Upcoming event

Data Analysis Workshop 2018

The ICIC will run a Data Analysis Workshop, funded by STFC and Winton Capital, from 3rd (afternoon) - 6th September 2018.

Registration

Registration is now CLOSED, due to high demand.  Apologies to those to whom we have been unable to offer a place.

Registration form ICIC Data Analysis Workshop 2018 (Word) for return to fundamental@imperial.ac.uk.

Course details and downloadable course materials

Course details and downloadable course materials for each year of the Data Analysis Workshops can be found by clicking on the expandable boxes below:

Course details and downloadable course materials for each year of the Data Analysis Workshops

Workshop September 2018

ICIC Data Analysis Workshop, September 3-6 2018

Principled statistical methods for researchers 
Venue: Imperial Centre for Inference and Cosmology (ICIC), Imperial College, South Kensington, London.  
Dates: Starts: 2 p.m. 3 September 2016. Ends: 4 p.m. 6 September 2016. 

NEWS: VENUE DIFFERENT ON THURSDAY

On Thursday, the school will be in the Royal School of Mines, Lecture Theatre 1.31.  Entrance on Prince Consort Road (turn left out of Beit Hall).

PROGRAMME

This is the current version of the Workshop Programme.   Please check back from time-to-time, as it may evolve.

Registration 

Registration is now CLOSED due to high demand.  

Registration form ICIC Data Analysis Workshop 2018 (Word).

Please contact Paula Consiglio or Dion Kordopati for adminstrative matters, at  fundamental-physics-admin@imperial.ac.uk

Lecturers and Demonstrators

  • Prof Alan Heavens (ICIC Physics)
  • Prof Andrew Jaffe (ICIC Physics)
  • Dr Daniel Mortlock (ICIC Physics and Mathematics)
  • Dr Jonathan Pritchard (ICIC Physics)
  • Dr Elena Sellentin (University of Leiden)
  • Dr Roberto Trotta (ICIC Physics)

Code of conduct

The meeting has a Code of Conduct. By registering at the beginning of the workshop, you are agreeing to abide by it.


Summary

We will run a 4-day course/workshop on statistical methods and tools for data analysis, aimed at PhD students, postdocs and any researchers interested in understanding Bayesian statistics and numerical techniques of data analysis. The course plan is to combine lectures with hands-on computational work in the afternoons. It will concentrate on setting down firm foundations of principled Bayesian data analysis, but a feature of the workshop will be a substantial element of hands-on classes where participants will learn how to apply the ideas in practice. It will be hosted by the Imperial Centre for Inference and Cosmology (ICIC) at Imperial College. 

Background

Most researchers will at some point be required to perform some form of data analysis.  This may be anything from simple line-fitting, through parameter estimation, to complex and computationally-demanding sampling for model selection on large datasets. Anecdotal evidence suggests that many researchers are not well prepared for this, often doing the right thing incorrectly, or picking up an inappropriate statistical tool.   The purpose of this course is to provide understanding of principled data analysis, and experience of applying appropriate methods to data.

Preparation

We expect all participants to bring their own laptop, and to do a simple computational exercise in advance (in whatever language suits) to ensure they have appropriate software in place before the workshop starts.   

Costs

The workshop has sponsorship from STFC's Education, Training and Careers Committee, and also a generous donation from Winton Capital.  

STFC-funded students will have accommodation, meals, refreshments and social activities paid for, and can also claim travel from STFC.  Other participants may need to pay accommodation costs and a modest course fee - see the registration page for more details of eligibility for cost reductions.

Accommodation

We have reserved rooms in Imperial College Student Accommodation, within easy walking distance of the workshop.

SOCIAL EVENTS
We will have a reception on Monday evening, and a barbecue on Tuesday evening, after a short talk from Dr Geraint Harker, VP Research at Winton, and former Astronomer, on using statistical methods in finance. Wednesday evening will be free to allow participants to explore London. 

Learning outcomes

At the end of the Workshop, the participants should be able to (non-exhaustive list):

  • Express stochastic problems in terms of fundamental probability and Bayes’ theorem.
  • Demonstrate by application to real data understanding of probability, inference, priors, posteriors, marginalisation, parameter estimation, hypothesis testing, model selection, sampling.
  • Code and apply a simple MCMC program to physical data.
  • Formulate model selection problems in a principled statistical framework, and be capable of executing some methods of solution.

