2025 Econometrics Summer School Cambridge

2025 Econometrics Summer School Cambridge

Join Prof. Jeffrey Wooldridge and Dr Melvyn Weeks in Cambridge for 5-days of interactive learning

Don't miss our in-person summer school at the University of Cambridge, hosted at the scenic and modern Churchill College, featuring courses on Difference in Differences, Machine Learning and Causal Inference

Zapisz się tutaj

Live and Learn in Scenic Cambridge

Zapisz się tutaj

Select Your Course(s):

1 050,00 GBP
Gwarancja bezpiecznej i pewnej realizacji transakcji
–
5 Days (Flexible Attendance)
Osobiście

Join us this July in Cambridge for a 5-day in-person Econometrics Summer School designed to equip researchers, analysts, and policy professionals with cutting-edge tools for causal inference and machine learning using Stata.

 

Hosted at Churchill College, the summer school brings together a community of researchers, students, and professionals from around the globe and offers a rare opportunity to study cutting-edge methods in causal inference and machine learning in one of the world’s most prestigious academic centres.

 

Participants will not only benefit from expert-led instruction and hands-on Stata sessions, but also experience life in a Cambridge college—with optional on-site accommodation available. In the evenings, participants will have the opporunity to unwind with fellow attendees over a drink or explore the vibrant university town with its winding lanes, bookshops, and riverside walks. Stay tuned for more updates on evening social activties organised for all attendees.

The programme is made up of two complementary 2.5-day courses, led by internationally renowned instructors and structured to build progressively from foundational methods to more advanced machine learning applications. Participants may choose to register on the whole school or on each course independently. The two courses have been structured to flow from one to the other, providing a seamless learning experience.

 

In addition, all participants are invited to an evening panel discussion and drinks reception on Day 3, offering an opportunity to engage in informal discussion with instructors and peers in one of the world’s most iconic academic settings.

Course Structure

Course One: An Introduction to Causal Inference and Difference-in-Differences using Stata

InstructorProfessor Jeffrey Wooldridge (University of Michigan)
Duration2.5 Days
LevelIntermediate–Advanced

This course provides a rigorous introduction to causal inference using the potential outcomes framework. You’ll explore both traditional and modern estimation techniques for treatment effects in cross-sectional and panel data settings.

 
Topics Include:

  • Regression adjustment, inverse probability weighting, and matching

  • Doubly robust methods and covariate balancing techniques

  • Local average treatment effect (LATE) and LATT estimation

  • Control function methods with heterogeneous treatment effects

  • Difference-in-differences (DiD): leads/lags, staggered adoption, parallel trends testing

  • Advanced DiD topics: clustered standard errors, few groups, rolling methods

 

Course Two: Causal Inference and Machine Learning using Stata

InstructorDr. Melvyn Weeks (University of Cambridge)
DurationDays 2.5–5
LevelAdvanced

This course explores the intersection of machine learning and causal inference, helping participants move beyond prediction-focused applications to unlock the full potential of ML in policy and economics research.

 
 Topics Include:

  • Contrasting econometrics and machine learning: Breiman’s “two cultures”

  • Ensemble methods: bagging, random forests, regularisation, averaging

  • ML for causal inference: double-robust methods, double-debiased Lasso, orthogonalisation

  • Frisch-Waugh-Lovell theorem & Lasso for treatment effect estimation

  • Parametric vs nonparametric methods in treatment effects

  • Managing high-dimensional data and sample splitting

 

New for 2025: Generative AI & Unstructured Data

  • Intro to LLMs (e.g., GPT-4, BERT)

  • Sentiment extraction from central bank speeches

  • Application to stock market response analysis

Evening Panel Discussion & Reception – Day 3

 

All attendees are invited to a panel discussion featuring both instructors, with additional guests from academia and industry. This will be followed by a drinks reception, offering a relaxed setting for networking and discussion.

