Meaning the least (best) of the worstchooses the best worst alternative. Meaning the least (best) of the worst..

  • 8/6/2019 3. Decision Analysis

    11/19

    MINIMAX REGRETMINIMAX REGRET

    SOLUTIONSOLUTIONGood Foreign Poor Foreign

    Competitive Conditions Competitive Conditions

    $1,300,000 - 800,000 = 500,000 $500,000 - 500,000 = 0

    1,300,000 - 1,300,000 = 0 500,000 - (-150,000)= 650,000

    1,300,000 - 320,000 = 980,000 500,000 - 320,000= 180,000

    Expand: $500,000 n Minimum

    Status quo: 650,000

    Sell: 980,000

    Decision: Expand

    Choose decision with the minimum of the maximum regrets for eachChoose decision with the minimum of the maximum regrets for eachalternativealternative

  • 8/6/2019 3. Decision Analysis

    12/19

    EQUAL LIKELIHOOD CRITERIAEQUAL LIKELIHOOD CRITERIA

    STATES OF NATURESTATES OF NATURE

    Good ForeignGood Foreign Poor ForeignPoor Foreign

    DECISIONDECISION Competitive ConditionsCompetitive Conditions Competitive ConditionsCompetitive Conditions

    ExpandExpand $ 800,000$ 800,000 $ 500,000$ 500,000

    Maintain status quoMaintain status quo 1,300,0001,300,000 --150,000150,000

    Sell nowSell now 320,000320,000 320,000320,000

    Two states of nature each weighted 0.50Expand: $800,000(0.5) + 500,000(0.5) = $650,000 n Maximum

    Status quo: 1,300,000(0.5) -150,000(0.5) = 575,000

    Sell: 320,000(0.5) + 320,000(0.5) = 320,000

    Decision: Expand

    Choose decision in which each state of nature isChoose decision in which each state of nature isweighted equallyweighted equally

  • 8/6/2019 3. Decision Analysis

    13/19

    DECISION ENVIRONMENTSDECISION ENVIRONMENTS

    There are three scenarios which refer toThere are three scenarios which refer to CERTAINTY,CERTAINTY,RISK & UNCERTAINTYRISK & UNCERTAINTY..

    Certainty:Certainty: You have an order for 3000 units (Demand = 3000 units).You have an order for 3000 units (Demand = 3000 units). Profit per unit is RS. 30Profit per unit is RS. 30

    Risk:Risk: probabilities can be assigned to the occurrence of states ofprobabilities can be assigned to the occurrence of states of

    nature in the futurenature in the future

    There is a 25% chance of 2000 units, 50% chance of 1000 unitsThere is a 25% chance of 2000 units, 50% chance of 1000 units& 25% chance of an order of 500 units.& 25% chance of an order of 500 units.

    Uncertainty:Uncertainty: probabilities can NOT be assigned to the occurrence of states ofprobabilities can NOT be assigned to the occurrence of states of

    nature in the future.nature in the future.

  • 8/6/2019 3. Decision Analysis

    14/19

    DECISION MAKING WITHDECISION MAKING WITHPROBABILITIES (RISK)PROBABILITIES (RISK)

    Risk involves assigning probabilities to states ofRisk involves assigning probabilities to states ofnaturenature

    Expected valueExpected value

    a weighted average of decision outcomes ina weighted average of decision outcomes inwhich each future state of nature is assignedwhich each future state of nature is assigneda probability of occurrencea probability of occurrence

    EV (EV (xx) =) = pp((xxii))xxii

    nn

    ii=1=1

    xxii = outcome= outcome ii

    pp((xxii)) = probability of outcome= probability of outcome ii

    wherewhere

  • 8/6/2019 3. Decision Analysis

    15/19

    DECISION MAKING WITHDECISION MAKING WITH

    PROBABILITIES: EXAMPLEPROBABILITIES: EXAMPLESTATES OF NATURESTATES OF NATURE

    Good ForeignGood Foreign Poor ForeignPoor Foreign

    DECISIONDECISION Competitive ConditionsCompetitive Conditions Competitive ConditionsCompetitive Conditions

    ExpandExpand $ 800,000$ 800,000 $ 500,000$ 500,000

    Maintain status quoMaintain status quo 1,300,0001,300,000 --150,000150,000

    Sell nowSell now 320,000320,000 320,000320,000

    p(good) = 0.70 p(poor) = 0.30

    EV(expand): $800,000(0.7) + 500,000(0.3) = $710,000EV(status quo): 1,300,000(0.7) -150,000(0.3) = 865,000 nMaximum

    EV(sell): 320,000(0.7) + 320,000(0.3) = 320,000

    Decision: Status quo

  • 8/6/2019 3. Decision Analysis

    16/19

    SEQUENTIALSEQUENTIALDECISION TREESDECISION TREES

    A graphical method for analyzing decisionA graphical method for analyzing decision

    situations that require a sequence ofsituations that require a sequence ofdecisions over timedecisions over time Decision tree consists ofDecision tree consists of

    Square nodesSquare nodes -- indicating decision pointsindicating decision points

    Circles nodesCircles nodes -- indicating states of natureindicating states of nature ArcsArcs -- connecting nodesconnecting nodes

  • 8/6/2019 3. Decision Analysis

    17/19

    EXAMPLE:EXAMPLE: (How to Develop A Decision Tree?)(How to Develop A Decision Tree?)A firm that plans to expand its product line must decide whetherA firm that plans to expand its product line must decide whether

    to build a small or a large facility to produce the new products.to build a small or a large facility to produce the new products.If it builds a small facility and demand is low, the net presentIf it builds a small facility and demand is low, the net presentvalue after deducting for building costs will be $400,000. Ifvalue after deducting for building costs will be $400,000. Ifdemand is high, the firm can either maintain the small facilitydemand is high, the firm can either maintain the small facility

    or expand it. Expansion would have a net present value ofor expand it. Expansion would have a net present value of$450,000 and maintaining the small facility would have a net$450,000 and maintaining the small facility would have a netpresent value of $50,000.present value of $50,000.

    If a large facility is built and demand is high, the estimated netIf a large facility is built and demand is high, the estimated netpresent value is $800,000. If demand turns out to be low, thepresent value is $800,000. If demand turns out to be low, the

    net present value will benet present value will be --$10,000.$10,000.

    The probability that demand will be high is estimated to be 0.60,The probability that demand will be high is estimated to be 0.60,and the probability of low demand is estimated to be 0.40.and the probability of low demand is estimated to be 0.40.

    Analyze using a tree diagram.Analyze using a tree diagram.

  • 8/6/2019 3. Decision Analysis

    18/19

    1

    2

    Demand High (0.6)

    Demand Low (0.4)

    $400,000

    $50,000

    $450,000

    $10,000

    $800,000

  • 8/6/2019 3. Decision Analysis

    19/19

    QUESTIONSQUESTIONS