MIS771 Descriptive Analytics and Visualisation

Assignment One

Background

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

Assurance of Learning

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

Case Study

You are Natalia Navarska, a data analyst in the Research and Analysis group at Financial Review Magazine. Your primary role is to evaluate new products and services. You are often required to report outcomes of your analysis to senior editors at the Magazine who have little or no knowledgeof data analysis.

Of specific interest to Financial Review magazine are the increasing numbers of companies that offer brokerage services for car insurance and potentially what this means for consumers. An insurance broker is an independent insurance agent who works with many insurance companies to find the very best available policies for his or her customers. Most of these brokers are advertising that they can save vehicle owners hundreds of dollars each year on insurance premiums.

Just recently, your research and analysis group secured a dataset from the Insurance Brokers Association (IBA), which is a random sample of 400 customers who obtained the services of car insurance brokers. You have performed an exploratory analysis and have emailed the results (see pages 6-7) to Edmond Kendrick, one of the senior editors of Financial Review Magazine.

Edmond has replied to your email regarding the Insurance Brokers. His email is reproduced next page:

Email from Edmond

To: Natalia Navarska

From: Edmond Kendrick

Subject: Analysis of car insurance brokerage services

Hi Nat,

Thank you for the comprehensive analysis and notes. Now I am more curious about what else could we learn from analysing the dataset.

1. From what I can gather from your notes, iChoose was able to save their customers more money than other brokers. Can I now conclude that iChoose, on average, can save more on insurance premiums than uChoose?
2. Your analysis of 400 customers showed that the proportion of dissatisfied (i.e. either

‘Dissatisfied’ or ‘Very Dissatisfied’) urban customers is smaller than the proportion of dissatisfied rural customers. Can we argue that this difference would hold across all urban and rural customers?

3. I did my own analysis of the sample and came to the following conclusions:
   1. The average savings on insurance premiums differ between rural and urban customers.
   2. On average, customers with ‘Agreed Value’ policy saved more on their insurance premiums than the customers with ‘Market Value’ policy;
   3. The proportion of female customers with a diamond level no claim bonus rating (NCBR) is less than male customers with a diamond level no claim bonus rating (NCBR);

What would be great is if you can verify my findings and tell me how much the difference is in each of the three scenarios mentioned above.

4. I would like you to expand the analysis and look at whether:
   1. The average savings on insurance premiums significantly differ between Victoria, NSW and Queensland.
   2. The average savings on insurance premiums significantly differ between 4WD, Luxury and Sports car.
5. Does the proportion of customers who approached their insurance provider before reaching out to a broker differ between the insurance providers?
6. I asked Raj to design an experiment to see the effects of the valuation method and the vehicle type on savings on insurance premiums, he sent me a table with some numbers (see AppendixA). Can you complete the analysis?

I look forward to your response.

Regards

Eddie

Appendix- A: Data for the experiment prepared by Raj

An Extract of the Analysis and Notes Prepared by Nat

Saving Outcome

Mean 229.64 Not benefited from (saving < 0) 72

Standard Error 16.03 & Neither benefited nor lost (saving =0) 25

Median 113

Mode 0 Benefited from (saving > 0) 303

iChoose uChoose vChoose yChoose

• Customer Satisfaction

Customer Satisfaction Count of Customers
Very Dissatisfied 35
Dissatisfied 57
Satisfied 174
Very Satisfied 134
Total 400

• Customer Satisfaction by Area

 Satisfaction
Area Very Dissatisfied Dissatisfied Satisfied Very Satisfied Total
Rural 10 23 32 30 95
Urban 25 34 142 104 305
Total 35 57 174 134 400

Notes to Edmond

Savings:

From a sample of 400 customers,

• On average, car insurance brokers saved their customers $113 (median).
• The middle 50% of customers saved between $12 and $357; a quarter of the customers saved at most $12; three-quarter of the customers saved no more than $357.
• The savings ranged from a loss of $87 to a substantial gain of $1956.
• Almost 40% of the customers, saved between $1 and $200 on their current insurance premiums; car insurance brokers have shown their ability to find an appropriate policy for most of their customers.
• The bulk of the customers have relatively low (in few cases none at all) annual savings on premium, with a relatively small number having high savings. 89% of customers saved up to $600; Only 4% of consumers saved between $1000 and $2000; with only 1%; shows that brokers have the ability to save consumers a massive amount (more than $1600) on their annual premiums but the prospect of making such savings is low.
• 24% of consumers paid a higher premium than previously or did not save on their annual premium.
• 18% of customers made a loss; the brokers are claiming to save most customers hundreds of dollars, but the discussion about the possibility of customers paying more money for the insurance is missing.

Guidelines for your Business Report

Once you have completed your data analysis, you need to summarise the key findings for each question and write a response to Edmond in a report format. Your business report consists of four sections: Introduction, MainBody, 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 brief. That is, avoid the use of any unnecessary technical statistical jargon. Your reader may not necessarily understand even the simplest statistical term. Thus your task is to convert your analysis into plain, easily understandable expressions.