Background

This is an individual assignment. You need to analyze a given data set, and then interpret and draw conclusions from your analysis. You then need to convey your findings using plain language in a written report to a person with small or no experience of Business Analytics.

Submission instructions

The assignment must be submitted by the due date, electronically in CloudDeakin. When filing electronically, you must check that you have sent the work correctly by following the instructions provided in CloudDeakin. Please note that we will NOT receive any paper or email copies, or section of the assignment submitted after the deadline.

You need to keep a backup copy of every assignment you submit (that is, the work you have done to date) until the assignment has been recorded. In the strange event that an assignment is misplaced, you will need to submit your backup copy. Work you provide will be checked by electronic or other means to detect collusion and plagiarism.

When you submit an assignment within your CloudDeakin unit site, you will receive an email to your Deakin email address confirming that the assignment has been sent. You should verify that you can see your homework in the Submissions view of the Assignment Dropbox folder after upload, and check for, and keep, the email receipt for the submission.

Penalties for late submission: The following marking fines will apply if you submit an assessment task after the due date without a permanent extension: 5% will be deducted from possible marks for every day up to 5days, and work that is submitted more than 5 days after the due date will not be marked. You will collect 0% of the task. ‘Day’ means calendar days or part thereof. The Unit Chair may refuse to receive a late submission where it is silly or impracticable to assess the task after the due date.

The assignment uses the file A1.xlsx, which can be downloaded from CloudDeakin. Analysis of the data needs the use of techniques studied in Module-1.

Assurance of Learning

This assignment assesses the following Graduate Learning Outcomes and related Unit Learning Outcomes:

Graduate Learning Outcome (GLO)	Unit Learning Outcome (ULO)
GLO1: Discipline-specific knowledge and capabilities – appropriate to the level of study related to a discipline or profession.  GLO3: Digital Literacy – Using technologies to find, use and disseminate information   GLO5: Problem Solving – creating solutions to authentic (real-world and ill-defined) problems.	ULO 1: Apply quantitative reasoning skills to solve complex problems.  ULO 2: Use contemporary data analysis and visualisation tools and recognise the limitation of such tools.

Feedback before submission

You can seek assistance from the teaching staff to ascertain whether the assignment conforms to submission guidelines.

Feedback after submission

An overall mark together with suggested solutions will be released via CloudDeakin, usually within 15 working days. You are expected to refer and compare your answers to the proposed solutions to understand any areas of improvement.

Case Study

According to a study published in the US News and World Report, the cost of medical neglect in the United States is $55.6 billion a year, which is 2.4% of yearly health-care spending*.Another 2011 study distributed in the New England Journal of Medicine reported that annually, as the season 1991 to 2005, 7.4 percent of all physicians authorized in the US had a malpractice claim. These large numbers not only contribute to the high cost of health care, but the size of successful negligence claims also adds to high premiums for medical malpractice insurance.

A report from McKinsey (May 2014)† Unleashing the Value of Advanced Analytics in Insurance states:

“The proliferation of third-party data references is reducing insurers’ confidence in internal data. Digital “data exhaust” from social media and multimedia, Smartphone, computers, and other consumer and manufacturing devices — used within privacy guidelines and assuring anonymity — has become a rich source for behavioral penetrations for insurance companies, as it has for virtually all businesses.

Recently, the release of earlier unavailable or inaccessible public sector data has dramatically expanded potential roots of third-party data. The US and UK governments and the European Union have recently started “open data” Web sites to make available large amounts of government statistics, including health, education, worker safety, and service data, among others. With a much greater path to third-party data from a wide variety of sources, insurers can pose new questions and better explain many different types of risks.”

The UnitedHealth Group: America’s most prominent health insurance provider has collated a range of data and wants to develop a better knowledge of its claims paid out for medical negligence lawsuits. Its records show claim payment amounts, as well as information about the presiding physician and the claimant for some adjudicated or settled lawsuits in this year.

You are a Data Analyst working for UnitedHealth Group. You’re Manager – Edmond Kendrick has asked you to conduct a preliminary analysis of collected data. In particular, you are expected to perform a series of descriptive and inferential analyses and produce a report based on the findings. This report must be written in plain language since the interested parties who may read the story do not necessarily have any statistical knowledge.

Edmond’s email detailing the questions you need to answer reproduced on the next page.

* https://www.hsph.harvard.edu/news/press-releases/medical-liability-costs-us/

† https://www.mckinsey.com/industries/financial-services/our-insights/unleashing-the-value-of- advanced-analytics-in-insurance

Email from Edmond Kendrick

To: You

From: Edmond Kendrick

Subject: Analysis of Claims

Hi,

As discussed earlier, I have cleaned and simplified the dataset to eight variables for your convenience. The cleansed dataset contains information the about 200 randomly selected claims made this year.

1. Please provide an overall summary of the Claim Payment amount.
2. I would like to build a profile of a typical claimant. For a start, please estimate:

• the average Age of claimants and
• The proportion of claimants with ‘No Insurance.’

Please include any other factors that you might think would be appropriate to add in the profile of the claimant.

