Phappine Copyright 201 Iman form by any me Ce RL a QUANTITATIVE TECHNIQUES FOR BUSINESS Book Soe ne. Al RightsReserved No partof his Leaning Device ay be reproduced of sored a detabse eeval system wihout pit permission om Rex BookStore,Cee UR ey Chapter 1 Decision Theory y Phappine Copyright 2013 Rex Bok Soe ne. Al RightsReserved, Nopartof ths Leaning Device ay be reproduced Iman frm by any means or sce a detabase reteval system wthout pr permssen om Rex Bock Store,Ce URE) Introduction In business, managers always make decision to ensure the efficient and effective operation of the business. Examples of business problems that demand decision: 1. What marketing strategy to utilize? 2. How many sales representative to hire? 3. What selling price to impose on the product? Phappine Copyright 2013 Rex Bok Soe ne. Al RightsReserved, Nopartof ths Leaning Device ay be reproduced Iman frm by any means or sce a detabase reteval system wthout pr permssen om Rex Bock Store,Ce URE! Decision-making * Decision-making is the act of selecting a preferred course of action among alternatives. y Phappine Copyright 2013 Rex Bok Soe ne. Al RightsReserved, Nopartof ths Leaning Device ay be reproduced Iman frm by any means or sce a detabase reteval system wthout pr permssen om Rex Bock Store, REXCe UR Td Steps in Decision-Making . Identify the problem . Determine the criteria that can solve the problem. . Search for different possible alternatives . Evaluate each alternative . Select the best alternative . Implement the chosen alternative NOUR WNB Monitor the implementation to ensure it is in accordance with the organization’s Phappine Copyright 2013 Rex Bok Soe ne. Al RightsReserved, Nopartof ths Leaning Device ay be reproduced Iman frm by any means or sce a detabase reteval system wthout pr permssen om Rex Bock Store, EXCe UR Ly Decision Environments 1. Decision-making under the condition of certainty. The decision maker knows which state of nature will occur 2. Decision-making under the condition of uncertainty. A decision maker uses any of the different strategies if he has no information or estimates of the probability of events. Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store, EXURL Ee Maximax Strategy Maximim Strategy Laplace Strategy Hurwicz Criterion Realism Minimax Regret Strategy y Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store,Ce UR Ly 3. Decision-making under the condition of risk. The decision maker does not know exactly which state of nature will occur, but can estimate that any one state will occur. y Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store,me Ra ed The Expected Value of Perfect Information (EVPI) * Ifthe managers are able to determine which among the states of nature will occur, definitely, they know which decision will be the best for the company. * The pay off increases as we determine the certainty of a particular event, this information has a value. Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store,eRe * There are two methods to compute the expected value of perfect information. These are: Method 1: Take the difference between the expected pay off under certainty and the expected pay off under condition of risk. y Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store,RE UR aE * The following are the steps to compute the value of perfect information using Method 1: 1. Multiply the best payoff under each state of nature to its probability. 2. Get the sum of these combined weights. 3. Subtract the highest payoff of the result in decision- making under the condition of risk from the sum of the combined weights. 4. The difference is the value of perfect information. EVPI = Expected Value — Maximum EMV under Certainty under Risk Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store, EXCURL ae} Method 2. Find the expected regret value for each alternative then, EVPI is the smallest expected value. * The following are the steps to compute the value of perfect information using Method 2: 1. Multiply each entry by the probability value of each state of nature of every alternative. 2. Get the sum of these combine weights. 3. The lowest expected regret value is the EPVI. Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store,CR UR se} Decision Tree Analysis A decision tree is a schematic model of decision-making showing the available alternatives for the decision maker including the possible consequences. * There are two types of nodes that can be used in making the tree diagram. A square (a) represents a decision point and a circle (0) represents a chance event. Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store, EXem URE ae The Decision Situation: Owel is planning to open up a new branch of Engrande Lechon at a new location in Pasig or expand the existing branch located in Marikina City. Demand on the new location is expected to be 60% high and 40% low. Fixed cost will reach the amount of P150,000. If the demand becomes high, he expects to have a revenue of P250,000, however if the demand becomes low, he could only expect a revenue of P200,000. Upon analyzing the situation in his existing branch, he believes that by Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store, EXCUR ne introducing new recipes the sales will reach the amount of P120,000 if the demand becomes high. However, if the demand becomes low, he could only expect P80,000 revenue. Projection on high demand in the existing branch tends to be 55% and upon computing the fixed cost it would reach the amount of P50,000. Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store,Information Table for Owel’s Decision Situation CUR ay mead Low (L) | High (H) Revenue Expenses Demand | Demand | Probability | High | Low [| Openanew | 60% | 40% |P250,000| P200,000| p150,000 Branch Expand existing 55% | 459% |P250,000| P80,000 | 50,000 branch Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store,ee RSA ad MS Excel Applications in Decision Theoryme OR aL} MS Excel Applications in Decision Theory * Start with the entries in the first seven rows of the spreadsheet by encoding the given payoff table with alternatives as labels for the rows 4 to 6 and events for the columns B to E. y Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store, EXChapter 1: Decision Theory: Slide 19 Add columns with labels as MAXIMAX in column F, MAXIMIN in column G, LAPLACE in column H, HURWICZ in column |, and E.V. in column J. For these columns along the row of IMPORTED, with the same highlighted array of payoff values in the row 4 of IMPORTED or just type (B4:E4) to create the following EXCEL formulas: Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store,Chapter 1: Decision Theory: Slide 20 F4 => MAXIMAX = MAX (B4:E4) G4 => MAXIMIN = MIN (B4:E4) H4 =} LAPLACE = AVERAGE (B4:E4) 14 => HURWICZ = 0.7*F4 + 0.3*G4 since F4 and G4 are the locations of the best and worst payoffs respectively, while 0.7 or 70% is the coefficient of realism and 0.3 is 100% — 70%. Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store,ee RUT ed J4—> E.V. = SUMPRODUCT ($B$7: SES7, B4:E4) with $ signs for the array B7:E7 to fix the location of the probability values which will be multiplied to each row entry of other alternatives. * Now, highlight all the computed values for the row of IMPORTED for the five criteria, then drag down to obtain corresponding values for row 2 of STANDARD and row of FLATBED. Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store, EXCe Ree) Decision on best alternative will be based on the highest value obtained in every criterion from columns F to J by the formula = MAX (column entries). These are computed in cell reference F7, dragged from F7 to the right until J7 as shown in Pictures 1 and 2. * Row 8 of CERTAINTY will be used for the calculation of the EVPI. * EVC is computed based on the best payoffs in each event, computed in cells B8 to E8, multiplied to the probabilities in cells B7 to E7. + Hence, G8—SEVC = SUMPRODUCT (B7:E7, B8:E8). Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store, EXa So hie sis Sonn SERIES A SW S|RM sewn (ow sIM creme I x a z ° (AMPLE: PROFIT PAYOFF MATRIC Type oftruck | __ Possible demand conditions topurehace _[Verytow| tow | High [veryHigh| MAKMAX [MAKIN | LARLACE | WURWiCZ | Imported | 20000 | 30000 | 18000] 25000 | =ax(ea:ee) | tain(atiea) | sAVERAGE(BA:E4]-0.7°F440.3°C8 | ‘Standard | 15000 [25000 | 12000 | 20000 L v L Flatbed | -20000 | 000 | 30000 | 40000 PRosasiury| 30% | aon | 20% | 10% CERTAINTY) =MAX(B8:6) > ‘=SUMPRODUCTB7:E7. 6:8) «ABS)7-68) cy EGRET TABLE “Type of ruck | __Possble demand conditions [MINIMAX to purchase |VeryLow| tow | High [Very High| REGRET Imported | =MAn(6$aiS6)84 | Man(si3i3)| (9516 $e516,015-613) ‘Standard v Flatbed | y Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store, REXCURL ea [Funnesee) | =avenaceteatal =0.7°F000 3°68] ses7ses7 see) + s + > t ~SUMPRODUCTIOTT B88) ures) | | Jeaniwax — JOweCrTED | | rece | _necrer 1ax(015-3) =SUMPRODUCT(S8S16:5¢516815-615) Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store, REXCR ey Copy and paste the given payoff matrix in row 11 with the same labels of alternatives and events. Type REGRET TABLE in row 10. The payoff entries in copied table will be deleted to set up computations for the regret values. For Profit payoff, we consider the formula Regret Value as the highest profit among the event minus each entry. y Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store,CUR es) * Hence, in EXCEL, we apply the following formula in just one cell B13 Regret Value = MAX (B$4:B$6) — B4, drag down to B15, then while the entries in B13 to B15 are highlighted, drag to the right reaching the cells E13 to E15 of the last event. The $ is inserted only as indicated to allow dragging the formula without changing the position of the row entries. Then add the columns for MINIMAX REGRET in column F and EXPECTED REGRET in column G with the following formulas: Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store,mE UR eed F13 —> MINIMAX REGRET = MAX9B13:E13) drag down to F15. G13—> EXPECTED REGRET = SUMPRODUCT ($B$16:$E $16,B13:E13) drag down. Picture 3 shows the complete table with the computation of EVPI, Method 1 in cell 18 =>EVPI = ABS(J7-G8) and method 2 in cell G16 => EVPI=MIN(G13:G15). Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store,Cee ae) oO He qo Type oftuck | Possible demar Standara | 15000 [25000 12000 | 18000 PROBABILTY, 20% | 40% [CERTAINTY] 20000 | 2500 me Type of truck Imported 10300 | PROBABILTY) 7300 _|€ EveL_ method? Phappine Copyright 2013 Rex Book Soe ne. Al RightsReserved, No partof ths Leaning Device ay be reproduced Iman frm by any means or sxe na dstabase reteval system wthout pr permissen om Rex Bock Store, REX