Inference for change-point and related processes

We have been made aware of a convincing email scam that is focusing on our Programme and Workshop participants. Participants may receive an email from a firm called Expo Hotel Services (ehotelservices.org) to arrange accommodation for workshops and/or programmes. This might include a request to provide them with credit card information.

Please note, INI will never ask for your card details. We take all payments via the University of Cambridge Online store https://onlinesales.admin.cam.ac.uk/.

If you have been contacted by this company please contact us as soon as possible.

Programme theme

In many applications data is collected over time or can be ordered with respect to some other criteria (e.g. position along a chromosome). Often the statistical properties, such as mean or variance, of the data will change along data. This feature of data is known as non-stationarity. An important and challenging problem is to be able to model and infer how these properties change. Examples occur in environmental applications (e.g. detecting changes in ecological systems due to climatic conditions crossing some critical thresholds), signal processing (e.g. structural analysis of EEG signals), epidemiology (e.g. early detection of hospital infections from changes in patients antibody levels), bioinformatics (e.g. detecting changes in copy number variation), and finance (e.g. changing volatility). As technology advances, and ever larger and complex data are collected, the need to model changes in the statistical properties of the data, and the difficulty of making inference for these models increases.

Two possibilities for modelling non-stationarity are changepoint models and locally-stationary models. The former splits data into segments, where the statistical properties of the data is the same within a segment, but changes between segments. These are often appropriate for applications with abrupt changes. By comparison, locally-stationary models are based on stochastic processes where the statistical properties vary more smoothly. These two approaches are thus complementary. To date research within both areas is generally carried out independently of the other.

The main themes of the programme will be:

to explore links and synergy between changepoint and locally-stationary models, methods for inference and the associate theory;
to develop (computationally) efficient inference methods, that can be applied to large data, and complex models in modern scientific applications; and
to develop associated statistical theory, that will impact on the application of these models and methods.

A focus of the programme will be the application of these methods, particularly within finance, energy and environment, and biomedical sciences.

Click here to download the programme's final scientific report

Preprints

Title	Year	Programme
Automatic construction and natural-language description of nonparametric regression models Authors: JR Lloyd, D Duvenaud, R Grosse, JB Tenenbaum, Zoubin Ghahramani Download PDF	2013	ICP
On optimal multiple changepoint algorithms for large data Authors: Rob Maidstone, T Hocking, Guillem Rigaill, P Fearnhead Download PDF	2013	ICP
Change points in high dimensional settings Authors: John Aston, Claudia Kirch Download PDF	2013	ICP
On some distributed disorder detection Authors: Krzysztof Szajowski Download PDF	2013	ICP

Workshops

ICPW01

Inference for change-point and related processes

13 January 2014 to 17 January 2014

Seminars

Monday 13th January 2014
10:00 to 11:30	Registration	No Room Required
11:30 to 12:30	Locally Stationary Processes - An Overview	Room 1
12:30 to 13:30	Lunch at Wolfson Court	No Room Required
15:00 to 15:30	Afternoon Tea	No Room Required
15:30 to 16:30	Detection and Exploitation of Nonstationarities in Time Series Data	Room 1
16:30 to 18:00	Welcome Wine Reception and Poster Session	No Room Required

Tuesday 14th January 2014
09:25 to 09:30	Welcome from John Toland (INI Director)	Room 1
10:30 to 11:00	Robust estimation of time-varying correlations	Room 1
11:00 to 11:30	Morning Coffee	No Room Required
11:30 to 12:15	Multiscale Change Point Inference	Room 1
12:15 to 13:30	Lunch at Wolfson Court	No Room Required
15:30 to 16:00	Afternoon Tea	No Room Required
16:30 to 17:00	Optimal Detection of a Hidden Target	Room 1