Course team

Prof Alan Heavens, Prof Andrew Jaffe, Dr Jonathan Pritchard, Dr Daniel Mortlock (ICIC Physics and Mathematics; University of Stockholm), Dr Elena Sellentin (University of Leiden), Dr Roberto Trotta (ICIC Physics)

Point of contact: Professor Alan Heavens, Director, Imperial Centre for Inference and Cosmology, Blackett Laboratory, Prince Consort Road, London SW7 2AZ. Email a.heavens@imperial.ac.uk Tel. 0207 594 2930, or Paula Consiglio or Dion Kordopati for adminstrative matters, at  fundamental-physics-admin@imperial.ac.uk or 0207 594 7824.

Practical info

Travel

The Huxley Building is very close to the Royal Albert Hall in South Kensington.  You enter Huxley (No. 13 on the map) from the Queen's Gate road side.  Nearest tube stops are South Kensington and Gloucester Road (10 mins walk), and there are buses which pass close by - see the map and the TfL website for details ( http://www.tfl.gov.uk/ ).  You may find the Journey Planner facility useful.  Note that it is worth buying a pay-as-you-go Oyster card if you are going to use the system at all - the fares are much cheaper than buying individual tickets. You can also use a UK contactless payment card (and some others), which has the same fares as Oyster.

From South Kensington Underground station: if it's raining, when you come through the barriers, you can turn right below ground and take the long tunnel from the station, which emerges pretty much at the bottom of the main map (attached).  Otherwise, it's preferable to go straight ahead and head up for the daylight, exit to street level immediately, turning right to get into Thurloe St (this is mostly pedestrianised now) - it's a more pleasant walk above ground past the museums.

Travel claims (UKRI STFC-funded students)

STFC Claim Form for UKRI STFC-funded students, covering travel and meals not provided by the workshop, should be filled in, signed (no electronic signatures), scanned and sent with scanned receipts to Susan Blackwell, at studentships@stfc.ukri.org 

HANDOUTS

Preliminary Exercise:

Please do this:  Preliminary exercise (pdf)‌ BEFORE the workshop!‌  

Supernova data file: jla_mub‌  Covariance matrix (not needed for prelimary exercise): jla_mub_covmatrix

DAY 1

Introduction, map and social programme

Lecture notes (Alan): Introduction to Bayes

Lecture notes (Elena): Distributions and Marginalisation

Day 1 Exercises‌ and Solutions to Day 1 exercises

DAY 2

Lecture notes (Daniel): Sampling

Case study notes (Alex Geringer-Sameth): Poisson counts in a background

Eddington 1919 eclipse problem: Eddington 1919 eclipse

Supernova cosmology problem: Supernova Hubble Diagram

DAY 3

Lecture notes (Andrew): HMC and Gibbs sampling

Python notebook: Andrew's python and Stan code (zip file)

Lecture notes (Elena): Convergence tests

Lecture notes (Alan): Bayesian Hierarchical Models (with more detail)

Model comparison exercises (Roberto): Model comparison exercises

DAY 4

Lecture notes from Thursday and Friday (Roberto): Model Comparison

Lecture notes (Elena): Bayesian vs Frequentist

2016

ICIC Data Analysis Workshop, September 5-8 2016

Principled statistical methods for researchers 
Venue: Imperial Centre for Inference and Cosmology (ICIC), Imperial College, South Kensington, London.  
Dates: Starts: 2 p.m. 5 September 2016. Ends: 4 p.m. 8 September 2016. 

Registration 

Registration is now closed. Please contact Louise Hayward for adminstrative matters l.hayward@imperial.ac.uk.

Lecturers and Demonstrators

  • Prof Alan Heavens (ICIC Physics)
  • Prof Andrew Jaffe (ICIC Physics)
  • Dr Daniel Mortlock (ICIC Physics and Mathematics)
  • Dr Jonathan Pritchard (ICIC Physics)
  • Dr Elena Sellentin (University of Geneva and ICIC Physics)

List of Participants 

A list of registered participants will be available later.