What You'll Take Away
  • Confidence using Stata for exploratory analysis, data visualisation, and statistical modelling.
  • Practical experience through worked examples, take-home materials, and Q&A sessions.
  • Skills that are transferable across disciplines – while examples are health-focused, the principles apply broadly.
Learning Outcomes
  • Apply inverse probability weighting, matching, and doubly robust methods using Stata
  • Implement advanced DiD designs, including staggered treatment and dynamic effects
  • Diagnose and address violations of the parallel trend’s assumption
  • Estimate and interpret LATE and LATT in observational studies
  • Handle clustering and small-sample inference issues in applied work
Why Attend?

  • Learn directly from Jeffrey Wooldridge, one of the most cited econometricians in the world

  • Explore machine learning for causal inference with Melvyn Weeks, an expert on applied econometrics and ML

  • Gain hands-on experience with Stata

  • Develop skills applicable across academia, policy, and industry

  • Build your professional network in the unique atmosphere of Cambridge

Accomodation

Participants may choose whether to register for the school either inclusive or non-inclusive of accomodation. All accomodation is provided at Chuchill College, University of Cambridge  and all rooms are double rooms allowing single occupancy.

Accomodation is included for the evenings between course days, for example, if you book accomodation for Course 1 you will recieve a room on the nights of the 21 & 22 July only. Similarly if accomodation is booked for Course 2, you will receive a room for the nights of the 23 & 24 July only. Those who book on the whole school will receive all 4 nights.

If you require accomodation for either Sunday 20 July or Friday 25 July, please contact us, we may also be able to arrange this onsite subject to availability and additional cost.

Social Schedule and Industry Panel

Get ready to balance learning with some brilliant social events! This year’s programme isn’t just about stats and study—we’ve lined up a series of fun, relaxed, and enriching experiences to help you connect and unwind.

Midway through the course, join us for an exclusive Panel Session and Reception, where you’ll hear from leading industry voices sharing how they use the techniques you’re learning in the real world.

 

Here's what’s in store:
  • Monday 21 July 2025: Pub Quiz Night
    Kick off the week with some friendly competition at our classic British pub quiz. Test your trivia skills and get to know your fellow participants.
  • Wednesday 23 July 2025: Panel Discussion & Drinks Reception
    Hosted at the prestigious Churchill College, this evening brings together experts from industry and academia for an insightful discussion, followed by a relaxed reception—your chance to network and ask questions.
  • Thursday 24 July 2025: Punt Tour on the River Cam
    Round off the week in true Cambridge style with a scenic punt tour along the River Cam. Glide past the city’s most iconic colleges and bridges as you soak up the summer sun and charming atmosphere.

 

Course 1: An Introduction to Causal Inference and Difference - in -Differences using Stata

Overview

Instructor: Prof. Jeffrey Wooldridge, Michigan State University

Date: 21 - 23 July 2025

Duration: 2.5 Days

Level: Intermediate - Advanced

This course covers causal inference for cross-section and panel data using the potential outcomes framework. We will cover identification of key treatment effects assuming unconfoundedness, and then study various estimators: regression adjustment, inverse probability weighting, combinations thereof (to achieve double robustness), and matching methods. More recent methods using covariate balancing to obtain the propensity score also will be covered. We will then study identification of the local average treatment effect (LATE) and the local average treatment effect on the treated (LATT) and cover recent doubly robust methods for estimating these parameters when one has covariates in the instrument propensity score. Control function methods can be used to allow heterogeneity when functional forms are imposed on the conditional mean functions. 

 

We then turn to difference-in-differences methods for panel data, starting with the common timing case with possibly many periods before and after the intervention. We will focus initially on regression-based methods, studying both “lags only” and “leads and lags” models. 

 

For the general staggered intervention case, we will discuss how to allow full heterogeneity in treatment effects by treatment cohort and calendar time. Various estimators turn out to be equivalent, including an extended version of two-way fixed effects. Covariates are easily incorporated. Testing and adjusting for violation of parallel trends in the staggered case will be covered. Rolling methods and long differencing, where one can apply standard treatment effects, will also be covered. 

 

Additional special topics include allowing for exit from treatment, clustering standard errors, and inference when there are few control or treated groups. 

