Coursework Dataset Analysis using Minitab - Report Findings

Use Minitab to analyse the coursework dataset. Report on your findings.Information on the dataset and on what to include in your report is given in the FURTHER DETAILS section on the next page.

You will need to submit a pdf containing your report, and your Minitab project file: ensure that you read the SUBMISSION INSTRUCTIONS section.

LEARNING OUTCOMES

This assignment will assess the following learning outcomes for the module:

LO1 Summarise and present data by applying appropriate statistical and graphical techniques

LO2 Analyse and interpret data using statistical software

GRADING CRITERIA

Work will be graded according to the criteria given at the end of this document.

FURTHER DETAILS

The dataset that you are required to analyse is available on Moodle as a Minitab worksheet. Note that there are several versions of this dataset: you must analyse your dataset. The dataset contains 100 observations, representing a sample of water pipes. Information on five variables is recorded for each:

• Material whether the pipe is made from Material A, B or C

• Age the age of the pipe (years)

• Diameter the diameter of the pipe (mm)

 [although this takes set values, we treat this as continuous]

• History whether the pipe has a history of damage (Y yes, N no)

• Pressure pressure recorded in the pipe (m)

Your report should have five sections.

Section 1: summary of data weighting 20%

Present numerical and (where appropriate) graphical summaries for each of the variables. Comment on their distributions, and the presence or absence of any outliers.

Section 2: overall estimate of the mean weighting 10%

The mean pressure in pipes of the type included in the sample is expected to be 30 m. Is there any evidence that the mean pressure in the sample is not equal to 30 m? Explain your reasoning, and include any relevant Minitab output to support your conclusion.

Section 3: exploring the effect of the categorical variables weighting 20%

(a) Explore whether the mean pressure differs by material.

(b) Separately, explore whether the mean pressure in pipes with a history of damage differs from that in pipes without a history of damage. Include any relevant Minitab output to support your conclusions.

Section 4: exploring the effect of the continuous variables weighting 20%

(a) Explore the relationship between pressure and age of pipe.

(b) Separately, explore the relationship between pressure and pipe diameter. Include any relevant Minitab output to support your conclusions.

Section 5: regression modelling weighting 30%

(a) Develop a model to predict pressure. Include all steps of your modelling process. Explain why you have chosen your final model, and why you have rejected other models.

(b) For your final model, interpret each of the coefficients and comment on the effect of each predictor in the model.

(c) Comment on the fit of the final model.

Include any relevant Minitab output to support your conclusions.

• Your work must be submitted to the Moodle submission box Data Analysis Report by 11pm on Thursday 3rd December 2020.

• You must submit your report as a single PDF file, including the completed student coursework coversheet.

• You must also submit a Minitab Project file containing a record of your analyses: any results or graphs included in your report must be present in the Minitab Project file.

This file must be submitted to the Moodle submission box Minitab Project File by the same date and time as your report. Note that not submitting this file will limit the mark you can achieve for each section