< Statistics and Operational Research (STOR-i) : PhD (Full Time)

Contact Information

If you encounter any difficulties accessing Online Courses Handbook information you should contact the student registry:

If you require further details in relation to academic content you should contact the appropriate academic department directly.

Breadcrumbs

Statistics and Operational Research (STOR-i)

PhD (Full Time)

Year:14/15
UCAS Code: 
Minimum Length:36 Month(s)
Maximum Length:48 Month(s)
Credit Points:180
Director of Studies:Professor JA Tawn

Compulsory Modules

back to top
The student must take the following modules:

Educational Aims: Knowledge, Understanding and Skills

back to top
Subject Specific Knowledge, Understanding and Skills
STOR-i’s training programme aims to develop graduates who are outstanding scientifically and who possess the broader competencies required by industry. The programme's development has been informed by consultations with our industrial partners and by STOR-i’s research philosophy. It will have industrial involvement throughout its delivery. We will have high expectations of the degree of ownership taken by STOR-i students of their PhD research. Students will be given ample opportunity to practice and develop the skills they are taught.
The MRes forms the first element of a 4 year integrated doctorate. The MRes will give students (i) a grounding in STOR's mathematical core; (ii) experience of modelling and problem solving for scientific and industrial applications; (iii) an overview of thriving research areas within STOR methodology and applications; (iv) research skills, including those related to computing and presentation; and (v) an opportunity to develop a formal research proposal for their PhD.

Skills:
Through a mixture of traditional taught modules and a problem-based learning approach, during the MRes component the students will gain experience and skills in advanced problem solving and presentation/dissemination skills.
In the later PhD component skills in cross-disciplinary working, project management, effective communication, group working, working with external stakeholders, leadership will be developed through courses on Public and Media Engagement, Impact of Research, Leadership and Project Management, and through the University’s generic transferable skills courses. The students will have the opportunity to practice and develop these skills through a range activities including:  project development; supervision; mentoring and leading group activities; organising workshops; applying for and managing grants; and developing press releases, software and a non-technical website for the dissemination of research.
Knowledge:
Through the statistics and operational research modules that comprise the mathematical core of the MRes component of the scheme of study, participants will:
(i) gain an in-depth knowledge of approaches to data-driven decision making processes from two different disciplinary perspectives;
(ii) learn how to apply such approaches to end user problems thus transcending disciplinary boundaries;
(iii) understand the limitations of a purely statistical approach and that a purely operational research approach fails to account for inherent uncertainty.
They will also be given an opportunity to enhance this knowledge with specific advanced study in key areas of the two disciplines through optional modules and further study through projects based on the Modelling and Problem Solving training elements of the scheme.
In the later PhD component subject knowledge continues to be taught through a range of CPD in STOR which will be achieved through student participation in a minimum of 4 APTS/NATCOR courses (nationally organised courses for PhD students in core topics in statistics and operational research respectively) and through 5 annual master-classes organised by STOR-i. The latter will involve visiting international experts who will give short courses on their specialism.
Student experience:
Students start the programme at the beginning of the academic year with an off-campus induction event to help start the process of team building.
The programme will seek to create a cohort identity to mitigate the risk of isolation often experienced by research students. Collaborative and co-operative work will play an important part throughout the programme of study. This will be a feature of all years of the programme, with considerable integration between the different cohorts.
We intend that each STOR-i student should feel an important part of the centre and be able and willing to contribute to it. We aim to facilitate co-working whenever appropriate. The fact that all STOR-i students will be based within the University’s recently opened Postgraduate Statistics Centre will strongly support the development of a group identity.
Initial development of a group identity will be supported by a team building away day prior to the start of the MRes. A second away day will involve all STOR-i students in structured development activities. To help students settle quickly into the centre, each will be assigned a student mentor from the year above. To maintain social interaction we plan a weekly coffee meeting for staff and students.
In the PhD component each student will present once per year at the STOR-i seminar series. The seminar series will be informal – with plenty of time for active and constructive discussion.
All PhD projects will be at one of the interfaces of statistics, operational research and industry. All students will have a team of two PhD supervisors. Projects at the interface with industry will have an academic staff member as primary supervisor and a representative from the sponsoring industry as a second supervisor. These students will typically spend 1-3 months based with at industrial partner’s institution. Projects at the interface of statistics and operational research will have a supervisor from both the Management Science and Mathematics and Statistics departments.
 
