INCLUDEPICTURE "/Users/karan/Library/Group Containers/UBF8T346G9.ms/WebArchiveCopyPasteTempFiles/com.microsoft.Word/0VbjWALCfTOMhVLwinDD6FJ4thKO1cc

5260848-60350400

INCLUDEPICTURE "/Users/karan/Library/Group Containers/UBF8T346G9.ms/WebArchiveCopyPasteTempFiles/com.microsoft.Word/0VbjWALCfTOMhVLwinDD6FJ4thKO1cco5zc54IuL9Z-wjgYv_ZF9nPh5vgSdZ4PASYO2Y4T1rCc=s900-c-k-c0x00ffffff-no-rj" * MERGEFORMATINET

CASE STUDY PROJECT PROPOSAL

COMM5000 | Data Literacy for Business

Milestone 2

Student name: Karan Rajaram Gavali

Student ID: z5424451

Term 1 2023

Table of Contents

TOC o "1-3" h z u Introduction: PAGEREF _Toc131342811 h 1Hypothesis Testing: PAGEREF _Toc131342812 h 1Hypothesis Test 1: PAGEREF _Toc131342813 h 2Hypothesis Test 2: PAGEREF _Toc131342814 h 2Hypothesis Test 3: PAGEREF _Toc131342815 h 2Hypothesis Test 4: PAGEREF _Toc131342816 h 2COVID Effect Test: PAGEREF _Toc131342817 h 3Conclusion: PAGEREF _Toc131342818 h 5References: PAGEREF _Toc131342819 h 6

Introduction:The descriptive analysis in the milestone 1, the obtained results were able to have an idea about the profitabilitys of the wholesale companies operating in the countries namely Australia, New Zealand and United states for an industry which was related to the medical, dental and hospital equipments. Moreover, the difference between the Gross Profit, Gross Operating expenses, other operating expenses, Profit and loss before tax and Percentage Gross margin for all the three countries. The Correlational analysis between the Profitability indexes were able to state the related analysis in between them. The Covid descriptive statistics helped to gain the overall effect of covid on the countries. The Milestone 2 deals with the hypothesis testing.

Hypothesis Testing:The Hypothesis testing for analysis in the milestone 2 will not only able to find the relationship between the variables but also can be used to predict the relationship based on the theoretical guidelines and empirical evidence. The hypothesis test also useful to test whether there is enough evidence available for the sample data to predict a certain condition is true for the entire population. The objective of the Price water coopers (PWC) to find out the correlation between the wholesale distributors profitability and the local jurisdictions GDP, unemployment rate and inflation and if there is any relation which may be positive or negative what maybe the reasons for such relation observed. The PWC aims for both quantitative and qualitative findings for such correlation.

Initially for the hypothesis testing two tail test is considered between the selected countries Australia and United States of America. The selected profitability variables f or the hypothesis testing are Operating Revenue and earnings before interest, taxes, depreciation, and amortisation (EBITDA). The same variables are cross analysed between countries for any difference, or any relation may be found in these countries for the three industries namely medical, electrical and the construction industry. The observed test result is then concluded using the P value method.

For hypothesis testing the Ho and Ha are considered where the null hypothesis Ho stands there is no evident difference of variation observed between the test profitability variables between the selected countries and alternate hypothesis Ha stands opposite to the null which states there is significant evidence of difference is observed between the profitability variables. For the test the financial year 2017 is selected for the hypothesis because of the enough availability of the data for the year.

In hypothesis testing the Type I and Type II error may be possible. When in the analysis result shows null hypothesis is rejected but in reality, it is true then this is considered as Type I error whereas, when the analysis result failed to reject the null hypothesis but in reality, it is false then Type II error is generated. Both the errors can be minimised by increasing the sample size.

Hypothesis Test 1:

For the medical related wholesaler industry in Australia and USA,

Ho is there is no any significant difference between the mean operating revenue of Australia And USA.

Ha is there is significant difference between the mean operating revenue of Australia and USA.

Country Comparison test = Xaustralia- XusaS2australianaustralia+S2usanusa = (60712.70909-2406991.092)13943418133+13040686409240.612 = -2.25

After comparing the T value and obtaining the P value for 2 tail test P value = 0.0459 which is less than significance level of 0.05 (P value < 0.05) and hence the Null hypothesis is rejected and there is significant evidence of difference between the Australia and USA profitability index of Operating Revenue for the year 2017.

Hypothesis Test 2:For Construction Industry related wholesaler companies in Australia and USA, the Hypothesis test performed as below.

