Modern Statistical Toolbox for Spatial and Functional Data: Theory and Practice

July 13-17, 2026 in Amsterdam

Faculty

Yicong Lin is an Assistant Professor at the Department of Econometrics and Data Science at Vrije Universiteit Amsterdam. He obtained his Ph.D. degree from Maastricht University.

Meet the lecturer

Course

Spatial and functional data analysis has become increasingly important across environmental sciences, economics, finance, and many other fields where complex data structures are now routinely collected. Spatial data can appear in several forms: in some applications they are aggregated over regions or lattices and can be described using classical spatial models; in others they are observed continuously over space, as in air pollution or climate studies, where ideas from functional data analysis provide a natural framework. Functional data methods themselves have a wide and well-developed literature, with applications ranging from modelling curves and surfaces to analysing dynamic processes such as volatility or yield curves. While both areas are broad, this course focuses on a selection of classical models together with a few recent developments, offering an introductory yet coherent view of how these tools are used in practice.

The aim of the course is to provide participants with a rapid yet rigorous overview of both foundational concepts and recent developments in these areas. It is structured to support future research and professional practice alike, emphasizing not only how to implement advanced analytical tools but also how to understand their mathematical assumptions, scope, and limitations. The course welcomes students and researchers interested in quantitative modelling, those planning to pursue research in related fields, and participants who are simply seeking a clear and efficient entry point into spatial and functional data analysis.

Learning Objectives

By the end of the course, participants will:

• Understand the conceptual background of key spatial and functional data models, including how the estimation and inference methods are obtained and how these derivations can be adapted to more general settings.
• Gain familiarity with the mathematical theory underlying these techniques, with attention to assumptions, properties, and theoretical implications.
• Develop practical skills for implementing the models discussed in the course, including data handling, estimation, and interpretation of results.
• Acquire the foundation needed to begin reading and engaging with the research literature in spatial and functional data analysis.

Topics

• Estimation and inference for classical static spatial regression models, including foundational formulations, dependence structures, and key asymptotic results.
• Estimation and inference for advanced dynamic spatial regression models, covering dynamic spatial dependence and recent methodological developments.
• Mathematical preparation for functional data analysis, including functional data representation, estimation of functional principal components for i.i.d. samples, and functional time series.
• Classical modelling approaches for functional data, such as functional regression models.
• Recent methodological and theoretical developments in dynamic functional data, including time-dependent functional processes, dynamic functional parameters, and modern extensions.

Schedule

The summer school offers a comprehensive, full-time schedule over 5 days, with both engaging lectures and tutorials throughout the mornings and afternoons, between 9:30-17:00. This structure ensures a rich, immersive learning experience. 

A full schedule will be made available to participants closer to the start of the course. 

 Literature

• LeSage, J. P., & Pace, R. K. (2009). Introduction to Spatial Econometrics. Chapman & Hall/CRC.
• Ramsay, J. O., & Silverman, B. W. (2005). Functional Data Analysis (2nd ed.). Springer.
• Ramsay, J. O., Hooker, G., & Graves, S. (2009). Functional Data Analysis with R and MATLAB. Springer.
• Horváth, L., & Kokoszka, P. (2012). Inference for Functional Data with Applications. Springer.
• Hörmann, S., & Kokoszka, P. (2012). Functional time series. In T. S. Rao, S. S. Rao, & C. R. Rao (Eds.), Time Series Analysis: Methods and Applications (Vol. 30, pp. 157–186). Elsevier.

Level

This course is suitable for (research) master students, doctoral candidates, and postdoctoral researchers who have an interest in quantitative modelling and wish to learn the fundamentals of spatial and functional data analysis. It also welcomes professionals from research or analytical units who intend to apply these methods in their data analysis work. No prior background in spatial or functional methods is required.

Admission requirements

Participants should be proficient in at least one programming language used for statistical analysis (e.g., MATLAB, R, Python, Julia) and be ready to engage with both the mathematical aspects and the practical implementation of the methods covered in the course.