Decision Support Tools for Investment, Market Research, Simulation and Regression Analysis

This article discusses various decision support tools such as utility function, decision matrix, EMV, simulation model, regression model, high-low method, break-even analysis, and more. It includes solved examples and references. The subject is relevant for courses in finance, operations research, and statistics. The content is available on Desklib, an online library for study material.

DECISION SUPPORT TOOLS
Student Name
[Pick the date]

Question 1
(a) With regards to individual views about return and risk, utility function plays a crucial role
in capturing the same as a mathematical equation. Also, it is essential to note that this
function tends to dynamic and individual specific. Besides, the amount of money that the
concerned individual has also impacts the utility function. To obtain utility states direct
or indirect method may be deployed. A direct method to represent utility is standard
gamble which highlights the preferences when the outcome is not certain. This is
especially used in healthcare so as to determine the utility of different states of health
which further can be used measuring the quality of life. (Flick, 2015).
(b) (1) State of natures (good, fair and bad)
Stock returns
Deci
sion matrix
(2) Optimist would take (MAXIMAX) maximum payoff strategy for making the decision for
investment. As evident from decision matrix that stock can deliver maximum payoff of $1400
and thus, stock will be the optimal investment choice.
(3) Pessimist would take (MAXIMIN) strategy for making the decision for investment.
1

As evident from above that bond has maximum value $900 and thus, bond will be the optimal
investment choice.
(4) Regret matrix
As evident from above, the minimum regret based on the regret matrix is zero for both bonds and
stocks and therefore the investor should be indifferent as per this criterion (Hillier, 2016).
(5) Expected Monetary Value (EMV) of bond and stock
As evident from above that bond will be the optimal investment choice.
(e) EMV in case when perfect information is available
Question 2
(a) EMV for new electric razor
Positive value implies that Jerry should take electric razor.
2

(b) Prior Probability table
The probability revision for favourable study
The probability revision for unfavourable study
(c) Posterior Probability table
3

(d) Expected value for perfect information
For favourable study
For unfavourable study
Expected value for perfect information would be would be higher than $ 5,000 and hence market
research provided by friend ought to be availed at the cost of $ 5,000.
Question 3
(a) Simulation model
4

5

(b) The average monthly profit for year = $3857.6
(c) “Selling price has increased by $40 and the profit margin has changed from 20% to 22% and
30% to 32%.”
6

The simulation results clearly reflect that the proposed changes are expected to lead to higher
absolute profits coupled with overall business profitability. This measure is therefore expected to
be beneficial for the value maximisation on the part of the shareholders. However, a critical
aspect which requires attention is that owing to increase in unit price, the volume of sales can be
adversely impacted as customers may seek cheaper alternatives. Therefore, it makes sense for the
company not to switch to the proposed changes without conducting limited scale pilot studies to
highlight the impact on sales. Once a favourable outcome is generated in this regards should the
actual switch be made.
Yours Sincerely
STUDENT NAME
7

Question 4
(a) The high- low method
(b) Regression model
Alpha = 0.05
The p value for MH is (0.77) that is higher than alpha 0.05. Therefore, the slope MH is
insignificant.
The significance F (0.774) that is higher than alpha 0.05 and thereby, the above regression model
would not be considered as good fit (Medhi, 2015).
Model 2:
8

Alpha = 0.05
The p value for batches is (0.00) that is lower than alpha 0.05. Therefore, slope batch is
significant.
The significance F (0.000) that is lower than alpha 0.05 and thereby, the above regression model
would be considered as good fit (Hillier, 2016).
Model 3:
9

Alpha = 0.05
For Machine Hours: The p value for MH is (0.79) that is higher than alpha 0.05. Therefore, slope
machine hour is termed as not significant (Flick, 2015).
For Batches: The p value for batches is (0.00) that is lower than alpha 0.05. Therefore, slope
batch is termed as significant (Harmon, 2015).
(c) Second regression model is termed as best model as it represents maximum coefficient of
determination i.e. 0.8331. It indicates that 83.31% changes in over-head cost would be
defined by changes in batches. Further, model 1 and model 3 clearly highlight that MH is an
insignificant variable for overhead cost determination and therefore a model ought to be
chosen which ignores the same (Hastie, Tibshirani & Friedman,2016).
(d) Best regression model equation
10

Question 5
(a) Calculation of unit contribution margin
(b) Total break even units for product B
Total fixed cost = Break even units for product B* Unit contribution margin
Fixed cost = $5000
Total break even units for product B = 5000/5 = 1000 units
(c) Total break even units for product A
Total fixed cost = Break even units for product A* Unit contribution margin
Fixed cost = $5000
Total break even units for product A= 5000/4 = 1250 units
(d) Production of product A to B would be 3:1.
(i) Before tax profit = $3500
Average contribution margin = (Profit before tax + fixed cost)/Sale volume
11

Average contribution margin = 4*(3/4) + 5*(1/4) = $4.25
Sale volume (units) = (5000+3500)/4.25 =2000
Units of product A (units) = (3/4) *2000 = 1500
Units of product B (units) = (1/4)*2000 =500
(ii) After tax profit = $8400
Monthly pre-tax profit is P. Hence, the equation can be made as shown below.
(1-30%) P = 8400,
P =$12,000
Sale volume (units) = (12000+5000)/4.25 =4000
Units of product A (units) = (3/4) *4000 = 3000
Units of product B (units) = (1/4)*4000 =1000
12

References
Flick, U. (2015) Introducing research methodology: A beginner's guide to doing a research
project (4th ed.). New York: Sage Publications.
Harmon, M. (2015) Hypothesis Testing in Excel - The Excel Statistical Master (7th ed.). Florida:
Mark Harmon.
Hastie, T., Tibshirani, R. & Friedman, J. (2016) The Elements of Statistical Learning (4th
ed.). New York: Springer Publications.
Hillier, F. (2016) Introduction to Operations Research. (6th ed.). New York: McGraw Hill
Publications.
Medhi, J. (2015) Statistical Methods: An Introductory Text (4th ed.). Sydney: New Age
International.
13