Marina Knight
Visit Marina Knight's profile on the York Research Database to:
- See a full list of publications
- Browse activities and projects
- Explore connections, collaborators, related work and more
Profile
Biography
BSc Mathematics (Bucharest)
MSc Stochastic Processes and Theoretical Statistics (Bucharest)
PhD Statistics (Bristol)
Post-doctoral research positions sponsored by GCHQ (Bristol, 2006-2008) and on the EPSRC funded project Locally Stationary Energy Time series (Bristol, 2011-2013). [Academic career break to fit with my very young family-- worked part-time as a medical statistician for NHS Blood and Transplant, Bristol, 2008-2011.]
In September 2013 I joined the Department of Mathematics at the University of York as a Lecturer in Statistics.
Departmental roles
University roles
Member of the University Impact Leads for Science Departments Group
Research
Overview
My main research interests are second generation wavelet techniques for analysing irregularly sampled data, possibly over networks (these are often termed lifting schemes); modelling and forecasting of time series whose characteristics evolve through time; long memory estimation.
Work in the real- and complex-valued second generation wavelet area led to improved precision in long memory and nonparametric regression estimation. The interested reader can use the associated R packages ‘liftLRD’, ‘CLiftLRD’, ‘CNLTreg’, ‘adlift’ and ‘nlt’, all on CRAN.
Work on locally stationary time series introduced new methods for spectral estimation in the presence of missing data with practical applications (e.g. paleoclimatic data) and clustering and spectral domain testing for circadian rhythms. Both real- and complex-valued second generation wavelets have been proposed, with the complex-valued construction allowing for phase and coherence information to be represented when dealing with nonstationary bivariate time series sampled over non-uniform designs.
Recent co-authors: Prof Seth Davis (Biology, York), Dr Jon Pitchford (Mathematics and Biology, York), Jess Hargreaves (Mathematics, York); Dr Matt Nunes, Dr Rebecca Killick , Prof Idris Eckley (Lancaster); Prof Guy Nason (Bristol), Dr Jean Hamilton (Sheffield), Prof Piotr Fryzlewicz (LSE).
Supervision:
Jonathan Embleton (PhD student): started October 2017.
Jess Hargreaves (PhD student): 2014-2018 (joint supervision with Pitchford and Davis).
Sarah Lock (MSc by Research): 2016-2017 (joint supervision with Davis).
Research group(s)
Statistics and Probability Research Group
Available PhD research projects
My projects span the fields of multiscale methods, nonparametric statistics, analysis and forecasting of non-stationary time series, in particular for data collected on irregular and spatial structures. Particular application fields of interest include energy and biology.
Supervision
Current Research Students
Dingjia Cao - dc1221@york.ac.uk
Jonathan Embleton - je687@york.ac.uk
Lisa Readdy - ljr563@york.ac.uk
Teaching
Undergraduate
- Financial Time Series
- Generalised Linear Models
Postgraduate
- Advanced Regression Analysis
- Generalised Linear Models