Country Comparison test = Xaustralia- XusaS2australianaustralia+S2usanusa = (61710.81-2444712.833)529404167423+16976000000006 = -4.48

After comparing the T value and obtaining the P value for 2 tail test P value = 0.006529453which is less than significance level of 0.05 and hence the Null hypothesis Rejected and there is significant evidence of difference between Operating Revenue of Construction industry of Australia and USA for the year 2017.

Hypothesis Test 3:For Electric Industry related wholesaler companies in Australia and USA, the Hypothesis test performed as belowCountry Comparison test = Xaustralia- XusaS2australianaustralia+S2usanusa = (26265.09-164974.31)660365438311+1544130541246.7812 = -1.196

After comparing the T value and obtaining the P value for 2 tail test P value = 0.2547 which is greater than significance level of 0.05 and hence the Null hypothesis is failed to reject and there is no any significant evidence of difference between the Australia and USA profitability index of EBITDA for the year 2017.

Hypothesis Test 4:Finally, for all three industries, the combined Hypothesis test performed as below.

Country Comparison test = Xaustralia- XusaS2australianaustralia+S2usanusa = (59016.047-2425851.96859055206368+6975310092496.1124 = -4.38

After comparing the T value and obtaining the P value for 2 tail test P value = 0.0021 which is less than significance level of 0.05 and hence the Null hypothesis Rejected and there is significant evidence of difference between Operating Revenue of Combined construction, Electric and Medical related wholesale industries of Australia and USA for the year 2017.

All in all, for the cross-country analysis for 3 industries namely Medical, Electronic and Construction related wholesale companies the obtained results for the hypothesis testing are as per the below table.

Australia

USA Full sample Medical Industry Construction Electric parts and equipment

Full sample Reject the Null Hypothesis Medical Industry Reject the Null Hypothesis Construction Reject the Null Hypothesis Electric parts and equipment Failed to reject the Null hypothesis

The above table clearly states whether the Null hypothesis is Rejected or failed to reject which gives the clear idea about the Significant difference that may be available or not. For only the electric industry the null hypothesis was failed to reject, for all other industries the null hypothesis was rejected stating there is enough evidence of difference in the mean of profitability indexes between the Australia and USA.

COVID Effect Test:For analysing the covid effect comparison for both the countries within them the following hypothesis is tested

For medical industries in Australia

Ho is there is no any significant difference.

Ha is there is significant difference.

Covid Effect Test = Xbefore- XafterS2beforenbefore+S2afternafter = (60712.71-66631.2771394348917133+1623243945529 = -0.1888

From the above covid effect test for medical industry on the operating revenue of the year 2017 and 2020 is considered. The p value corresponding to -0.1888 is 0.85087 which is larger than significance level of 0.05 and hence, the null hypothesis is failed to reject and there is no any significant evidence of difference between the medical industries profitability and the covid effect.

The similar test is carried out on the electric and construction industry and the results of the same are as below.

Industries Medical Industry Construction Electric parts and equipment

Medical Industry Failed to reject the Null Hypothesis Construction Failed to reject the Null Hypothesis Electric parts and equipment Failed to reject the Null Hypothesis

The above table clearly states the covid effect on the Wholesale companies operating in the Australia shows for the Medical, Construction and the Electric Industry related wholesale companies there was no any significant evidence of change observed between the pre-covid and post-covid profitability indexes of the country. Moreover, the GDP of the country can be seen on the same line of growth hence the outcome of the test is considerable CITATION The231 l 3081 (The World Bank, 2023).

For the covid effect test on USA the same analysis is applied for the results

The hypothesis test stated for medical industry in USA is as follows:

Ho is there is no any significant difference.

Ha is there is significant difference.

Covid Effect Test = Xbefore- XafterS2beforenbefore+S2afternafter = (1925611.5-2115928.07911239366384440.315+112362675131272.714 = -0.14896

for the above covid effect test for medical industry for operating revenue of the year 2017 and 2020 is considered. The p value corresponding to -0.14896 is 0.850875 which is larger than significance level of 0.05 (P value>0.05) and hence, the null hypothesis is failed to reject and there is no any significant evidence of difference between the medical industries profitability and the covid effect for the given set of years.

For the other 2 industries in USA the covid effect test analysis is conducted, and results of the analysed test are as per the below table.

Industries Medical Industry Construction Electric parts and equipment

Medical Industry Failed to reject the Null Hypothesis Construction Failed to reject the Null Hypothesis Electric parts and equipment Failed to reject the Null Hypothesis

So overall, the table clearly depicts that there is no any significant difference between the pre-covid and Post Covid profitabilitys of the wholesale distributor industries namely medical, Construction and the electrical industry in the USA. Also, the country's GDP can be seen to be growing in the same direction, hence the test's results are significant CITATION The231 l 3081 (The World Bank, 2023).

