Hints and tips:
  • You may need to look up some unfamiliar terms in the title or description to get more of a sense of what is involved.
  • If the project has "No" in the "Current Availability:" field, it is already taken or not being offered this academic year but may be available again in future years.
  • The supervisor name links to a contact details webpage so, if you are interested, you can arrange to discuss this project or even propose a related topic of your own.
Level: BSc, MSc, MSci
Title: Transformations in regression
Supervisor:

Hugo Maruri-Aguilar
Research Area: Probability and Applications [Including Statistics]
Description:

The standard linear regression model assumes that the errors are normally distributed with constant variance. It is of course a simplistic assumption which in practice often leads to overconfident predictions.

This project is concerned firstly with a revision of literature in transformations of data and/or trend in a regression model,  with special emphasis in the technique known as TBS. The aim of transforming the data is to achieve approximate normality

in the (transformed) residuals. Analysis of data will also be a part of this project, and depending on the progress, a simple implementation will be built either in statistical software R or using the known package EXCEL.
Further Reading:

Ruppert, D., Carroll, R.J. (1988). Transformation and Weighting in Regression. CRC
Key Modules:

Students undertaking this course are expected to have taken Statistical Modelling I or equivalent and have interest in data analysis.
Other Information:
Current Availability: Yes