Module Details:
Module Name (Credits) Indicative Content
Mathematical Core (90)
Probability and Stochastic Processes (20) Introduction to probability, Markov processes, Poisson processes and their use for modelling.  The evaluation of complex stochastic properties via simulation
Optimisation (10) Linear programming, mixed-integer programming, heuristics for large scale problems, stochastic programming, stochastic dynamic programming
Likelihood Inference (10) Model-based (likelihood) inference for generalised linear models and stochastic processes and model diagnostics, randomisation methods for non-parametric testing
System Modelling and Simulation(10) Modelling for planning and decision support, systems ideas including complexity and feedback, stochastic discrete event simulation, output analysis with model validation, computational challenges including parallelisation.
Bayesian Statistics (10)  Bayesian inference, prediction and decision making. Conjugate analyses, prior  
Computationally Intensive Methods (10) Importance sampling and related approximations to integrals, and MCMC for analysing complex stochastic systems
Optional Modules
(totalling 20) Choice from a wide-range of existing postgraduate-level courses to allow specialism. Examples include: spatial statistics, extreme value theory, time series and forecasting, credit-scoring, derivative pricing, financial econometrics, credit assessment, revenue management and multivariate statistics and data mining.
Training for Research and Industry (30)  consisting of the following elements:
Skills  Presentation skills for non-technical and technical talks/posters/web design.  Computer skills including programming in C++,R and Visual Basic.
Scientific Modelling (8 half day sessions led by STOR staff and LU or external scientists) Skills for eliciting relevant background to problems through to conceptualising these in a model formulation which integrates the relevant scientific knowledge with STOR methods which capture an appropriate level of assumption.
Industrial Problem Solving Days (4 full days led by industrial collaborators) A current open industrial problem will be presented to the students in groups which are facilitated by staff and current STOR-i students.  An outline approach or solution will be developed for presentation to the collaborator.
Topical Research  Overview (10 half days led by staff and PhD students) Presentations on thriving research areas in STOR. Students will be expected to produce a summary and a brief literature review.
Research  Planning (60)
PhD Research Proposal
(3 month project) Literature review, preliminary study and development of a firm plan for the PhD.

Learning Outcomes: Knowledge, Understanding and Skills

back to top

Subject Specific: Knowledge, Understanding and Skills

The successful doctoral student on the programme is expected to be able to (taken from the expected doctoral outcomes as published by the QAA):
initiate research projects and formulate viable research questions in consultation with other stakeholders including end user organisations;
design, conduct and report collaborative and original research on a user-focused project;
critically evaluate scholarly literature;
demonstrate flexible problem-solving abilities appropriate to the associated disciplines;
align themselves with scholarly conventions in the associated discipline areas;
work in a way that demonstrates respect for intellectual integrity and the ethics of research and scholarship;
work co-operatively with other researchers;
manage time in order to maximise the quality of research;
interrogate information effectively, including the application of computer systems and software where appropriate to the students field of study.

In keeping with the goals of the Doctoral Training Centre initiative generally and the more specific goals of STOR-i, we add the following key learning outcomes:

To have a deep appreciation of the importance of research of high quality which has major industrial and scientific impact;
To have a strong appreciation of the process of determining the key STOR issues in an application, the solution of those problems in terms of inference and decision making and the integration of the solution into practice;
To be able to transcend disciplinary boundaries more generally in solving real world problems relating to today's data-driven decision making processes.

Other differentiating factors relating to transferable skills are brought out in the section below.

The integral MRes qualification provides the necessary underlying skills in terms of research and core transferable skills (being able to articulate, reflect and to be user facing). In more detail, the MRes will develop the necessary skills to define and conduct a collaborative, cross-disciplinary and user focused research project. This will equip them for more sustained, individual and original work at the doctoral level.

The intended learning outcomes for the MRes students are that they should develop:

An ability to initiate research projects and to formulate viable research questions in consultation with other stakeholders including end user organisations;
A capacity to conduct and report collaborative and original research on a user-focused project;
An understanding of the major topics of current STOR international research;
A capacity for critical evaluation of relevant scholarly literature;
Well-developed and flexible problem-solving abilities appropriate to the associated disciplines;
A respect for intellectual integrity and the ethics of research and scholarship;
A capacity to cooperate with other researchers;
An ability to manage time in order to maximise the quality of research;
An ability to manage information effectively, including the application of computer software where appropriate to the student’s field of study;
In addition, students should attain the general skills as outlined below related to being articulate, reflective and user-focused.

General: Knowledge, Understanding and Skills

The programme has a strong emphasis on transferable skills and has the following specific intended learning outcomes in this area:
Present work both in written form and verbally to a variety of audiences to the highest standard, be able to discuss work in collaborative settings and be able to engage in academic discourse;
Apply an advanced understanding of research methodology including quantitative techniques from the different traditions involved and adapt techniques for their own problem domains;
Work with end user organisations in terms of the elicitation of STOR problems; to collaborate with them to bring in the end user’s knowledge to the problem; to build their confidence in the progress of the project; and to negotiate the transfer a solution back into a framework suited for end user.
 

Lancaster University
Bailrigg
LancasterLA1 4YW United Kingdom
+44 (0) 1524 65201