PhD Scholarship in Designs for Response Surface Methodology with Multiple Responses

This is a scholarship for a PhD in Mathematical science in the field of Experimental designs and Statistics.

Candidates should have an excellent mathematical and statistical background with advanced R programming skills. The project is to generate the needed new design matrices for response surfaces and investigate possible applications.

  • Scholarship for 3 years ($33,000 AUD per year)
  • International (currently in Australia) and Domestic applicants are eligible
  • Eligible applicants must fulfil all the following 3 requirements:
    • Have a Master of Science or Engineering with a research component (thesis).
    • Have a Bachelor (Hons) of Science or Engineering.
    • Have an excellent knowledge of programming in R.

Applications should be submitted by email to A/Prof Stelios Georgiou within a single email titled “Scholarship Application in Designs for Response Surface Methodology with Multiple Responses”.

In this email the applicant needs to attach:

  1. A cover letter describing how the applicant’s skills and research experience address the selection criteria.
  2. A current CV, academic transcripts, and a list of publications (if applicable).
  3. At least one reference letter.

Candidates will be notified of outcome to nominated email.

Selection criteria

  • Degrees in Science or Engineering or equivalent (honours and MSc).
  • An interest in design of experiments and statistics.
  • Knowledge in using the R software in designing experiments.
  • Ability to work both independently and in a team.

Incomplete applications will not be considered.

Applications are open now.

6th February 2022

The project associated with this scholarship is given below: 

Title: Designs for Response Surface Methodology with Multiple Responses

Project description:  Efficient designs for response surface methodology [1] have a broad application area from food science [2] to chromatography [3] and robotics [4]. A lot of these practical applications requires the modelling of processes with multiple inputs and outputs. The traditional design matrices are no longer the best option as their application in such cases would be either infeasible or extremely costly.

The aim of this project is to investigate such situations, to develop new statistical methodology and to generate efficient design matrices for experiments qualified to collect useful data in a feasible and inexpensive way. This new approach will consider prior knowledge on the relationships between the input controllable factors and the output response variables.  The mathematical and statistical properties on the resulting new designs matrices are to be investigated and their optimality under the given prior information is to be proved.

The project also aims to design and develop the needed algorithms and implement them using the R language. All the mathematical and statistical tools that will be established in this project, as well as any new algorithms and any derived software, will be available to the research community.   

[1] Design and Analysis of Experiments DC Montgomery

[2] Applications of Response Surface Methodology in the Food Industry Processes

[3] A Bayesian Approach for Multiple Response Surface Optimization in the Presence of Noise Variables

[4] Optimal robot placement using response surface method

Associate Professor Stelios Georgiou (stelios.georgiou@rmit.edu.au)

aboriginal flag
torres strait flag

Acknowledgement of country

RMIT University acknowledges the people of the Woi wurrung and Boon wurrung language groups of the eastern Kulin Nation on whose unceded lands we conduct the business of the University. RMIT University respectfully acknowledges their Ancestors and Elders, past and present. RMIT also acknowledges the Traditional Custodians and their Ancestors of the lands and waters across Australia where we conduct our business - Artwork 'Luwaytini' by Mark Cleaver, Palawa.