 

Participants should have good working knowledge of ordinary least squares estimation, fixed effects estimation, and basic nonlinear models such as logit, probit, and exponential conditional means. Sufficient background is provided by my introductory econometrics book, Introductory Econometrics: A Modern Approach, 7e, Cengage, 2020. My book Econometric Analysis of Cross Section and Panel Data, 2e, MIT Press, 2010, covers the background material at a higher level. 

 

Some of the material is based on my recent working papers, “Two-Way Fixed Effects, the Two-Way Mundlak Regression, and Difference-in-Differences Estimators,” and my Econometrics Journal paper, “Simple Approaches to Nonlinear Difference-in-Differences.” Some of the recent material on doubly robust and matching estimators is in the paper “A Simple Transformation Approach to Difference-in-Differences Estimation for Panel Data” (with Soo Jeong Lee). 

Day 1 - 21 July 2025

Session 1: 9:00-10:30 

Potential outcomes and parameters of interest. Randomization. Unconfoundedness and overlap. Identification. Regression adjustment. 

Break: 10:30-10:45 

Session 2: 10:45-12:15 

Inverse probability weighting, normalized weights. Covariate balancing propensity score estimation. Matching and doubly robust estimators. Improved efficiency under randomized controlled trials. 

Lunch: 12:15-13:30 

Session 3: 13:30-15:00 

Potential treatment status. Constant effect model. Compliers and defiers. One-sided non-compliance. Identification of LATE and LATT. Including covariates for LATE and LATT estimation. 

Break: 15:00-15:15 

Practical: 15:15-17:00 

Q&A: 17:00-17:30 

Day 2 - 22 July 2025

Session 4: 9:00-10:30 

Control function methods. Regression discontinuity (time permitting). 

Break: 10:30-10:45 

Session 5: 10:45-12:15 

Difference-in-Differences with Common Timing. Parameters, no anticipation, parallel trends. 

Lunch: 12:15-13:30 

Session 6: 13:30-15:00 

Difference-in-Differences with Staggered Interventions. No anticipation, parallel trends. Imputation and flexible regression-based methods. All units eventually treated. 

Break: 15:00-15:15 

Practical: 15:15-17:00 

Q&A: 17:00-17:30 

Day 3 - 23 July 2025

Session 7: 9:00-10:30 

Event study methods with staggered interventions. Heterogeneous trends. Testing no anticipation. 

Break: 10:30-10:45 

Session 8: 10:45-12:15 

Small number of treated units. Synthetic control and synthetic difference-in-differences. 

 

Course 2: Causal Inference and Machine Learning using Stata

Overview

Instructor: Dr. Melvyn Weeks, University of Cambridge

Date: 23 - 25 July 2025

Duration: 2.5 Days

Level: Advanced

The course will focus upon topics at the intersection of machine learning and econometrics, covering a mix of theory and applications. In making the distinction between models which are used to solve a prediction problem and models which are used to estimate some form of causal effect, we demonstrate how empirical strategies such as unconfoundedness, instrumental variables, and difference-in-difference can be used alongsidemachine learning methods for prediction.

Using Breiman’s (2001) notion of two cultures in the use of statistical modelling, the course begins with a review of the fundamental differences between machine learning and econometrics. 

In this context we contrast a modelling approach where the analyst makes certain assumption on model specification, including functional form, with an approach where the data mechanism is presumed unknown. In this context we consider the econometrician’s concern for internal validity, alongside the focus within machine learning of ensuring that a model is robust in the sense of generalising to unseen data (external validity).

According to Splunk’s latest report, The Economic Impact of Data Innovation 2023, 67% of data innovation leaders strongly agree that their data is growing faster than they can keep up. However, there can also be a problem of “too much data”. ml models use big data to learn and improve predictability and performance automatically through experience and data. Participants will be introduced to the use of ensemble methods such as simple averaging and other regularization devices, that are able to manage the problems associated with having too much data.

In this context we will explore a number of general methods for model averaging including bootstrap sampling (so-called bagging) and random forests.

