Statistics project -- 2
Budget: $10 – $30 USD
Task 2: Statistical Report – 15 marks
In this part of the assignment, we will examine data collected within the Australian court system. The subjects in the study are people who suffered brain damage in automobile accidents and sued for monetary damages based on their injury.
The dataset comes from a study that was carried out by Professor J. Chaseling, Griffiths University, Brisbane, to investigate several aspects affecting the recovery of people who have received head injuries and are awaiting the results of litigation. The study took place over twenty years and involved patients from all states in Australia. The data is contained in the file Injury.xls.
The file contains the following information:
Column Name Count Description
C1 Gender 200 0 = male and 1 = female
C2 ID 200 Subject identification number
C3 AgeGrp 200 1 = 0 – 11; 2 = 12 – 20; 3 = 21 – 35; 4 = 35 – 60; 5 = over 60
C4 Mental 1 200 Mental performance before injury
C5 Mental 2 200 Mental performance after injury
C6 Amount 200 Expected payout through litigation
Before you begin your analysis, you will have to take a random sample of 60 from the 200 people on the file. You will need to get your tutor to show you how this can be done in EXCEL. The statistical analysis, described below, is to be based on this sample of 60.
The main aim of the report is to see if there is a difference in the amount of money the plaintiffs requested and the age group and/or gender of the injured person. Your report should contain the following aspects:
Introduction: 3 marks
State the purpose of the report and carefully define the nature of all the variables listed above by classifying them as qualitative or quantitative, discrete or continuous.
Statistical Analysis: 9 marks
• Start by investigating the distribution of the expected payouts through litigation. Make sure you include an appropriate graph and a table comprising those summary statistics you feel are relevant. You should present a brief discussion taking into consideration factors such as measures of centre and spread, as well as the overall shape of the distribution. You should also mention and comment on any outliers if they are present and what effect they might have on the summary statistics.
• Using the same variable as above, take your analysis one step further by making comparisons between the levels (or groups) defined by an appropriate qualitative variable. You should include appropriate comparative graphs, a table comparing summary statistics and appropriate comments on similarities and/or differences between the groups.
• Investigate the relationship between two or more of the variables, at least one of which must be a quantitative variable. In your investigation you should make appropriate use of any of the following techniques, accompanied by appropriate discussion.
• scatterplot
• summary table
• side-by-side boxplots
• comparative (grouped) summary statistics
Discuss each item of computer output that you include. You will be penalised heavily for only showing graphs without discussing what they show!!
Conclusion: 3 marks
• Discuss any overall conclusions or patterns that are apparent from the statistical analysis of the data, graphs, or tables.
In this part of the assignment, we will examine data collected within the Australian court system. The subjects in the study are people who suffered brain damage in automobile accidents and sued for monetary damages based on their injury.
The dataset comes from a study that was carried out by Professor J. Chaseling, Griffiths University, Brisbane, to investigate several aspects affecting the recovery of people who have received head injuries and are awaiting the results of litigation. The study took place over twenty years and involved patients from all states in Australia. The data is contained in the file Injury.xls.
The file contains the following information:
Column Name Count Description
C1 Gender 200 0 = male and 1 = female
C2 ID 200 Subject identification number
C3 AgeGrp 200 1 = 0 – 11; 2 = 12 – 20; 3 = 21 – 35; 4 = 35 – 60; 5 = over 60
C4 Mental 1 200 Mental performance before injury
C5 Mental 2 200 Mental performance after injury
C6 Amount 200 Expected payout through litigation
Before you begin your analysis, you will have to take a random sample of 60 from the 200 people on the file. You will need to get your tutor to show you how this can be done in EXCEL. The statistical analysis, described below, is to be based on this sample of 60.
The main aim of the report is to see if there is a difference in the amount of money the plaintiffs requested and the age group and/or gender of the injured person. Your report should contain the following aspects:
Introduction: 3 marks
State the purpose of the report and carefully define the nature of all the variables listed above by classifying them as qualitative or quantitative, discrete or continuous.
Statistical Analysis: 9 marks
• Start by investigating the distribution of the expected payouts through litigation. Make sure you include an appropriate graph and a table comprising those summary statistics you feel are relevant. You should present a brief discussion taking into consideration factors such as measures of centre and spread, as well as the overall shape of the distribution. You should also mention and comment on any outliers if they are present and what effect they might have on the summary statistics.
• Using the same variable as above, take your analysis one step further by making comparisons between the levels (or groups) defined by an appropriate qualitative variable. You should include appropriate comparative graphs, a table comparing summary statistics and appropriate comments on similarities and/or differences between the groups.
• Investigate the relationship between two or more of the variables, at least one of which must be a quantitative variable. In your investigation you should make appropriate use of any of the following techniques, accompanied by appropriate discussion.
• scatterplot
• summary table
• side-by-side boxplots
• comparative (grouped) summary statistics
Discuss each item of computer output that you include. You will be penalised heavily for only showing graphs without discussing what they show!!
Conclusion: 3 marks
• Discuss any overall conclusions or patterns that are apparent from the statistical analysis of the data, graphs, or tables.