Accounting Decision Support Tools - Doc

Accounting Decision Support Tools
ASSIGNMENT 3
Student Name
[Pick the date]

Question 1
(a) The decision making process has mainly the following five steps highlighted below
(MTaylor and Tyalor, 2004):
Step 1: Define the expectation from the decision and with highlighting the potential outcomes of
the decision that needs to be made.
Step 2: Listing out all the potential alternatives based on brainstorming
Step 3: For each of the alternatives possible, a risk and outcome analysis needs to be performed
which highlights the potential outcomes and the underlying risk associated.
Step 4: For each of the alternatives, quantify the risk and outcomes in terms of cost and benefit.
Step 5: Select the relevant decision model and then choose the relevant alternative which can
enable making the appropriate decision.
(b) The alternatives refer to the various strategies that the decision maker can potentially deploy
and hence are within the control of the decision maker. States of nature are potential future
events which may occur and are outside the control of the decision maker. The intrinsic
relation between alternatives and state of nature is that for different state of nature, a different
alternative or strategy would work. As a result, the decision maker needs to make a choice
with regards to the optimum alternative keeping in mind the potential probabilities associated
with states of nature (Lieberman, et. al., 2013).
(c) The information and data are shown below:
(1) Conditional profits matrix for the five alternatives and for five sales levels is highlighted
below (Hillier, 2006).
1

(2) Fish vendor: Optimist
Maximum –maximum rule
Maximum payoff =450 and thus, 30kg should be bought by fish vendor.
(3) Fish vendor: Pessimistic
Maximum –minimum rule
Maximum payoff =150 and thus, 10kg should be bought by fish vendor.
(4) Fish vendor is using Laplace criterion.
2

Average rule
Maximum payoff =255 and thus, 25kg should be bought by fish vendor.
(5) Fish vendor is using criterion of regret.
Regret rule
Minimum regret =75 and thus, 25kg should be bought by fish vendor.
(6) Fish vendor is using criterion of regret.
Expected monetary value rule
3

Maximum value =75 and thus, 25kg should be bought by fish vendor.
(7) The optimal sea food quantity that fish vendor needs to buy each week so to maximize the
profit (Hillier, 2006).
Cost of underage = $30-$15 = $15
Cost of overage =$15-$10 =$5
Hence,
Critical factor = 15 / (15 +5) = 0.75
Z value for the critical factor = NORMSINV (0.75) = 0.675
Therefore, optimal seafood quantity = (20) + (5 *0.675) = 23.37 kg
Question 2
Prior probability of success = 0.3
(a) Probability of success p = 0.3
Probability of failure q = 1- p = 0.7
Expected value of profit = (0.3 * 1,000,000) – (0.7*600,000) = -120,000
(b) Expected value of perfect information regarding success and failure of product (Hastie,
Tibshirani and Friedman, 2006).
Expected value of perfect of success =0.3 * 1,000,000 = 300,000
Expected value of perfect of failure = 0
(c) Prior probabilities
4

P (favourable | success) = 0.7
P (unfavourable | success) 1-0.7 = 0.3
Similarly,
Similarly,
P (unfavourable | failure) = 0.8
P (favourable | failure) =1-0.8 = 0.2
Hence,
P (favourable) = (0.3*0.7) + (0.7*0.2) = .35
P (unfavourable) = (0.3*0.3) + (0.7*0.8) = .65
(d) Posterior probability of success for a given favourable
P (success | favourable) = (0.7 *0.3)/0.35 = 0.60
P (failure | unfavourable) = (0.8*0.7)/0.65 = 0.8615
(e) Maximum the firm should pay for market survey
Company would take the project when the survey predictions are favourable (Harmon, 2011).
 Expected value of profit with information
= (0.35*0.60*1,000,000) = 210,000
 Expected value of profit with information
EVPI = 210,000 -0 =210,000
5

Question 3
(a) Simulation model for 1 month operation
(b) Normal and formula views of simulation model (Lieberman, et. al., 2013)
6