3. I would also like to compare this year’s claims data against several industry standards.

• An industry report suggests that the average amount of paid claims has dropped below $77,500. Is there any indication to support this argument?
• A similar study last year reported that 3 out of 4 applications are with either ‘MILD’ or ‘MEDIUM’ severity conditions. Check if this statement is still valid for all patients?
• Is there a difference in the proportion of ‘MILD’ or ‘MEDIUM’ claims by patient’s Gender? Can we assume that there is a variation in the proportion of ‘MILD’ or ‘MEDIUM’ claims by female patients compared to that of male patients?
• As an industry standard, it is believed that the payment amounts are related to whether or not a private attorney representing the claimant. In particular, the average claim amount when a private attorney is involved is higher than when there is no private attorney involved. Does the data support this proposition?
• Also, the industry stakeholders believe that private attorney representation is higher for ‘SEVERE’ claims than for claims with a ‘MEDIUM’ severity. Is this a valid statement?

4. I would love to get an opinion on the relationship between the specialty of the physician involved, the severity of the claim, and average claim amounts.

• I believe that the percentage of ‘SEVERE’ claims with the involvement of an Orthopaedic surgeon is lower than that of other specialists.
• I also believe that the average claim amount for ‘SEVERE’ claims is higher when an Orthopedic surgeon is involved than the other specializations.

Is there any evidence to support my assertions above?

I look forward to your response. Sincerely,

Edmond Kendrick

Chief Data Scientist – UnitedHealth Group

Chief Data Scientist – UnitedHealth Group

SUBMISSION

The assignment consists of two sections: Analysis and Report. You are asked to submit both your written report and analysis.

Guidelines for Data Analysis

Read the case study and questions asked by Edmond carefully. Then spend some time reviewing the data to get a sense of the context. The analysis required for this assignment involves material covered in Module 1, with the corresponding tutorials being a useful guide.

The analysis should be submitted in the appropriate worksheets in the Excel file. Each question from Edmond’s email should be analyzed in a separate tab (e.g., Q1, Q2 … or Q3.1, Q3.2 …). You need to add these. Before submitting your analysis, make sure it is logically organized, and any incorrect or unnecessary output has been removed. Marks will be penalized for poor presentation or disorganized/incorrect results.

For all questions in the email, you can assume that:

• 95 % confidence level is appropriate for confidence intervals and;
• 0 % level of significance (i.e. α = 0.05) is appropriate for any, hypothesis tests.

You can complete all data analysis using the Excel templates provided in the assignment data file. In choosing the technique to use for a given question, keep the following in mind:

• Are we dealing with a numerical (quantitative) variable or categorical (qualitative) variable?
• Do we have to make an estimate or are we testing a theory, claim, etc.? Each type of question must be answered using a proper technique.
• Are we dealing with one sample/population?
• Are we dealing with two samples/populations (independent samples or pair-samples)?
• Even though question(s) may lead you to inferential analysis, consider conducting the descriptive analysis of the sample data first.

ATTENTION! When you have established that there is a difference between two means or proportions, we expect you to estimate and report the difference.

You may need to make sure assumptions about the dataset we are using to answer some questions. For other problems, there will be technical/statistical assumptions that you need to make; for example, whether to use an equal or an unequal variance test.

Note: Give the Excel file the following name A1_YourStudentID.xlsx (use a short file name while you are doing the analysis.

Guidelines for your Business Report

Once you have completed your data analysis, you need to summaries the key findings for each question and write a response to Edmond’s problems in a report format.

Your business report consists of four sections: Introduction, Main Body, Conclusion, and Appendices. The report should be around 1,500 words.

Use proper headings (e.g., Q1, Q2 … or Q3.1, Q3.2…) and titles in the main body of the report. Use subheadings where necessary.

Keep the language plain and the explanations succinct. That is, avoid the use of any technical statistical jargon. Your reader may not necessarily understand even simple statistical terms. Thus your task is to convert your analysis into plain, understandable expressions.

General instructions:

• You MUST report both descriptive and inferential analysis results. Otherwise, marks will be deducted.
• The report is to be written as a stand-alone document (assume Edmond will only read your written report). Thus, you should not have any direct evidence in the report to your analysis.
• Your report may include relevant excel outputs including templates, tables, charts, and graphs but ONLY as Appendices (appendices are not included in the word count).
• Make sure these outputs are visually appealing; have a consistent formatting style, and proper titles (title, axes titles, etc.); and are numbered correctly. Where necessary, refer to these outputs in the main body of the report.
• The introduction begins by highlighting the main purpose(s) of analysis and concludes by explaining the structure of the report (i.e., subsequent sections). The resolution should highlight the key findings of analyses and explain the main limitations (if any).
• Marks will be decreased for the use of technical terms, inappropriate material, and poor presentation/ organization.

When you have completed the report, it is a useful exercise to leave it for a day, return to it and then re-read. Does it flow easily? Does it make sense? Can someone without prior experience follow your written conclusions? Often, on re-reading, you grow aware that you have clumsily made some points, and you find that you can re-phrase them much more clearly.

Note: Give the report the following name A1_YourStudentID.docx.