The University of Southampton
Courses

FEEG6025 Data Analysis & Experimental Methods for Civil and Environmental Engineering

Module Overview

This module concerns the design of experimental or observational studies aimed at enabling the understanding, analyses and interpretation of data and to deliver datasets from which robust, statistically defendable conclusions can be drawn. Essentially the module takes the student through the steps of (i) experiment design, (ii) data analysis and visualisation methods and (iii) data archiving. Engineering and energy case studies with large datasets will be used to enable the student to explore this topic from a real world perspective.

Aims and Objectives

Module Aims

This module is designed for students who have a basic grounding in maths and/or statistics and who want to know more about how to design experimental or observational studies and how to analyse and interpret the data collected in order to draw robust conclusions. The module will follow the ‘lifecycle’ of a number of Faculty/external research projects to provide real-world case studies. It will begin by using these case studies to introduce the basic principles of observational and experimental methods including the choice of approach, instrument design, data collection methods, data management and ethical considerations. Students will be introduced to appropriate descriptive/exploratory statistical and data visualisation methods using data derived from the case studies. The main part of the module will then focus on the multivariate analysis of the available data with a particular focus on regression models involving both continuous and discrete variables, as well as models for failure time, for time series analysis and the application of non-parametric methods. The module will conclude with an introduction to post-study data management including data anonymisation, documentation and archiving. Throughout the focus is on generally applicable concepts, and competences and practical application to contemporary problems in the engineering context.

Learning Outcomes

Knowledge and Understanding

Having successfully completed this module, you will be able to demonstrate knowledge and understanding of:

  • Develop an appropriate experimental research design for an engineering case study taking into account practical limitations.
  • Apply knowledge of statistical analysis to assess a hypothesis by selecting appropriate statistical tests and by correctly interpreting the results of these tests.
  • Propose an appropriate statistical model for a given dataset and interpret the goodness of fit.
Transferable and Generic Skills

Having successfully completed this module you will be able to:

  • As our participants are Post Graduate students who will have already demonstrated a wide range of skills, the list below is included more for the completeness of the module description.
  • Develop and apply deductive and inductive research approaches.
  • Compose a research paper in engineering.
  • Communicate project’s output both orally and in writing.
  • Display initiative and personal responsibility within a team.
Subject Specific Practical Skills

Having successfully completed this module you will be able to:

  • Critically analyse and reflect upon the appropriateness of parametric and non-parametric inference.
  • Critically assess the fit of statistical models including linear, logistic and autoregression models.
Subject Specific Intellectual and Research Skills

Having successfully completed this module you will be able to:

  • Formulate a research question and associated set(s) of hypothesis.
  • Critically evaluate statistical analysis.
  • Apply best practice in data management, anonymization and archiving, in line with current ethical considerations.

Syllabus

The course will endeavour to cover the following topics - Experimental and observational study design, including: power calculations, sample selection & recruitment, and data collection method selection; - Descriptive and exploratory data analysis, including: measures of central tendency, histograms, density distributions, box plots and correlograms; - Statistical inference of parametric and non-parametric data, including: tests, confidence intervals and hypothesis testing. - Statistical models of independent data, including: simple and multiple linear regression; logistic regression, and factorial models. Principles of model selection, Goodness-of-fit. Sensitivity analysis. - Statistical models of dependent data, including: time series analysis (stationarity, trend and seasonality), autocorrelation and autoregression models. - Data management, copyright, anonymization and archiving including open, public and restricted/licensed access data models.

Special Features

Use of a wide range of engineering/energy research datasets, some of which are unique to the faculty. Use of R statistical software: - http://www.r-project.org/ - http://www.rstudio.com (the module will use RStudio) Use of version management tools for statistical analysis: - Students will be encouraged to use tools such as github.com to manage their statistics code and to share/collaborate where appropriate.

Learning and Teaching

Teaching and learning methods

Teaching methods consist of four hours per week, comprising of lectures and of supporting tutorials and practical classes. The classes will require a small amount of preparation and provide material to be reviewed and/or developed through independent study. Students will be expected to demonstrate additional independent learning via their coursework assignments.

TypeHours
Lecture20
Preparation for scheduled sessions6
Wider reading or practice24
Practical classes and workshops18
Follow-up work12
Tutorial10
Revision32
Completion of assessment task28
Total study time150

Resources & Reading list

Field, A., Miles, J. and Field, Z. (2012). Discovering Statistics Using R. 

Shumway, R.H. and Stoffer, D.S (2011). Time series analysis and its applications with R examples. 

Assessment

Assessment Strategy

.

Summative

MethodPercentage contribution
Coursework assignment(s) 40%
Exam 60%

Referral

MethodPercentage contribution
Exam 100%

Repeat Information

Repeat type: Internal & External

Share this module Facebook Google+ Twitter Weibo

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×