Quantitative Techniques (OK Na!)

UNIVERSITY OF SAINT LOUIS-TUGUEGARAO
School of Business Administration and Accountancy, 2013-2014

Junior Philippine Institute of Accountants
MEMORY AID IN MANAGEMENT ADVISORY SERVICES
Any form of reproduction of this copy is strictly prohibited!!!
________________________________________________________________________________________________________
CHAPTER 14:
Quantitative Techniques in Business
RATIONALE IN USING QUANTITATIVE TECHNIQUES 1. Probability Analysis
2. Decision Tree
 Managers aim to influence the future. To do 3. Gantt Chart
that, the future must be predicted. Second, 4. Program Evaluation and Review Technique
plans must be in place. Third, actions should (PERT)
be controlled to see to it that it conforms to 5. Linear Programming
the plan. Moreover, Management 6. Queuing
accountants use quantitative techniques in 7. Learning Curves
developing the necessary information 8. Sensitivity Analysis
needed by management in carrying out 9. Regression Analysis
their functions that include planning, 10. Present Values
controlling, and decision-making. 11. Inventory Models
QUANTITATIVE MODELS PROBABILITY ANALYSIS

(OR MATHEMATICAL MODELS )
☛PROBABILITY ANALYSIS
 Real-life decision situations are modeled  commonly used in planning, as well as in
mathematically under certain assumptions decision- making under uncertainty. It deals
in order to achieve a deterministic solution. with a chance that a future event may or
may not occur.
☛SIMULATION
 a technique for experimenting with  DECISION-MAKING UNDER
mathematical/ logical models using a CERTAINTY – for each decision
computer. alternative, there is only one
event, and therefore only one
☛STEPS IN THE SIMULATION PROCEDURE outcome. The event has a 100%
a. Defining the objective chance of occurrence.
b. Formulating the model – the variables, their
behavior, and their interrelationships are  DECISION- MAKING UNDER
spelled out in precise logical/ mathematical CODITIONS OF RISK– the
terms. probability distribution of the
c. Validating the model – to ensure realistic possible future states of nature is
result of the experiment known.
d. Designing the experiment – involves
sampling the operation of the system.  DECISION-MAKING UNDER
e. Conducting the simulation and evaluating CONDITIONS OF UNCERTAINTY –
the results each decision alternative has
several events or outcomes. The
☛COMMONLY USED QUANTITATIVE MODELS probability distribution of the
1 Management Advisory Services (MAS) Committee : Hazeleen Martinez; Jimmy Joe Miranda; Cliff Mark
Confidente; Corina Bariuan; Kristina Gaddon; Rizalyn Taguibao ;Niῆo Rey Mangupag; Marjhon Maramag; Leo
Jay Labasan
Adviser: Mary Queen Ramos, CPA
________________________________________________________________________________________________________
possible future states of nature  INDEPENDENT EVENTS - the occurrence of
(events) is not known and must be one event has no effect on the other event.
determined subjectively.  DEPENDENT EVENTS - the occurrence of
one event has an effect on the other event.
☛PROBABILITY DISTRIBUTION  PAYOFF – the value assigned to the
 specifies the values of the variables and different outcome from a decision
their respective probabilities.
☛EXPECTED VALUE
☛PROBABILITY  The expected value of an action is
 a mathematical expression of doubt or calculated by multiplying the probability of
assurance about the occurrence of a chance each outcome by its payoff and summing
event. Its value varies from zero (0) to one the products. Expected value represents the
(1) or 100% long-term average payoff from repeated
trials.
PROBABILITY OF 0 - the event cannot occur
PROBABILIT OF 1 OR 100% – the event is ☛PAY OFF (DECISION) TABLE
certain to occur  presents the outcomes (payoffs) of specific
PROBABILITY BETWEEN O AND 1 – decisions when certain states of nature
indicates the likelihood of the event’s occurrence. (events which are not controllable by the
decision-maker) occur. The payoff table is a
☛TYPES OF PROBABILITIES helpful tool for identifying the best solution
1. OBJECTIVE PROBABILITIES – calculated given several decision alternatives and
from either logic or actual experience. For future conditions that involve risk.
example, the probability that a coin will
yield heads is 0.50 or 50% on any singe toss.
2. SUBJECTIVE PROBABILITIES – estimates of EXPECTED VALUE OF PERFECT INFORMATION
the likelihood of future events are based on
judgment and past experience. ☛Perfect Information
Example: The likelihood that a winner in an  the knowledge that a future state of nature
amateur singing contest will become a (event) will occur with certainty. In this
successful recording artist case, it is assumed that the probability
distribution is an accurate representation of
☛BASIC TERM USED IN PROBABILITY ANALYSIS the relative frequency of future demand
and that the decision maker knows exactly
 MUTUAL EXCLUSIVE - if two events cannot when each possible event will occur.
occur simultaneously
 JOINT PROBABILIITY - both events will ☛EXPECTED VALUE OF PERFECT INFORMATION
occur  the difference between the expected value
 CONDITIONAL PROBABLITY - one event will without perfect information and the result
occur given that the other event has already if the best action is taken given perfect
occurred. information
Jay Labasan
________________________________________________________________________________________________________
☛COST OF PERFECT INFORMATION 4. Compute the expected values of the
 Management may have the opportunity to outcomes
acquire additional information that may 5. Evaluate the results and choose the
help in choosing the best alternative. best course of action.
However, obtaining information requires
incurrence of cost. GANTT CHART
DECISION TREE ☛GANTT CHART (or Bar Chart)