Day 3 - 23 July 2025

Session 1: 13:30-15:00 

Introduction, Machine Learning: The Vernacular, Causal Inference in Low Dimensions

Break: 15:00-15:15 

Session 2: 15:15-17:00 

The Best Predictor and The Conditional Expectation Function, Linear Regression, Nonlinear in Variables, Departing From The Linear cef: Wages and Education

Day 4 - 24 July 2025

Session 3: 9:00-10:30 

Prediction, Estimation and Attribution, Prediction Policy Problems, Beyond Prediction and Attribution: Causal Effects, Estimation and Inference for Causal Effects, An Introduction to Treatment Effect Model, Anticipating Heterogeneous Causal Effects, Weak Instruments in Nonparametric Settings, Binary Response and Endogeneity

Break: 10:30-10:45 

Session 4: 10:45-12:15 

High-Dimensional Methods for Linear Models, Least absolute Shrinkage and Selection

Lunch: 12:15-13:30 

Session 5: 13:30-15:00 

Applications of Regularised Regression for Linear Models

Break: 15:00-15:15 

Session 6: 15:15-17:00 

Double Machine Learning, The Partial Linear Model (plm), Regularisation Bias Revisited, Orthogonalisation and Sample Fitting, A Decomposition of Bias, Variations on the plm, Stata Practical: The Impact of Institutions on Growth

Q&A: 17:00-17:30 

Day 5 - 25 July 2025

Session 7: 9:00-10:30 

Treatment Effects: ate and cate, Identification Strategies, Estimators, Regression Adjustment, Inverse propensity score weighting, AIPW and Double Robust Estimators, Double Robust Estimators Meet Machine Learning

Break: 10:30-10:45 

Session 8: 10:45-12:15 

Random Forests, Machine Learning and Decision Trees, Machine Learning for Prediction

Lunch: 12:15-13:30 

Session 9: 13:30-15:00 

The Architecture of Causal Trees and Generalised Random Forests, Why not use Off-the Shelf Methods for Prediction? From Random to Causal Forests, Infeasible MSE, Sample Splitting, Honest Estimation, From Hard Partitioning to Forest-Based Weights, Generalised Random Forests

Break: 15:00-15:15 

Session 10: 15:15-17:00 

Testing for Heterogenous Treatment Effects

Q&A: 17:00-17:30 

Time permitting there will also be an Introduction to Generative AI and Large Language Models

 

Course Timetable

Subject to minor changes

Session

Time

First Session

9am-10:30am (UK time)

Break

10:30am-10:45am (UK time)

Second Session

10:45am-12:15pm (UK time)

Lunch

12:15pm-1:30pm (UK time)

Third Session

1:30pm-3:00pm (UK time)

Break

3:00pm-3:15pm (UK time)

Fourth Session

3:15pm-5pm (UK time)

Q&A

From 5:00pm (UK time)

 

Subject to minor changes

First Session

Break

Second Session

9am-10:30am (London time)

10:30am-11am(London time)

11am-12:30am (London time)

10am-12pm (London time)

2pm-4pm (London time)

4pm-4:30pm (London time)

 

Terms

  • Student registrations: Attendees must provide proof of full time student status at the time of booking to qualify for student registration rate (valid student ID card or authorised letter of enrolment).
  • Additional discounts are available for multiple registrations.
  • Delegates are provided with temporary licences for the principal software package(s) used in the delivery of the course. It is essential that these temporary training licenses are installed on your computers prior to the start of the course.
  • Payment of course fees required prior to the course start date.

 

Cancellations

  • 100% fee returned for cancellations made over 28-calendar days prior to start of the course.
  • 50% fee returned for cancellations made 14-calendar days prior to the start of the course.
  • No fee returned for cancellations made less than 14-calendar days prior to the start of the course.

The number of attendees is restricted. Please register early to guarantee your place.

Thinking of joining us in Cambridge this summer?
Get a head start with a free pre-course webinar hosted by Jeffrey Wooldridge.

