COMM5000 Data Literacy Term 1 2024Matlab

Java Python ASSESSMENT GUIDE

COMM5000

Data Literacy

Sandbox PwC Distribution Project

Milestone 2 Information

Term 1, 2024

Assessment Administrative Details

Turnitin

Turnitin is an originality checking and plagiarism prevention tool that enables checking of submitted written work for improper citation or misappropriated content. Each Turnitin assignment is checked against other students' work, the Internet and key resources selected by your Course Coordinator.

If you are instructed to submit your assessment via Turnitin, you will find the link to the Turnitin submission in your Moodle course site. You can submit your assessment well before the deadline and use the Similarity Report to improve your academic writing skills before submitting your final version.

You can find out more information on the Turnitin information site for students.

Late Submissions

The parameters for late submissions are outlined in the UNSW Assessment Implementation Procedure. For COMM5000, if you submit your assessments after the due date, you will incur penalties for late submission unless you have Special Consideration (see below). Late submission is 5% per day (including weekends), calculated from the marks allocated to that assessment (not your grade). Assessments will not be accepted more than 5 days late.

Special Consideration

Special consideration is the process for assessing the impact of short-term events beyond your control (exceptional circumstances), on your performance in a specific assessment task.

What are circumstances beyond my control?

These are exceptional circumstances or situations that may:

• Prevent you from completing a course requirement,

•     Keep you from attending an assessment,

• Stop you from submitting an assessment,

• Significantly affect your assessment performance.

Available here is a list of circumstances that may be beyond your control. This is only a list of examples, and your exact circumstances may not be listed.

You can find more detail and the application form. on the Special Consideration site, or in the UNSW Special Consideration Application and Assessment Information for Students.

CASE STUDY INFORMATION-- PricewaterhouseCoopers (PwC)

Distribution Project Statement

Wholesale distribution companies typically purchase products from manufacturers/suppliers and then sell them to retail stores, making them available for consumers. Typically, wholesale distributors deal in large quantities of goods and are set up to have warehouses, distribution centres and logistic functions to manage and deliver inventory to retail stores. We are interested in better understanding the profitability of wholesale distribution companies.

Looking at the profitability of wholesale distribution companies globally over the past five years (PwC to provide excel containing raw data), is there a correlation (positive or negative) between their profitability and their local jurisdiction’s GDP and other key economic metrics or events (e.g., the COVID-19 pandemic). If so, what may be the reasons for the correlation? Please provide both quantitative and qualitative analysis supporting any findings.

In addition, with a straightforward business model, wholesale distributors aren’t involved in other key business functions such as manufacturing, R&D, retail trade etc. Are researchers able to review the publicly available information of key global distribution companies and corroborate their key functions, assets, and risks across various jurisdictions (e.g., comparing the activities performed, assets held, and risks borne by wholesale distributors based in the US vs China) to determine the other drivers of profitability that may exist? Please also provide any supporting analysis for these additional considerations.

The key jurisdictions we are interested in are the US, UK, China, Japan, South Korea, Australia, and New Zealand.

MILESTONE 2: Case Study Project Proposal

Report details

Week 7, Sunday 31th March 11:59PM

20%

Report: This is individual work. Reports will be checked for plagiarism.

1000-1500 words (not including tables, graphs, and references)

Via Moodle course site

Description of assessment task

In M1, you have spent time understanding the dataset of your assigned country or countries. M2 aims to use hypothesis testing to explore some of the patterns you may have observed in your analysis in M1.

To address the question of whether the profitability of wholesale distribution companies differs by country of jurisdiction, we can check bar charts of key profitability variables first by country and for some industries.   This is what some of you were able to do in M1, and others will be describing while preparing for M2. However, this descriptive analysis needs to be given a statistical analysis. This will be achieved by conducting significance hypothesis tests to evaluate the evidence from the data and measure uncertainty around the conclusions made.

(A) Country and profits variables

For M2, you are required to consider the following:

Profitability variables:

-     Operating Revenue ($’000)

-     EBITDA: earnings before interest, taxes, depreciation, and amortisation

https://www.investopedia.com/terms/e/ebitda.asp

Countries:

Each student MUST use the TWO countries assigned to then in the data allocation spreadsheet for M1.

Note: Those who want to prepare an analysis for PwC showcase should add at least one more country (of

your choice) to the analysis. We will select some of these M2 reports and send to PwC for feedback. But this

will not affect the grade of M2! (PLEASE IGNORE IF YOU ONLY WANT TO DEAL WITH THE COURSE REQUIREMENT)

(B) Industry Classification

A random selection of THREE industries have been allocated to you in the Country/Year/Industries allocation M2. Please check that your name is in the sheet. If not email [email protected] ASAP!