 shows the different activities or tasks in a
☛DECISION TREE project, as well as their estimated start and
 a graphic representation of the decision completion times.
points, the alternative courses of action
available to the decision maker, and the ☛ADVANTAGES:
possible outcomes from each alternative, as 1. A gantt chart is simple to construct and use
well as the relative probabilities and the requiring no special tools or mathematics. It
expected values of each event can be used on all types of projects.
2. A gantt chart is a very useful control tool. As
☛ADVANTAGES OF USING DECISION TREE the project progresses, actual completion
1. Decision trees facilitate the evaluation time can be compared with the plan.
of alternatives by giving the decision 3. A gantt chart can be used to monitor the
maker a visual presentation of the activities in a project. It shows which
expected results of each alternative. activity should be in progress as of a certain
2. Decision trees are useful when date and how close it is to completion time.
sequential decisions are involved
☛DISADVANTAGE
☛LIMITATIONS OF DECISION TREE  A gantt chart does not show the
1. It may be difficult to determine all the interrelationships among the activities in a
possible events, outcomes, and their project. Only simple relationships can be
probabilities. shown on the chart.
2. A case involving so many events and
sequential decision may result into a PROGRAM EVALUATION AND REVIEW TECHNIQUE
more complex decision tree which may (PERT)
not be that easy to use.
☛PERT – A networking technique used for planning
☛STEPS IN PREPARING A DECISION TREE and controlling the activities in a project. It provides
1. Identify the decision points and the management pertinent information about a project,
chance points such as:
2. Determine the events that may result  Expected completion time of the project;
from the chance points. when each activity in a project is scheduled
3. Determine the outcome (payoffs) of to start and finish;
each event, as well as their estimated
probabilities.
Jay Labasan
________________________________________________________________________________________________________
 Which part of the project must be finished
on time to avoid making the whole project Critical path- the longest path through the network.
late;
 How resources may be shifted from one  [NOTE:] A delay in the completion of activities
part to another part of the project without in the critical path would cause a delay in the
affecting the overall completion time of the completion of the entire project.
project; Shortening the total completion of the
whole project can be accomplished only by
 The progress of each part of the project as
shortening the critical path.
of a certain date.
Slack time- the length of time by which a particular

☛PERT DIAGRAM
activity can slip (be delayed) without having any
 An arrow diagram on a network showing
delaying effect on the end event.
the interrelationships or interdependencies
of the various activities of a project.
 [NOTE:] Activities along the critical path have
Although more complex than Gantt Charts,
a slack of Zero, while all non-critical activities
a PERT Diagram has the advantage of
have positive slack.
incorporating probabilistic time estimates
and identifying the critical path.
☛Critical Path Method
 may be considered as a subset of PERT.
-Node- can be called event when all the
CPM is a network technique that uses
activities leading to a node are finished.
deterministic time and cost estimates. Aside
from cost estimates, CPM includes the
Event- represents a specified accomplishment at a
concept of crash efforts and crash cost.
particular instant in time. It represents the start or
finish of an activity, such as 1 or 2 in the network.
☛Crash time
 the time required to complete an activity
-Branch- represents the activities in a
assuming that all available resources are
project
devoted to such activity.
Activity – task to be accomplished. It represents the