Code of conduct

The meeting has a code of conduct: Meeting Code of Conduct

STFC claim form

For STFC- and self-funded students, travel and extra subsistence can be claimed using STFC Claim form. Rerturn to Studentships, STFC, Polaris House, North Star Avenue, Swindon SN2 1SZ


Handouts

Preliminary Exercise:

Please do this BEFORE the workshop!

Instructions and background: Preliminary Exercise 2016

Supernova data file: jla_mub

Covariance matrix: jla_mub_covmatrix

Workshop handouts:

  • Day 4 - Roberto Trotta: Public Engagement Lunch PE Lunch RT

Python code

Alan's python 3 code for the 2-parameter case: SN code Python

Inverse covariance matrix: Inverse covariance

Updated programme: ICIC 2016 Programme


Summary

We will run a 4-day course/workshop on statistical methods and tools for data analysis, aimed at PhD students, postdocs and any researchers interested in understanding Bayesian statistics and numerical techniques of data analysis. The course plan is to combine lectures with hands-on computational work in the afternoons. It will concentrate on setting down firm foundations of principled Bayesian data analysis, but a feature of the workshop will be a substantial element of hands-on classes where participants will learn how to apply the ideas in practice. It will be hosted by the Imperial Centre for Inference and Cosmology (ICIC) at Imperial College. 

Background

Most researchers will at some point be required to perform some form of data analysis.  This may be anything from simple line-fitting, through parameter estimation, to complex and computationally-demanding sampling for model selection on large datasets. Anecdotal evidence suggests that many researchers are not well prepared for this, often doing the right thing incorrectly, or picking up an inappropriate statistical tool.   The purpose of this course is to provide understanding of principled data analysis, and experience of applying appropriate methods to data.

Preparation

We expect all participants to bring their own laptop, and to do a simple computational exercise in advance (in whatever language suits) to ensure they have appropriate software in place before the workshop starts.   

Costs

The workshop has sponsorship from STFC's Education, Training and Careers Committee, and also a generous donation from Winton Capital.  

STFC-funded students will have accommodation, meals, refreshments and social activities paid for, and can also claim travel from STFC.  Other participants may need to pay accommodation costs and a £75 course fee - see the registration page for more details of eligibility for cost reductions.

Accommodation

We have reserved rooms in Imperial College Student Accommodation, in Beit Hall, within easy walking distance of the workshop.

SOCIAL EVENTS
There will be a drinks reception on the roof terrace on Monday evening, and a barbecue at Princes Gate on Wednesday.  Tuesday evening will be free to allow participants to explore London. 

Provisional Programme

Day 1 (Monday 5 September 2016). Clore Lecture Theatre, Huxley Building

  • From 1.30 p.m. Registration.
  • Start of Workshop 2 p.m.
  • Bayesian Foundations: 
  • What is probability?
  • The Laws of Probability and Bayes’ Theorem
  • Priors
  • Parameter inference
  • Marginalization
  • Confidence intervals, credibility intervals
  • Problem class: Simple problems
  • Tutorial: day summary
  • Talk by Dr Geraint Harker (Winton Capital and UCL Astrophysics)
  • End: 5.30 p.m.
  • Drinks reception. Roof Terrace, Level 8, Blackett Lab. 

Day 2 (Tues 6 September 2016).  Skempton Building Lecture Theatre 201

  • Bayesian Computation: Parameter Estimation and Sampling
  • Grid-based methods
  • Markov Chain Monte Carlo
  • Metropolis-Hastings algorithm
  • Convergence tests – Rubin-Gelman
  • Hands on: MCMC code from scratch.  Cosmology from the Supernova Hubble Diagram.
  • Day summary
  • End: 5 p.m.
  • Evening: free

Day 3 (Weds 7 September 2016) Clore Lecture Theatre, Huxley Building

  • Gibbs Sampling
  • Hamiltonian Monte Carlo
  • Day summary
  • End: 5 p.m.
  • 6 p.m. Workshop Barbecue. 58 Princes Gate.

