Accounting Decision Support Tools Assignment - Finance Analysis

This document presents a comprehensive solution to an accounting decision support tools assignment, addressing various aspects of financial decision-making. It begins with an overview of the decision-making process, including the identification of alternatives, risk analysis, and monetary considerations. The assignment then delves into specific cases, such as determining the optimal purchase quantity of seafood using a conditional profit matrix and different decision-making rules (optimistic, pessimistic, Laplace, regret, and maximum expected monetary value). The solution also includes a simulation model to analyze the costs associated with overbooked hotel rooms and provides recommendations for optimizing the hotel's overbooking policy. Furthermore, the assignment explores regression analysis, comparing different models to determine the best fit for predicting car prices based on mileage and age. Finally, the solution covers break-even analysis and profit maximization scenarios for different products, providing insights into production levels and profitability.

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

Question1
(a) The decision making process is a multi-step process. Firstly, the underlying decision maker
has to outline the expectations from the decision and also identify the possible otucomes for
the decision that needs to be undertaken. Secondly, the various alternatives have to be
outlined using brainstroming if required. Thirdly, in the context of each alternative that is
possible, an analysis needs to be done so as to highlight not only the risk but also the possible
outcomes. Fourthly, this information regarding risk and outcomes needs to be converted into
monetary terms. Lastly, by taking into consideration the monetary consideration with each
alternatvie and in line with the decision making model consdiered apporpriate, the decision
maker has to be make the requisite decision.
(b) The strategies that a decision maker can take while making a decision are termed as
alternatives. There are potential future events which the decision maker cannot control and
these are referred to as states of nature. The objective of the decision maker is to consider the
various states of nature and their respective likelihood and thereby choose the suitable
alternative.
(c) Determination of purchase quantity of sea food for various cases
(1) The respective conditional profit matrix
(2) Optimistic case
1

Fish vendor should buy sea food quantity = 30 kilogram
(3) Pessimistic case
Fish vendor should buy sea food quantity =10 kilogram
(4) Laplace rule case
Fish vendor should buy sea food quantity = 25 kilogram
(5) Criterion of regret
2

Fish vendor should buy sea food quantity = 25 kilogram
(6) The maximum expected monetary value
Fish vendor should buy sea food quantity = 25 kg
(7) Sea food quantity that the fish vendor should buy = x
Question 2
The various values are computed below:
3

Question 3
(a) Simulated 30 values for various costs for overbooked rooms.
4

(b) Simulation model (Normal and formula view)
5

6

(c) Average cost per day for the overbooked rooms are calculated through simulation model
and is represented below:
(d) From: STUDENT NAME
To: Hotel Manager
Date: 10th May, 2018
7

Dear Sir/Mam
The objective of the simulation undertaken was to compute the related costs of the overbooking
practice that the hotel currently follows. The relevant implications in terms of cost from the
simulation have been highlighted in Part C. The current policy of the hotel is not the most
optimum choice as clear from the output obtained above. It would be recommended that the hotel
makes a shift to overbooking four rooms as the average cost would be lowered to zero taking the
no show trends of the guests into cognizance.
Yours Faithfully
STUDENT NAME
Question 4
a) Model A
Dependent Variable: Price of Car
Independent Variable = Mileage of Car
R2 = 0.7221
8

The above value highlights that mileage variable can explain 72.21% change in the car price.
Further, the slope of the model is also significant assuming 1% significance level since the p
value corresponding to the test statistic is less than 0.01.
Model B
Dependent Variable: Price of Car
Independent Variable = Age of Car
R2 = 0.7311
The above value highlights that mileage variable can explain 73.11% change in the car price.
Further, the slope of the model is also significant assuming 1% significance level since the p
value corresponding to the test statistic is less than 0.01.
Model C (Multiple Regression Model)
9

Dependent Variable: Price of Car
Independent Variable = Age of Car, Mileage of Car
R2 = 0.7388
The above value highlights that mileage & age jointly can explain 73.88% change in the car
price.
Further, the slopes of the model are insignificant assuming 1% significance level since the p
value corresponding to the test statistics for the two slopes is higher than 0.01.
Best Model
The multiple regression would not be selected since the increased R2 is prompted by higher
predictors. Further, in this model, the slope coefficients are insignificant. Therefore, the best
model would be one in which age would be the independent variable as it results in higher R2
value when compared to corresponding value for the model with mileage as the independent
variable.
b) From the simple regression model A and B, the clear superior choice is B on account of better
predictive ability as has been outlined in part (a). Further, it has been observed in the
regression models A and B that the slope coefficients pertaining to mileage and age are
10

negative which does not surprise considering that as these factors increase, the depreciation
charged on the car would increase owing to general deterioration of the car. Thus, the
negative coefficients are on expected lines.
c) With model C, there is an interesting observation that even though R2 is high but neither of
the slope coefficients are significant. This has been caused on account of the high correlation
exhibited between the two independent variables used for the regression model. The multiple
regression model is based on the central assumption of multicollinearity being absent. Due to
violation of this assumption, the multiple regression is not suitable for use.
Question 5
(a) Model I
The total units of ‘product A’ for the break-even = 300 units
(b) Model II
11