Choose TWO industries of the three to analyse for M2. The third will be added to the analysis in final report.

(C) Economic Indicators data:

PwC indicated that they wish to check whether some of the economic indicators of a country are factors that drive profitability. You can refer to the Data Economy 2017-2022 file provided with M1.

Statistical Analysis Required for M2:

The task in M2 is to check if:

- (1) there are differences between the TWO countries assigned to you in M1 (analyse only the year 2019) in the TWO profitability measures specified in (A) above ;

-     (2) there is statistical evidence for an Covid effect in the TWO countries assigned to you (in M1). Analyse the two profits measures specified in (A). Do this for full sample and the THREE industries (assigned to you).

In M1, you compared the average profits between 2019 and 2022. You may have not seen a qualitatively big difference. In M2, you will be comparing the year 2019 to the year 2020.

Those who want to explore more for PwC making sense analysis should consider how Covid 19 has impacted different countries GDP:

Australia: It seems 2020 is the comparison year, The economy seems to have recovered to pre-Covid levels in 2022.

China: For China, there seems to be an impact in 2020 and then in 2022.

UK, NZ, US: Similar to Australia, the biggest impact felt in 2020 with levels almost returning to pre-Covid (or higher)levels in 2022.

Run significance hypothesis tests of a series of null hypotheses of equal profitability between your selected countries/years.

1.   Formulate the null hypothesis and the alternative hypothesis for each test. Given what you see in the bar charts, you may decide whether to run a one-tailed or two-tailed test.

2.   State the assumptions under the null hypothesis and consider a test of equal means given by:

Country comparison:

Covid effect test:

Given the large sample sizes in this case, the test statistic above is normally distributed as N(0,1).

3.   State the conclusion of the tests using the p-value method. Use a 1% and 5% significance level to illustrate the test conclusions.

Structure of the report

* The introduction You should briefly summarise the main findings in M1 and how you will approach the analysis of the country effect and Covid effect in M2.

* Hypothesis testing: Describe the purpose of hypothesis testing and how it will help you further your analysis of the objectives stated by PwC, especially for their point about the country of jurisdiction's effect on  COMM5000 Data Literacy Term 1, 2024Matlab ;profitability and about the effect of Covid 19.

- Clearly state your null hypothesis, and especially the alternative(s). One-sided alternatives may be useful in driving links between a country's economic conditions and its wholesale companies' profitability.

For example, if you are testing a null that average profits are the same in China and Australia, but you reject in favour of a one-sided hypothesis that profitability is larger/or smaller in Australia. You may try to check what differs in between China and Australia in terms of their key economic indicators. If Australia’s GDP growth is higher in that year and you suspect that to be driving higher profits, you can argue for an ‘>’ alternative in favour of Australia.  If you do not believe there is any argument for a one-sided alternative, then a two-sided is fine. It

- Explain the rationale of the test statistic and present your test’s finding using the  p-value method.   Your analysis should show that you understand the assumptions behind the tests and the considerations around type

1 and type 2 errors in this case.

This doesn’t need to be long but stated in your description of what you will achieve from significance hypothesis testing for both the country effect and the Covid effect. Remember to state any statistical considerations that may make your tests poor regarding power.

You may choose to present your test decision for the 2 countries in a table:

Table 1: Country Effect summary results of hypothesis testing

		Full sample	Industry 1	Industry 2
Country 2 (2019)	Full sample	Reject/not reject p-value
	Industry 1		Reject/not reject p-value
	Industry 2			Reject/not reject p-value

You can do the same to summarise your test results for the Covid effect (by country).

Table 2: Covid19 Effect summary results of hypothesis testing for ‘Country 1’

		Country 1 year 2019
		Full sample	Industry 1	Industry 2
Country 1 Year 2020	Full sample	Reject/not reject p-value
	Industry 1		Reject/not reject p-value
	Industry 2			Reject/not reject p-value

Table 3: Covid19 Effect summary results of hypothesis testing for ‘Country 2’

		Country 2 year 2019
		Full sample	Industry 1	Industry 2
Country 2 Year 2020	Full sample	Reject/not reject p-value
	Industry 1		Reject/not reject p-value
	Industry 2			Reject/not reject p-value

You may find that the effect is significant for a country and a specific industry. Again, use the bar chart to help you choose what variable/industry and year you want to use for the significance testing.

* Conclusion: The conclusion in M2 should present the key ideas you have been able to extract from your data analysis this far including any key findings from M1 that you can support statistically.

It would be best if you also discussed the plan for the final data modelling. Since we are gearing up to learn about linear regression, your conclusions should indicate how you plan to model the relationship between the profits variable(s) and the company characteristics.  Especially, you should have a clear plan about whether to add the country of jurisdiction and Covid effect in the regression model