Day 4 (Thurs 8 September 2016) Clore Lecture Theatre, Huxley Building

  • Why not p-values and reduced chisquared?
  • Model Comparison with Bayesian Evidence
  • Hands on: Bayesian evidence: the Savage-Dickey Density Ratio
  • Bayesian Hierarchical Models
  • Workshop summary
  • 4 p.m. End of Workshop

Learning outcomes

At the end of the Workshop, the participants should be able to (non-exhaustive list):

  • Express stochastic problems in terms of fundamental probability and Bayes’ theorem.
  • Demonstrate by application to real data understanding of probability, inference, priors, posteriors, marginalisation, parameter estimation, hypothesis testing, model selection, sampling.
  • Code and apply a simple MCMC program to physical data.
  • Formulate model selection problems in a principled statistical framework, and be capable of executing some methods of solution.

Course team

Prof Alan Heavens, Prof Andrew Jaffe, Dr Jonathan Pritchard, Dr Daniel Mortlock (ICIC Physics and Mathematics), Dr Elena Sellentin (University of Geneva/ICIC Physics)

Point of contact: Professor Alan Heavens, Director, Imperial Centre for Inference and Cosmology, Blackett Laboratory, Prince Consort Road, London SW7 2AZ. Email a.heavens@imperial.ac.uk Tel. 0207 594 2930, or Louise Hayward (l.hayward@imperial.ac.uk) 0207 594 7679.

Practical info

Travel

The Huxley Building is very close to the Royal Albert Hall in South Kensington.  You enter Huxley (No. 13 on the map) from the Queen's Gate road side.  Nearest tube stops are South Kensington and Gloucester Road (10 mins walk), and there are buses which pass close by - see the map and the TfL website for details ( http://www.tfl.gov.uk/ ).  You may find the Journey Planner facility useful.  Note that it is worth buying a pay-as-you-go Oyster card if you are going to use the system at all - the fares are much cheaper than buying individual tickets. You can also use a (UK only) contactless payment card, which has the same fares as Oyster.

From South Kensington Underground station: if it's raining, when you come through the barriers, you can turn right below ground and take the long tunnel from the station, which emerges pretty much at the bottom of the main map (attached).  Otherwise, it's preferable to go straight ahead and head up for the daylight, exit to street level immediately, turning right to get into Thurloe St (this is mostly pedestrianised now) - it's a more pleasant walk above ground past the museums.

2014

ICIC Data Analysis Workshop 2014

Preparatory Exercise is Preliminary Exercise 2014

Supernova data file is SN

Lectures

Monday

Tuesday

Thursday

PROBLEM SHEETS and COMPUTATIONAL exercises

Day 1 problems: Hands on Day 1 Problems and solutions: Hands on Day 1 Solutions

Day 2 problems: Sampling Problems and solutions (Sampling Solutions / Sampling Solutions.ipynb)

Day 2-4 computations: SN MCMC project

Gelman-Rubin formula: Gelman Rubin from SAS STAT Users Guide

DATA

(for Importance Sampling advanced exercise).
Planck chains are available here.

Choose one of the sets of 'key chains'.  You will get a zip file with a set of MCMC chains.  There is also a file telling you which order the parameters are in "...paramnames".  You may need to compute Omega_m from Omega_m=Omega_b+Omega_c, and the parameters include Omega_b h^2 and Omega_c h^2, so you need to find the column with h in it as well.

2013

ICIC Data Analysis Workshop, September 11-13 2013

Principled statistical methods for researchers

Venue: Imperial Centre for Inference and Cosmology (ICIC), Imperial College, South Kensington, London.  Workshop in Huxley Building, Room 311.
Dates:  11-13 September 2013

Lecturers

Prof Alan Heavens (ICIC Physics)
Prof Andrew Jaffe (ICIC Physics)
Dr Roberto Trotta (ICIC Physics)
Dr Daniel Mortlock (ICIC Physics and Mathematics).

Lecture Handouts:

Alan Heavens:
Presentation:  ICIC Data Analysis lectures
Case study: Population Mean

Andrew Jaffe:
Presentation 1: Probability: more examples and concepts
Presentation 2: CMB Case Study

Daniel Mortlock:
Presentation 1: Parameter estimation
Presentation 2: Hypothesis tests

Roberto Trotta:
Summary notes day 3
Slides day 3

Hands-On Handouts:

Day 0:
Preliminary Exercise
Data: SN

Day 1:
Problems Day 1
Solutions Day 1

Day 2:
SN MCMC Project

For general Universes:
Here LumDistRows is a file with DL*(z) for different pairs of Om, Ov (matter, vacuum energy)
Schematically:
for Om=0 to 1 in steps of 0.01 (101 points)
for Ov=0 to 1 in steps of 0.01
A line of DL(z) for z=0 to 1.8 in steps of 1.8 (181 points), separated by spaces
end
end

Day 3:
Model comparison exercises


This event took place in 2013

Latest news

We will have a wine reception on Wednesday after the afternoon session.  Details at the workshop.

