Till further notice you can reach me @…

Ask an Expert - Visit my Virtual Office at LivePerson

Advertisements

PhD Openings [Canada]

PhD Opening at the School of Computational Engineering & Science, McMaster University

An opening for a Ph.D. student is available at McMaster University with a start date in January 2008. The student will be enrolled in the graduate program in the School of Computational Engineering & Science, or in the Department of Mathematics and Statistics, and will work with
Dr. Protas on problems of PDE-constrained optimization using adjoint-based techniques (the project will involve collaboration with an Industrial Partner).

Candidates should have an M.Sc. degree in Applied Mathematics, Computer Science or a relevant engineering discipline. For further details, including admission procedures and requirements and a description of the CES and Applied Mathematics programs, please consult the following URLs:

http://computational.mcmaster.ca/
http://www.math.mcmaster.ca/graduate/

Inquiries should be directed to Dr. Protas at the address:

Bartosz Protas
Department of Mathematics & Statistics
McMaster University
Hamilton, Ontario, CANADA L8S 4K1
Phone: +1 (905) 525 9140 ext. 24116
Fax: +1 (905) 522 0935
Email: bprotas[ at ]mcmaster.ca

PhD Opening at Department of Mathematical and Statistical Sciences, the University of Alberta

An opening for a Ph.D. student is available at the University of Alberta with a start date in September 2008. The student will be
enrolled in the graduate program in the Department of Mathematical and Statistical Sciences,and will work with Professor Minev on
modelling and simulation of red blood cells in shear flows. Candidates should have an M.Sc. degree in Applied Mathematics, Computer Science or a relevant engineering discipline.

For further details, including admission procedures and requirements and a description of the Applied Mathematics programs, please consult the URL: http://www.math.ualberta.ca.

Inquiries should be directed to Professor Minev at:
Peter Minev,
Department of Mathematical and Statistical Sciences
University of Alberta, Edmonton, Alberta, Canada T6H 1J8;
e-mail: minev[ at ]ualberta.ca

Statistical Research in Lancaster

PhD Research Topics in Statistics

A selection of current and previous research topics in Statistics, Social Statistics and Medical Statistics

The following are a selection of research topics that have been put forward by supervisors and are available for suitably qualified students to take up. If one of these projects interests you, then please contact the supervisor listed to discuss what it entails and whether it is still available. We will also consider topics suggested by students and can devise other projects connected with the research interests of the Department. In addition, note also that this list is not exhaustive since many supervisors have not listed their projects here.

Robust Estimation in ARCH Models

Supervisor: Dr Kanchan Mukherjee

A common characteristic of time series data is that the instantaneous variability, called the volatility of the series, is not constant over time but depends strongly on its immediate past. In his seminal work, Nobel Laureate (for the year 2003) R. F. Engle (1982, Econometrica) modeled volatility of a time series by a linear combination of the squares of its immediately past observations and named it the Autoregressive Conditional Heteroscedastic (ARCH) Model. A PhD project in this area could involve investigation of the robust estimation procedures of the underlying regression and variance parameters in a nonlinear regression model with errors exhibiting ARCH effect. Numerical as well as theoretical properties can be studied in details based on weak convergence properties of certain randomly weighted empirical processes.

Multiple Classifier Systems

Supervisor: Dr Idris Eckley

This project will research the theory and application of multiple classifier systems. The project is jointly funded by a FTSE 100 consumer goods company and the EPSRC. Thus, in addition to the usual PhD experience, this will provide an opportunity for you to occasionally work at the company’s site to understand how these tools might be applied in an industrial R&D setting.

Identification of Causal Genetic Variations on Heart Disease

Supervisor: Dr Thomas Jaki

Personalised medicine aims to tailor treatments based on the individual patient’s specific characteristics and is one of the key development areas in health care. New technological developments in the past decade enabled fast and inexpensive genotyping allowing genetic factors to be considered for personalisation of treatments. Single nucleotide polymorphisms (SNPs) are variations in the DNA sequence that occur when a single nucleotide in the genome sequence is altered. The impact of SNPs can be large as they are often related to diseases and to differences in how individuals respond to a therapy or drug. It therefore is of major interest to identify SNPs responsible for these differences in the outcome in order to determine the optimal treatment and dosage.

Based around a collaborative clinical research project in heart disease, this project aims to develop statistical methods for identification of causal SNPs in genotype-phenotype association studies. These relationships are essential for the effective development of specialised treatments and personalisation of doses and treatment regimes.

Developing Valid and Reliable Assessment Tools for Use in Children

Supervisor: Dr Gillian Lancaster

There are many issues related to the measurement of outcomes for health evaluation particularly with respect to child health in developing countries. It has been estimated that more than 200 million children under five years fail to reach their potential in cognitive development because of poverty, poor health and nutrition and deficient care. Increasing evidence has shown that early interventions may help prevent the loss of potential in affected children. However, one of the drawbacks in the implementation of these interventions is the availability of tools to assess child development in non-Western settings. Western developmental assessment tools may be inaccurate when testing children in a different cultural setting, both in terms of the items tested and the normal reference values given for the population. We have developed the Malawi Developmental Assessment Tool (MDAT) and qualitative methods have highlighted that more culturally relevant items can be identified. Performance of these items has been examined using a simple graphical technique based on logistic regression with regression splines. The aim of this project is to develop methods for assessing the validity and reliability of the tool, and particularly to implement and contrast methods for scoring the stages of development of children in Malawi. The tool will be of benefit to community health workers in rural African settings as well as those looking at the developmental outcomes of children in sub-Saharan Africa.
Continue reading