☛Crashing the network
time and resources necessary to move from one

determining the minimum cost for
node or event to another.
completing the project in minimum time so
that an optimum trade-off between time
☛Types of activities
and cost is achieved.
☛Accountants role in PERT
Series- an activity cannot be performed unless its
predecessor activity is finished.
1. Determination of cost estimates and actual
cost of each activity in a project.
Parallel- activities that can be performed
2. Preparation of activity/project cost reports
simultaneously
and computation/analysis of cost variance.
Path- a series of activities from start to finish.

Jay Labasan
________________________________________________________________________________________________________
☛Benefit of PERT 1. Specification of a cost or revenue objective
formula.
1. PERT is a very useful technique for planning 2. The limited resources must be subject to
and controlling activities in a project or the alternative uses.
entire project itself. 3. The alternative uses of the limited
2. Some of the procedures included it PERT or resources must be specified.
in PERT/CPM are in harmony with the
accountant’s budgetary tasks and in the ☛Methods for solving linear programming problems
application of a responsibility accounting
system. 1. Graphical method- limited to problems with
3. The technique may be used to solve only two variables
managerial problems pertaining to project 2. Simplex method- applicable even when
scheduling, information system design, and there are more than two variables.
transportation system design.
4. PERT helps to keep the project on schedule QUEUING THEORY
and to provide feedback to management
about the progress of each part of the ☛QUEUING THEORY (Waiting-line Theory)
project.  a study of random arrivals at a processing
or servicing facility of limited capacity. It
☛Limitations of PERT allows the decision maker to calculate the:
 Reliable time and cost data may not be a. Lengths of future waiting lines
readily available and obtaining them may be b. Average time spent in line awaiting
difficult. Persons involved may overstate service or processing
budgeted cost and time estimates to avoid c. Additional facilities required
unfavorable variances and pressure from d. Service level or capacity that minimizes
the superior. waiting and operating cost
LINEARPROGRAMMING ☛EXAMPLES OF QUEUING THEORY APPLICATIONS

1. Check-out counters (cashiers) in groceries/malls
☛LINEAR PROGRAMING 2. Movie ticket booths
 a technique used to optimize an object 3. Expressway toll booths
function (maximize revenue or profit 4. School registrar’s office windows
function, or minimize a cost function), 5. Bank teller windows
subject to constraints (such as scare
resources, minimum/maximum levels of ☛COSTS INVOLVED
production, performance etc. 1. FACILITY COSTS AND OPERATING COSTS- the cost
of providing service
In business linear programming is used for planning 2. WAITING COST- the cost of idle resources waiting
resource allocations (to make optimum use of in line, including the income foregone (opportunity
limited resources.) conditions calling for the use of cost) in the case of waiting customers
linear programming includes:
Jay Labasan
________________________________________________________________________________________________________
 the study of how the outcome of a decision
Objective: to minimize total cost involved (both the process changes as one or more of the
service and waiting costs). assumptions change.
LEARNING CURVES
Decision tree Example
☛LEARNING CURVES (or Experience Curve)
 describes the efficiencies arising from Your company is considering whether it should
tender for two contracts (MS1 and MS2) on offer
experience, because with experience comes
from a government department for the supply of
increase productivity. This productivity certain components. The company has three
increases with production size, but at a options:
decreasing rate.
 tender for MS1 only; or
 A mathematical expression of the  tender for MS2 only; or
phenomenon that incremental unit costs to  tender for both MS1 and MS2.
produce (or incremental unit time used to
produce) decrease as managers and labor If tenders are to be submitted the company will incur
additional costs. These costs will have to be entirely
gain experience from practice.
recouped from the contract price. The risk, of
course, is that if a tender is unsuccessful the
 The time required to perform a given task company will have made a loss.
becomes progressively shorter, but this is
applicable only to the early stages of The cost of tendering for contract MS1 only is
production or any new task. £50,000. The component supply cost if the tender is
successful would be £18,000.
 The curve is expressed as a percentage of
reduced time (usually between 60% and The cost of tendering for contract MS2 only is
£14,000. The component supply cost if the tender is
80%) to complete a task of each doubling of
successful would be £12,000.
cumulative production. Hence, the time
required is reduced by 20% to 40% each The cost of tendering for both contract MS1 and
time cumulative production is doubled. contract MS2 is £55,000. The component supply cost
if the tender is successful would be £24,000.
☛Assumptions:
1. The cumulative average time per unit is For each contract, possible tender prices have been
reduced by a certain percentage each time determined. In addition, subjective assessments
production doubles. have been made of the probability of getting the
contract with a particular tender price as shown
2. Incremental unit time (time to produce the
below. Note here that the company can only submit
last unit) is reduced when production one tender and cannot, for example, submit two
doubles. tenders (at different prices) for the same contract.
SENSITIVITY ANALYSIS Option Possible Probability

