ACF5320 – Semester 1, 2025 – Assignment 2 | 1
+-


ASSESSMENT TASK: Assignment 2
WEIGHTING: 30%
COMPLETION: Individual
GENERATIVE AI: Generative AI tools can be used in this assessment task
In this assessment, you can use generative artificial intelligence (AI) to generate the
specified content in relation to the assessment task. This material must be
acknowledged and recorded in your declaration of AI use.
DUE DATE: 11:55pm, Wednesday, 9 April 2025
OVERVIEW
In this assignment, you are tasked with conducting regression analysis on multiple datasets
provided in Excel format. The assignment is structured around four key cases, each requiring you
to apply regression techniques to predict outcomes based on various independent variables. This
exercise aims to assess your proficiency in predictive modelling, data analysis, and the
interpretation of results within a business analytics context.
• In the Decision case, using the "Decision.xlsx" dataset, you will analyse the impact of
experience on decision-making quality among auditors, examining how it correlates with
intelligence, thinking styles, and personality traits.
• The Haircut case requires you to explore the "Haircut.xlsx" database to determine the factors
that significantly influence a company's revenue, employing regression analysis to identify
these key predictors.
• For the Audit scenario, with the "Audit.xlsx" dataset, you are to investigate the relationship
between audit delay and various descriptive variables, focusing on developing a regression
model that can accurately predict delay durations.
• The Prescription Cost Analysis involves the "Prescription.xlsx" dataset, where you will model
and predict drug costs based on a set of independent variables, enhancing your model's
accuracy through iterative refinement.
Your submission should demonstrate a thorough understanding of regression analysis as applied
to predictive analytics. This includes not only the technical execution of statistical tests but also the
ability to interpret and communicate the significance of your findings in a clear, concise manner.
Through this assignment, you will showcase your capability to leverage Excel for predictive
modelling and to derive actionable insights from complex datasets.

OBJECTIVES
• Understand and apply regression analysis techniques.
• Analyse relationships between dependent and independent variables.
• Interpret and evaluate regression model outputs.
• Develop predictive models based on the analysis.
• Communicate analytical findings effectively.





ACF5320 – Semester 1, 2025 – Assignment 2 | 2



SUBMISSION REQUIREMENTS
Type your responses in a MS Word document and submit your Word document to Moodle.
Cut and paste any relevant output from Excel into your Word document.

You do not need to clean the data and do not delete any data.


Case 1: Decision (10 marks)

Using the “Decision.xlsx” dataset, analyse differences between experienced and
inexperienced participants.
(1.1) Do the experienced versus the inexperienced auditors differ in the quality of their
decisions (i.e., the Decision variable)? Cut and paste relevant statistics from Excel and
explain the statistics. (4 marks)
(1.2) Do the experienced versus the inexperienced differ in terms of any intelligence,
thinking style, or personality trait variables? Identify the ones that are different and
provide the relevant statistics. Cut and paste relevant statistics from Excel and explain
the statistics (only for those that are different). (4 marks)
(1.3) Without using the language of statistics, what do you conclude about experienced
versus inexperienced auditors? (2 mark)

Decision data description
Participants consist of auditors and students. Auditors are considered experienced and
students are inexperienced.


Variable Definition
ID Participant identification number.
Decision Higher values indicate better performance on task requiring professional
judgment.
WPT Number of questions correctly answered on the Wonderlic Personnel Test.
An IQ test. Higher scores indicate higher IQs.
FFM_agree Response to the measures of the agreeableness factor in the Five Factor
Model.
FFM_cons Response to the measures of the conscientiousness factor in the Five
Factor Model.
FFM_ES Response to the measures of the emotional stability factor in the Five
Factor Model.
FFM_extra Response to the measures of the extraversion factor in the Five Factor
Model.
FFM_open Response to the measures of the openness factor in the Five Factor Model.
Exp dummy 0 = inexperienced, 1= experienced
ACF5320 – Semester 1, 2025 – Assignment 2 | 3




Case 2: Haircut (5 marks)

Use the “Haircut.xlsx” database to run regression models that explain the factors that
significantly influence revenue at this company.
(2.1) Report and interpret your best model’s technical details. Cut and paste the relevant
statistics from Excel and explain the statistics. (2 marks)
(2.2) Do you believe that your model is effective for explaining changes in revenue? Explain
and justify your response. (2 marks)
(2.3) Explain in plain language the meaning of your findings. (1 mark)
Haircut data description
You have been provided an Excel file that contains 4 data items. Each row represents the
data for one haircut at a business that operates in two countries. The business does not take
appointments. Customers walk in and wait for a haircut.

