Master's degree in Statistics and Operations Research

Share:

Introduction to Functional Data Analysis with R - July 5th to July 9th

Date:

July 5th to July 9th. Afternoon from 3.00 to 6.00 pm.

Classroom:

005

Modality:

Face-to -Face  or Streaming

Instructor

Pedro Delicado

Pedro Delicado is full professor of Statistics at the Universitat Politècnica de Catalunya Barcelona-TECH. His research activity has been mainly devoted to Functional Data Analisys (focusing on dimensionality reduction and spatial dependence), but in recent years he is interested in exploring links between Statistics and Machine Learning, with particular interest in predictive models interpretability.

Language

Castellano

Description

Functional data arise when one of the variables of interest in a data set can be seen naturally as a smooth curve or function. Functional Data Analysis (FDA) can then be thought of as the statistical analysis of samples of curves. In the last two decades, FDA techniques have evolved rapidly, which has allowed the FDA to reach a remarkable methodological maturity. Many standard statistical methods have been adapted to functional data: regression models (lm, glm, non-parametric regression, ...), multivariate analysis (PCA, MDS, Clustering, Depth measures, ...), time series, spatial statistics, among other. At the same time, its methods have been applied in medicine, business, engineering, demography and social sciences, etc. This course offers an introduction to FDA and presents some of the R libraries oriented to this type of data.

Course goals

The aim is that at the end of the course the students are able to identify situations in which they can treat their data as functional, to represent them computationally, to apply simple FDA techniques (descriptions, dimensionality reduction, regression) and to visualize the results.

Course contents

  1. Introduction to Functional Data Analysis (FDA). An overview.
  2. Observed functional data and its computational representation.
    1. Developments in bases of functions.
    2. Smoothing: Kernel, Local Polynomials, Splines.
  3. Exploratory analysis of functional data.
    1. Location and dispersion statistics.
    2. Depth measurements.
    3. Outliers detection.
  4. Dimensionality reduction.
    1. Functional Principal Components.
    2. Multidimensional Scaling.
  5. Regression with functional data.
    1. Scalar response and functional regressor.
    2. Functional response.
  6. FDA in Demography.

Prerequisites

Knowledge about Multivariate Analysis (Principal Component Analysis, Multidimensional Scaling), smoothing techniques and regression methods (linear model and GLM) is convenient, but not strictly required.

Targeted at

  • MESIO UPC-UB students.
  • Professionals of data analysis interested in learning how to deal with functional data.

Evaluation

A small applied project based on real functional data analysis.

Computer class or student's laptop?

Student's laptop

Software requirements