We’re offering a complimentary online session ahead of the Econometrics Summer School in Cambridge to introduce key themes that will be explored in depth during the programme.

 

Date: 3 June 2025
Time: 14:00–16:00 BST
Format: Live Online via Zoom
Speaker: Professor Jeffrey Wooldridge

What to Expect:

This two-hour webinar provides a concise review of the method of Ordinary Least Squares (OLS) for cross-sectional data—still the foundational tool in modern econometrics, even in more complex causal inference settings.

 

Professor Wooldridge will present a contemporary perspective on OLS, asking a critical question: What can we learn when our model is only an approximation? He will cover:

  • Motivation for OLS and its Real-World Applicability

  • Conditional Expectations and Linear Projections

  • Statistical Properties of OLS

  • Practical Challenges in Applying OLS

 

Additional discussion will include functional form issues, interpreting partial effects when they vary, and addressing common sources of confusion such as multicollinearity.

 

Register below to reserve your spot – it’s free!

 

Delivered By

Student Testimonials

Giovanni's delivery is fantastic; makes great connections between new and prior knowledge and focuses on the key strengths and limitations of the discussed methods. Excellent course design that builds on the Introductory Machine Learning course and knowledge acquired in the PhD Econometrics sequences of courses. This is all nicely supplemented by detailed Stata code with explanations and sample datasets. 

Excellent course and great explanations on ML techniques and applications from Giovanni ! I leanred so much including the coding and applications plus the fundamentals of ML.

The 'Advanced Machine Learning (AML)' experience was excellent for trying to gain more experience in Statistics using links Python and STATA.  

I'm not a Statistician! However, Giovanni managed to link the 'Fundamentals of Machine Learning (FML) ' to 'Advanced Machine Learning' in his usual excellent way. When starting the AML, for me I am pleased that the FML was a tremendous help and allowed me to use my mathematical knowledge for Physics and Science. I'm looking forward to Giovanni's next course (using large datasets) and his book.

Linking my knowledge of mathematics (from Science and Engineering) to Statistics. I do hope it is leading towards becoming better at 'Medical Statistics' that require very large datasets...and a big thank you to Giovanni!

Very well organized, very useful and relevant content, looking forward to joining future events!

As always great service and real good courses. In addition, thanks to Professor Cerulli for making himself understood in the best way.

The delivery of this course was exceptionally well done. It really helped me to appreciate the concepts as well as the practical applications in Stata. If you are new to this topic, this will provide a good introduction to complex issues.

Very easy to communicate, all emails contained all the information necessary. I think that the course was very well structured and organized. The tutor provided a number of codes that were extremely helpful for understanding. Overall, very useful and easy to follow!

I highly appreciated Professor Giovannu Cerulli course. The classes notes are very clear   and well prepared with an extensive coverage of the course subjects. And they are simultanesouly quite objective by focusing on the most important contents. Professor Giovannu Cerulli lectures are very didatic which greately helps the easily assimilation of the   corespondent knowledge. Furthermore, the course materials are quite   comprehensive and they englobe not only the classes notes, but also the referenced papers as well as data and Stata programs to estimate the models in this software. All in all, I greatly recommend this   course, as it really amazingly speeds up the acquaintance of the underlying theory and appied aplication in a very short period of time.

I found the Stata Summer School 2021 very useful and interesting. The course was perfectly structured and organised, with a good progression during the week. The instructors presented the topics covered in an easy and understandable way. There were room for questions and answers when needed. Materials shared for the course were tidy and informative, and I am sure I will use them frequently. This course was arranged online, which in my opinion worked very well. I believe the course delivered as promised and according to information found online when I signed up for the course. Easy to purchase/sign up for the course. User friendly. Quick and timely response.

Very efficient in terms of communication and delivery. Provides a very comprehesnive applied knowledge of stata. I would definitely recommend others to buy from them.

I went UK University of Cambridge for a summer school with Timberlake, it was excellent.

It was a great course and I thoroughly enjoyed it. Many of my fellow participants were eager to share their ideas. I thought the course could help further many people in a similar stage to my career!