Variable Definition
Wait_time the number of minutes the customer waited for the hair cut
Chair_time the number of minutes needed to complete the hair cut
Revenue revenue generated from the hair cut
Labour_cost cost of labor for the hair cut
Country dummy variable for country 1 and country 2
ACF5320 – Semester 1, 2025 – Assignment 2 | 4




Case 3: Prescription Cost Analysis (15 marks)

Assume that you are working for a government agency that is trying to determine the main
causes of different drug costs for different patients. You have data (“Prescription.xlsx”) from six
months of drug prescriptions. You need to model and predict drug costs. The appendix shows
descriptions of the data.

(4.1) Assume that we are using this model: (3 marks)
GrossDrugCost = B0 + B1 * RiskScore + ε
i. Interpret the coefficient and the p-value for the RiskScore variable. Provide a practical
explanation of the RiskScore variable for senior management. (1 mark)
ii. Explain what R-squared means in a statistical way and provide a practical explanation of
the information to senior management. (1 mark)
iii. A coworker wants to know what the predicted gross drug costs would be for a new
member. The new member is a 73-year-old man who the government classifies as frail
and he has a risk score of 510. Using the model above, what would you predict the gross
drug costs will be? (1 mark)
(4.2) Assume we are using this model: (8 marks)
GrossDrugCost = B0 + B1 * Risk Score + B2 * Age + B3 * Gender + ε
iv. Provide a statistical interpretation of the coefficient and p-value for the gender variable.
Provide a practical explanation of the information to senior management. (1 mark)
v. Provide a statistical interpretation of the coefficient and p-value for the age variable.
Provide a practical explanation of the information for senior management. (1 mark)
vi. Provide a statistical interpretation of this model’s intercept. Provide a practical explanation
of the information to senior management. (1 mark)
vii. Compare the adjusted R-squared values between Models 1 and 2. Are they the same or
different? Why? What could you conclude about the differences (if any) in the adjusted R-
squared values? (2 marks)
viii. Senior management wants to know the expected gross drug costs of the average
customer. That is, for the median value of the RiskScore, age and gender, what would you
expect the average gross drug costs to be? (2 marks)
ix. A coworker wants to know what the predicted gross drug costs would be for a new
member. The new member is a 73-year-old who the government classifies as frail and he
has a risk score of 510. Using the model above, what would you predict the gross drug
costs will be if they were a man and if they were a woman? (1 mark)

(4.3) Create a better model (4 marks)
x. Develop a better regression model to predict gross drug costs. (2 marks)
xi. What did you learn from this model that previous models did not tell you? (2 marks)
ACF5320 – Semester 1, 2025 – Assignment 2 | 5




Variables Definition
RecordID Primary key from the database that is a unique number for each
row of MemberID; A unique ID for each different member
Month The month to which the data pertains, listed in numeric format as 1
for January, 2 for February, etc.
GrossDrugCost The total amount of drug costs incurred by a member during the
corresponding month
NLISDummy A dummy variable that takes the value of 1 if the member is listed
as non-low income by the government and 0 otherwise
LISCHOSERDummy A dummy variable that takes the value of 1 if the member chose a
specific plan and 0 if the member automatically was assigned a
plan, i.e., members automatically are assigned (thus,
LISCHOSERDummy
RiskScore A score assigned by the government based on previous
government data indicating how sick someone is, higher scores
indicate members are sicker
SpecialtyDummy A dummy variable that takes the value of 1 if the member utilizes
specialty drugs and 0 otherwise
AdjudicationDays The number of non-holiday workdays in a month Age
Gender A dummy variable that takes the value of 1 if the member is female
and 0 if the member is male
FrailtyDummy A dummy variable that takes the value of 1 if the government
indicates the member is frail and 0 if the government indicates the
member is not frail
HospiceDummy A dummy variable that takes the value of 1 if the member is
receiving hospice care and 0 if they are not
InstitutionDummy A dummy variable that takes the value of 1 if the member is
receiving institutionalized long-term care (e.g., hospital, nursing
facility) and 0 if they are not
ESRDDummy A dummy variable that takes the value of 1 if the member is
receiving care for end-stage renal disease (i.e., end-stage kidney
disease) and 0 if they are not


SUBMISSION DOCUMENT
MS Word file with the answers to all assignment questions supported by screenshots from Excel
output (where relevant). The submitted file should contain student’s Name, Surname, and Student ID.

学霸联盟