7

(c) The minimum average cost as per overbooked rooms are shown below:
(d) To: The Hotel Manager
From: STUDENT NAME
Date : May 8, 2018
Dear Sir
I have carried out the simulation as advised in order to ascertain the respective costs
associated with the overbooked rooms. The results in this regards are highlighted in part
C. From that analysis, it clearly emerges that there needs to be a change in the hotel’s
current overbooking policy as the average costs associated with overbooking by 3 rooms
is about $ 17. However, the optimum choice in this regards is to overbook by 4 rooms as
it would reduce the cost further based on the given trend of no-shows.
Yours Sincerely
STUDENT NAME
Question 4
(a) The requisite regression model with price as the dependent variable and mileage as the
independent variable is given below.
8

Comment
In the above model, the R2 value is 0.7221 which implies that Mileage is able to explain 72.21%
variation in the price of the car. Further, the slope coefficient of mileage is also statistically
significant since the p value is 0.002 and hence significance at 1% can also be established
(Hastie, Tibshirani and Friedman, 2006).
The requisite regression model with price as the dependent variable and age of the car as the
independent variable is highlighted below (Harmon, 2011).
Comment
9

In the above model, the R2 value is 0.7311 which implies that age is able to explain 73.11%
variation in the price of the car. Further, the slope coefficient of mileage is also statistically
significant since the p value is 0.0016 and hence significance at 1% can also be established.
The requisite regression model with price as the dependent variable and age & mileage of the car
as the independent variables is highlighted below.
Comment
In the above model, the R2 value is 0.7388 which implies that age & mileage are jointly able to
explain 73.88% variation in the price of the car. Further, neither the slope coefficient of mileage
nor age is statistically significant since the p value for both the slopes is greater than 0.50
(Hastie, Tibshirani and Friedman, 2006).
Best Model
The best model to use would be simple regression model with age as the independent variable.
This is because for this model the R2 is higher than the corresponding R2 for the simple
regression model. The increase in R2 in the multiple regression model is on account of increase
10

in predictor variables but since both of these end of being insignificant, the adjusted R2 value is
the lowest for the multiple regression model (Lieberman, et. al., 2013).
a) Owing to the higher R2 value produced by the model with age as the independent variable,
this simple regression model would be preferred. Further, the negative coefficient for age and
mileage are acceptable considering the fact that both with age and mileage, there is wear and
tear in the car leading to depreciation in the values. Hence, the inverse relationship between
age &mileage with the price of the car(Lind, Marchal and Waten, 2012).
b) No, Barry should not use the multiple regression models. This is because for this model, both
the slopes are not significant as reflected from the respective p values. One of the major
reasons for this is the high amount of correlation between age and mileage which violates a
key assumption of multiple regression and leads to multi-collinearity. Also, the adjusted R2
value for this model is lower than the two simple regression models. Hence, this model has
poor predictive power and hence the usage of this model is not recommended (Hastie,
Tibshirani and Friedman, 2006).
Question 5
(a) Let the number of unit is x.
At break even, profit =0 (Hair, et. al., 2015)
Model
11

Therefore, the number of units at breakeven point 300
12

(b) Model
Let the number of unit is x.
At profit = $1600
13

Therefore, the number of units for profit of $1600 is 300.
(c) One more product B is also produced by the company.
Total profit = $20,000
Ratio A to B = 2: 1
Let the number of units produced for B is x and hence, A is 2x.
14

15

Therefore, the number of units produced of B is 1000 and of A is 2000.
16

Reference
Hair, J. F., Wolfinbarger, M., Money, A. H., Samouel, P., and Page, M. J. (2015) Essentials of
business research methods. 2nd edn. New York: Routledge.
Harmon, M. (2011) Hypothesis Testing in Excel - The Excel Statistical Master. 7th edn. Florida:
Mark Harmon.
Hastie, T., Tibshirani, R. and Friedman, J. (2011) The Elements of Statistical Learning. 4th
edn. New York: Springer Publications.
Hillier, F. (2006) Introduction to Operations Research. 6th edn. New York: McGraw Hill
Publications.
Lieberman, F. J., Nag, B., Hiller, F.S. and Basu, P. (2013) Introduction To Operations Research.
5th edn. New Delhi: Tata McGraw Hill Publishers.
Lind, A.D., Marchal, G.W. and Wathen, A.S. (2012) Statistical Techniques in Business and
Economics. 15th edn. New York : McGraw-Hill/Irwin.
Taylor, K. J. and Cihon, C. (2004) Statistical Techniques for Data Analysis. 2nd edn.
Melbourne: CRC Press.
17