For both the countries the Pre covid and Post covid profitability variables shows no any significant difference however, it has to be also noted that it doesnt mean the pandemic didnt had any impact on the industry maybe the impact wasnt strong enough to detect through the analysis.

Conclusion:The hypothesis testing for the two countrys comparison and the covid effect within the countries highlights the clear idea of any significant difference that maybe possibly overviewed without the test. The Country comparison between Australia and USA for the profitability variables like Operating Revenue and EBITDA shows that for some cases there is significant difference between the mean of the profitability variables and for some its not. The GDP, inflation rate and unemployability rate of both the countries for the year 2017 shows great difference. That suggests the Significant difference depicted by the analysis seems reasonable. These results are useful for Final data modelling as the regression model can depict the relation between the dependant and independent variables.

The Country jurisdiction for both the countries shows some variation but for covid analysis there is no any significant difference between mean is observed that may suggest that the profitability of the wholesale dealing companies was unaffected due to the Corona Pandemic. Considering the GDP, unemployment rate and inflation rate for the years 2017 and 2020 as there is no any major change found in this years the result of the analysis seems considerableCITATION The231 l 3081 (The World Bank, 2023)References:

BIBLIOGRAPHY The World Bank, 2023. The World Bank. [Online] Available at: https://data.worldbank.org[Accessed 30 03 2023].

Milestone 1

Introduction:

Funds management is a company that manages the portfolio investment on behalf of individuals and an organisation. Currently, company is interested in international services industry as one of the high potential investment market. This study report will give insights about historical performance and future projection of industries across key regions like China, Australia, and New-Zealand where China as a reporter country and, Australia and New Zealand as partner countries. Taking insights from this report will help client to through creating investment strategy effectively.

The cross border services industry plays an important role in global economy by generating substantial employment and contributing significantly to both importing and exporting countries. However, covid 19 brought unseen challenges by lockdown and unemployment of millions of people. This report will help to understand how this disruption has affected the business and how it has accelerated some trends like remote service delivery and digital transformation which thrived specific services in specific region. Using this information client can make strategic decision ensuring the high opportunities with low risks.

Data Summaries and Descriptive Statistics:

1. Data Preparation

1.1 Data and Resources

There are two datasets available. Data_Service.xlsx contains annual bilateral data covering reporter and partner countries. There are five (5) spreadsheets for each reporter country. Data_Economy.xlsx contains economy specific variables in four (4) spreadsheets. Both datasets are checked for consistency, partially cleaned and formatted.

You are required to use notes and descriptions of variables in each database to gain further insights.

You will also receive extra help during the lectures and seminars on how to handle the databases.

Data Merging

However, the data from these countries are deliberately not merged. It is for you to decide if you want the data to be merged into one large spreadsheet file or leave it as separate countries. This depends upon the type of analysis you want to do.

Extra Data

If you want data to be used in your analysis, which is not presented in the spreadsheet, then you have to go and find the data from websites or the library. For example, you might want to use an annual inflation rate as part of your analysis.

In the Excel spreadsheet, you need to create a few columns for the annual inflation rate (assuming you want them for several years).

2. Data Cleaning

Category 1: Fill Missing Values

There were some missing values in the dataset. You have the choice of deleting the whole column or substituting the missing values with another value, such as an average, instead of deleting them. It is perfectly all right for you to delete the whole column. However, you must be able to justify your action.

Alternatively, if there are many missing values for one year, then you might want to exclude data for that year.

If you find one row has plenty of data missing but other rows have data, then you might decide to delete that row.

If you want to substitute the missing values with a number, you can use techniques and methods such as imputation. Imputation method is to substitute the missing value based on calculation such as mean, median or mode. As for replacing the missing value with mean, median or mode, you can do this if it makes sense to do so. For example, the missing value could potentially use this technique. However, you must justify if replacing the missing value makes sense.

When you try to work out the mean, say, you should exclude missing values and zeroes. Here, we assume zero values are also missing values, not zero. For example, in Excel, you will make a copy of the column and save it in another tab (because you want to delete some of the rows). You may want to delete the missing values and zeroes rows before performing the calculation. You then perform the new mean (it excludes all the zero rows) calculation. Once you have the mean, you then go back to sheet to substitute the missing values with the new mean.

Category 2: Delete Columns

Delete the columns you do not need for your analysis. If you are unsure if you need the columns for your analysis, then just leave them in spreadsheet first.