tender of getting
☛SENSITIVITY ANALYSIS prices (£) contract
Jay Labasan
________________________________________________________________________________________________________
MS1 only 130,000 0.20 working out the total profit for each of the paths
115,000 0.85 from the initial node to the terminal node (all figures
MS2 only 70,000 0.15 in £'000).
65,000 0.80
60,000 0.95 Step 1
MS1 and MS2 190,000 0.05
140,000 0.65
 path to terminal node 12, we tender for
MS1 only (cost 50), at a price of 130, and
In the event that the company tenders for both MS1
win the contract, so incurring component
and MS2 it will either win both contracts (at the
supply costs of 18, total profit 130-50-18 =
price shown above) or no contract at all.
62
 What do you suggest the company should MS1 only (cost 50), at a price of 130, and
do and why? lose the contract, total profit -50
 What are the downside and the upside of  path to terminal node 14, we tender for
your suggested course of action? MS1 only (cost 50), at a price of 115, and
 A consultant has approached your company win the contract, so incurring component
with an offer that in return for £20,000 in supply costs of 18, total profit 115-50-18 =
cash she will ensure that if you tender 47
£60,000 for contract MS2 only your tender  path to terminal node 15, we tender for
is guaranteed to be successful. Should you MS1 only (cost 50), at a price of 115, and
accept her offer or not and why? lose the contract, total profit -50
The decision tree for the problem is shown below. MS2 only (cost 14), at a price of 70, and win
the contract, so incurring component
supply costs of 12, total profit 70-14-12 = 44
MS2 only (cost 14), at a price of 70, and lose
the contract, total profit -14
MS2 only (cost 14), at a price of 65, and win
MS2 only (cost 14), at a price of 60, and win
Below we carry out step 1 of the decision tree MS1 and MS2 (cost 55), at a price of 190,
and win the contract, so incurring
solution procedure which (for this example) involves
Jay Labasan
________________________________________________________________________________________________________
component supply costs of 24, total profit Hence the best decision at decision node 2 is to
190-55- 24=111 tender at a price of 115 (EMV=32.45).
MS1 and MS2 (cost 55), at a price of 190,  For chance node 7 the EMV is 0.15(44) +
and lose the contract, total profit -55 0.85(-14) = -5.3
 path to terminal node 24, we tender for  For chance node 8 the EMV is 0.80(39) +
MS1 and MS2 (cost 55), at a price of 140, 0.20(-14) = 28.4
and win the contract, so incurring  For chance node 9 the EMV is 0.95(34) +
component supply costs of 24, total profit 0.05(-14) = 31.6
140-55- 24=61
 path to terminal node 25, we tender for Hence the best decision at decision node 3 is to
MS1 and MS2 (cost 55), at a price of 140, tender at a price of 60 (EMV=31.6).
and lose the contract, total profit -55
 For chance node 10 the EMV is 0.05(111) +
Hence we can arrive at the table below indicating for 0.95(-55) = -46.7
each branch the total profit involved in that branch  For chance node 11 the EMV is 0.65(61) +
from the initial node to the terminal node. 0.35(-55) = 20.4
Terminal Node Total profit £'000 Hence the best decision at decision node 4 is to
12 62 tender at a price of 140 (EMV=20.4).
13 -50
14 47 Hence at decision node 1 have three alternatives:
15 -50
16 44
 tender for MS1 only EMV=32.45
17 -14
 tender for MS2 only EMV=31.6
18 39  tender for both MS1 and MS2 EMV = 20.4
19 -14
20 34
Hence the best decision is to tender for MS1 only (at
21 -14
a price of 115) as it has the highest expected
22 111 monetary value of 32.45 (£'000).
23 -55
24 61
The downside is a loss of 50 and the upside is a profit
25 -55 of 47.
We can now carry out the second step of the With regard to the consultants offer then, ignoring
decision tree solution procedure where we work ethical considerations, we could of course, tender 60
from the right-hand side of the diagram back to the for MS2 only without her help and if we were to do
left-hand side. that we would have a 0.95 probability of having our
tender accepted. Hence there are essentially three
Step 2 options:
 For chance node 5 the EMV is 0.2(62) + 0.8(-  as before, tender for MS1 only at a price of
50) = -27.6 115: EMV 32.45, downside -50 (probability
 For chance node 6 the EMV is 0.85(47) + 0.15), upside 47 (probability 0.85)
0.15(-50) = 32.45  tender for MS2 only at a price of 60,
unaided by the consultant: EMV 31.6,
Jay Labasan
________________________________________________________________________________________________________
downside -14 (probability 0.05), upside 34 Y= aXb
(probability 0.95) where:
 tender for MS2 only at a price of 60, with Y= average time for X number of batches
the consultants help, then (assuming she a= the time required for the first batch (or unit)
can fulfill her promise of guaranteeing we X= total output (number of batches)
will be successful), we have a certain b= the learning exponent
outcome with a profit of 34 (terminal node
20) - 20 (cash paid to the consultant) = 14 The value of b is the log of the learning RATE
(express as a decimal) divided by the log of 2. With
On an EMV basis we would still support our original the formula you can find the average time for any
decision. Looking at the risks (probabilities) of output level.
loosing money, and considering tendering for MS2
only at 60, we would essentially be paying the
consultant 20 to avoid a 0.05 chance of loosing 14,
the downside of tendering unaided.
Paying 20 to guarantee not incurring a loss of 14

