Skip navigation, view page content

The Ohio State University

www.osu.edu

  1. Help
  2. Campus map
  3. Find people
  4. Webmail


Yoonkyung Lee Teaching

Autumn 2018

  • STAT 6560 Applied Multivariate Analysis

Spring 2018

  • STAT 7620 Elements of Statistical Learning:

    Statistical learning or machine learning methodology explores various ways of estimating functional dependencies between a response variable and possibly a large set of explanatory variables (features), when one is trying to find and understand an unknown, regular component within the realm of noisy, complex data. Modern regression and pattern recognition analyses fall in this framework.This course will provide an overview of supervised learning and discussions of statistical learning algorithms such as Discriminant Analysis, Classification Tree, Support Vector Machines, and Boosting, and illustrate practical uses of the algorithms.

  • STAT 3202 Introduction to Statistical Inference for Data Analytics

Courses taught previously

  • STAT 7630 Nonparametric Function Estimation:

    This course aims to introduce a nonparametric function estimation method with roughness penalties. Starting from smoothing splines for univariate data, a unified framework for penalized likelihood approach will be developed for flexible model building with splines covering multivariate data with both Gaussian and non-Gaussian responses. Mathematical formulation of smoothing splines, reproducing kernel Hilbert space methods, selection of a smoothing parameter, computation, and their applications will be treated in detail. In addition, connection between spline models and kernel methods in machine learning (especially support vector machines) will be discussed.

  • STAT 5302 Intermediate Data Analysis II

  • STAT 5301 Intermediate Data Analysis I

  • STAT 4201 Introduction to Mathematical Statistics I

  • STAT 881 Advanced Statistical Learning:

    This course provides an introduction to statistical learning theory. It focuses on formulation of prediction problems, in particular, classification in a probabilistic framework and how to estimate and analyze the performance of statistical and computational learning methods. Concepts and techniques for the theoretical analysis of such methods will be developed. Topics include notion of consistency, concentration inequalities, uniform convergence, empirical risk minimization, convex optimization, and general treatment of kernel methods and boosting among others.

  • STAT 882 Topics in Variable Selection and Model Selection

  • STAT 621 Statistical Theory II

  • STAT 428 Introduction to Probability and Statistics for Engineering and the Sciences