Wednesday 15th January 2014
10:30 to 11:00	Nonparametric change-point detection with sparse alternatives	Room 1
11:00 to 11:30	Morning Coffee	No Room Required
11:30 to 12:15	Modelling multivariate nonstationarity	Room 1
12:15 to 13:30	Lunch at Wolfson Court	No Room Required
15:00 to 15:30	Afternoon Tea	No Room Required
19:30 to 22:00	Conference Dinner at Cambridge Union Society hosted by Cambridge Dining Company	No Room Required

Thursday 16th January 2014
11:00 to 11:30	Morning Coffee	No Room Required
11:30 to 12:15	Constructing adaptive interference-reduced Wigner-Ville spectral estimators of non-stationary time series	Room 1
12:15 to 13:30	Lunch at Wolfson Court	No Room Required
13:30 to 14:15	Bayesian inference in continuous time jump processes	Room 1
14:15 to 15:00	An Automated Statistician which learns Bayesian nonparametric models of time series data	Room 1
15:00 to 15:30	Afternoon Tea	No Room Required
15:50 to 16:10	Inferring change points in signal levels through deterministic minimization of a generalized global functional	Room 1

Friday 17th January 2014
09:30 to 10:15	The group fused Lasso for multiple change-point detection	Room 1
11:00 to 11:30	Morning Coffee	No Room Required
12:15 to 13:30	Lunch at Wolfson Court	No Room Required

Tuesday 21st January 2014
11:30 to 12:30	Graph-Based Change-Point Detection	Room 2
14:00 to 15:00	The Volatility of International Migration Flows: Estimating Past Trends in Nordic Countries and Lessons for Forecasting with Uncertainty.	Room 2

Wednesday 22nd January 2014
11:30 to 12:30	Robust monitoring of CAPM portfolios beta	Room 2

Thursday 23rd January 2014
11:30 to 12:30	Measuring dependence with local Gaussian correlation: Theory and applications.	Room 2

Friday 24th January 2014
12:00 to 13:00	Statistical Inference for Panel Data	Room 2
14:00 to 15:00	Fourier based statistics for irregular spaced spatial data: with an application to testing for spatial stationarity.	Room 2

Monday 27th January 2014
14:00 to 15:00	Abrupt changes in the Earth's climate system: opportunities and challenges for change-point detection.	Room 1
15:10 to 16:10	Characterizing, predicting and handling rapid and large changes of wind power production.	Room 1

Tuesday 28th January 2014
11:30 to 12:30	Modeling spatial nonstationarity and inference for exceedances in environmental applications.	Room 2

Wednesday 29th January 2014
11:30 to 12:30	Incorporating Geostrophic Wind Information for Improved Space-Time Short-Term Wind Speed Forecasting and Power System Dispatch.	Room 2

Thursday 30th January 2014
11:30 to 12:30	Theory and Inference for a Class of Nonlinear Models with Application to Time Series of Counts.	Room 2

Monday 3rd February 2014
11:30 to 12:30	Detection of Genomic Signals by Resequencing	Room 2
14:00 to 15:00	Exact Bayesian inference for change point models with application to genomics	Room 2

Tuesday 4th February 2014
11:30 to 12:30	Detecting copy number variants for rare genetic disorders and non-invasive pre-natal diagnosis	Room 2
14:00 to 15:00	Wavelet-based Bayesian Estimation of Long Memory Models - an Application to fMRI Data	Room 2

Wednesday 5th February 2014
10:00 to 11:00	Methods for detecting graph based change points for fMRI and financial data	Room 2
11:30 to 12:30	Applications of Change-Points Methods in Brain Signal and Image Analysis	Room 2

Inference for change-point and related processes

Organisers

John Aston University of Warwick
Idris Eckley Lancaster University
Paul Fearnhead Lancaster University
George Sofronov Macquarie University

Inference for change-point and related processes

Programme theme

Preprints

Automatic construction and natural-language description of nonparametric regression models

On optimal multiple changepoint algorithms for large data

Change points in high dimensional settings

On some distributed disorder detection

Workshops

Inference for change-point and related processes

Seminars

Organisers

Supported By

Register for updates