which will occur with a probability of 0.05 (one in
twenty) does not seem like an awfully good
investment and so we should reject her offer (or
offer her a smaller sum of money in return for her
guarantee!).
Learning Curve Example
Examples of Expected Average and Total Times

Total Output in Expected Expected Total
Batches Average Time Time (hours)
per Batch
(hours)
1 10 (given) 10
2 8 ( 10 x 80% ) 16 ( 2 x 8 )
4 6.4 ( 8 x80%) 25.6 ( 4 x 6.4 )
8 5.12 ( 6.4 x80%) 40.96 ( 8 x
5.12 )
Notice that the schedule shows results only at

doubling points (2 is double 1, 4 is double 2, 8 is
double 4). To determine the average time for some
other number of batches, we can use the following
formula.
Jay Labasan

Quantitative Techniques (OK Na!)

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Quantitative Techniques (OK Na!)

Uploaded by

Copyright:

Available Formats

UNIVERSITY OF SAINT LOUIS-TUGUEGARAO

School of Business Administration and Accountancy, 2013-2014

QUANTITATIVE MODELS PROBABILITY ANALYSIS

DECISION TREE ☛GANTT CHART (or Bar Chart)

Slack time- the length of time by which a particular

Activity – task to be accomplished. It represents the

Path- a series of activities from start to finish.

LINEARPROGRAMMING ☛EXAMPLES OF QUEUING THEORY APPLICATIONS

SENSITIVITY ANALYSIS Option Possible Probability

Paying 20 to guarantee not incurring a loss of 14

Learning Curve Example

Examples of Expected Average and Total Times

Notice that the schedule shows results only at

You might also like