Otherwise each day will finish at 5 p.m.

Summary

We will run a 3-day course/workshop on statistical methods and tools for data analysis, aimed at PhD students, postdocs and any staff interested in understanding Bayesian statistics and numerical techniques of data analysis.  The course plan is to combine morning lectures with problem sets and practical work in the afternoons. It will concentrate on setting down firm foundations of principled data analysis, but a feature of the workshop will be a substantial element of hands-on classes where participants will learn how to apply the ideas in practice.  It will be hosted by the Imperial Centre for Inference and Cosmology at Imperial College.

Background

Most researchers will at some point be required to perform some form of data analysis.  This may be anything from simple line-fitting, through parameter estimation, to complex and computationally-demanding sampling for model selection on large datasets. Anecdotal evidence suggests that many researchers are not well prepared for this, often doing the right thing incorrectly, or picking up an inappropriate statistical tool.   The purpose of this course is to provide understanding of principled data analysis, and experience of applying appropriate methods to data.

Preparation

We expect all participants to bring their own laptop, and to do a simple computational exercise in advance (in whatever language suits) to ensure they have appropriate software in place before the workshop starts. The instructions are here: Preliminary Exercise. The data file of supernovae is here: SN

Costs

There will be a small registration fee of £20 to cover refreshments. Participants will be responsible for all other travel and subsistence costs.  Inexpensive lunch is readily available on campus.

Registration

This event took place in 2013. Registration is now closed.

Draft programme

Day 1  (Weds 11 September 2013)

  • 9.15 a.m. Registration, coffee and pastries. 311 Huxley Building
  • Start of Workshop 9.45 a.m.
  • Bayesian Foundations:
  • What is probability?
  • The Laws of Probability and Bayes’ Theorem
  • Priors
  • Parameter inference
  • Marginalization
  • Confidence intervals, credibility intervals
  • Problem class: Simple problems
  • Tutorial: day summary
  • End: 5 p.m.

Day 2 (Thurs 12 September 2013)

  • Bayesian Computation: Parameter Estimation and Sampling
    • Grid-based methods
    • Markov Chain Monte Carlo
    • Metropolis-Hastings algorithm
    • Convergence tests – Rubin-Gelman
    • Gibbs Sampling
    • Hamiltonian Monte Carlo
    • Case Study: Cosmic Microwave Background
    • Hands on: MCMC code from scratch.  Cosmology from the Supernova Hubble Diagram.
    • Tutorial: day summary
    • End: 5 p.m.

Day 3 (Fri 13 September 2013)

  • Why not p-values and reduced chisquared?
  • Model Comparison with Bayesian Evidence
  • Case study: is the Universe flat?
  • Hands on: model comparison calculations and computations &/or complete MCMC codes.
  • Tutorial: wrap up the workshop
  • 5 p.m. End of Workshop

Learning outcomes

At the end of the Workshop, the participants should be able to (non-exhaustive list):

  • Express stochastic problems in terms of fundamental probability and Bayes’ theorem.
  • Demonstrate by application to real data understanding of probability, inference, priors, posteriors, marginalisation, parameter estimation, hypothesis testing, model selection, sampling.
  • Code and apply a simple MCMC program to physical data.
  • Formulate model selection problems in a principled statistical framework, and be capable of executing some methods of solution.

Course team

Prof Alan Heavens, Prof Andrew Jaffe, Dr Roberto Trotta (ICIC Physics); Dr Daniel Mortlock (ICIC Physics and Mathematics).

Point of contact: Professor Alan Heavens, Director, Imperial Centre for Inference and Cosmology, Blackett Laboratory, Prince Consort Road, London SW7 2AZ. Email a.heavens@imperial.ac.uk Tel. 0207 594 2930, or Rachel Groom (r.groom@imperial.ac.uk) 0207 594 7770.