Scribd Logo
Upload

Welcome to Scribd!

  • 1K views

    Regression Analysis - ISYE 6414

    Uploaded by

    Yasin Çagatay Gültekin
    This document outlines the syllabus for a graduate level regression analysis course. It provides information on the instructor, class schedule, required textbooks, course objectives, activities, evaluations, and topics to be covered. The course will introduce students to simple and multiple linear regression, variance-bias decomposition, variable selection, logistic regression, generalized linear models, and nonparametric regression methods. Students will complete assignments, two midterm exams, and a final project applying regression analysis to real-world data to demonstrate their learning. Their grade will be based on exam scores, project work, and assignment completion.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Regression Analysis - ISYE 6414

    Uploaded by

    Yasin Çagatay Gültekin
    1K views3 pages
    This document outlines the syllabus for a graduate level regression analysis course. It provides information on the instructor, class schedule, required textbooks, course objectives, activities, evaluations, and topics to be covered. The course will introduce students to simple and multiple linear regression, variance-bias decomposition, variable selection, logistic regression, generalized linear models, and nonparametric regression methods. Students will complete assignments, two midterm exams, and a final project applying regression analysis to real-world data to demonstrate their learning. Their grade will be based on exam scores, project work, and assignment completion.

    Original Title

    ISYE 6414 Syllabus

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document outlines the syllabus for a graduate level regression analysis course. It provides information on the instructor, class schedule, required textbooks, course objectives, activities, evaluations, and topics to be covered. The course will introduce students to simple and multiple linear regression, variance-bias decomposition, variable selection, logistic regression, generalized linear models, and nonparametric regression methods. Students will complete assignments, two midterm exams, and a final project applying regression analysis to real-world data to demonstrate their learning. Their grade will be based on exam scores, project work, and assignment completion.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    1K views3 pages

    Regression Analysis - ISYE 6414

    Uploaded by

    Yasin Çagatay Gültekin
    This document outlines the syllabus for a graduate level regression analysis course. It provides information on the instructor, class schedule, required textbooks, course objectives, activities, evaluations, and topics to be covered. The course will introduce students to simple and multiple linear regression, variance-bias decomposition, variable selection, logistic regression, generalized linear models, and nonparametric regression methods. Students will complete assignments, two midterm exams, and a final project applying regression analysis to real-world data to demonstrate their learning. Their grade will be based on exam scores, project work, and assignment completion.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 3
    At a glance
    Powered by AI
    The key takeaways are that the course will cover topics such as linear regression, logistic regression, generalized linear models and nonparametric regression. Students will learn both theoretical and applied aspects of regression analysis.

    The activities include two midterm exams, homework assignments, and a final project with a presentation and report. The homework assignments and exams will help students prepare for the final project and deepen their understanding.

    The course will cover topics such as simple and multiple linear regression, variable selection, logistic regression, generalized linear models, and nonparametric regression methods like kernel regression and smoothing splines.

    Regression Analysis - ISYE 6414

    Instructor: Instructor Assistant:


    Dr. Nicoleta Serban
    Office: 438 Groseclose, ISyE E-mail:
    E-mail: [email protected] Office: , Main building, ISyE
    Office Hours: Tuesday 4-5pm Office Hours: Wednesday 4-5pm

    Class Schedule
    12:05pm - 1:25pm Tuesday and Thursday (IC 105)

    Class Web Address https://t-square.gatech.edu


    Most of our class material will be submitted via class email including
    • Course syllabus
    • Lecture and computer notes
    • Homework assignments and solutions
    • Your course grades
    • Questions and replies for homework assignments
    • Important announcements

    Honor Code For any questions involving Academic Honor Code issues, please consult me, my
    teaching assistants, or www.honor.gatech.edu.

    Course prerequisites: A sound familiarity with undergraduate or graduate statistics and prob-
    ability.

    Textbook: The course material will be based on a set of lecture notes being prepared by the
    instructor, but two primary textbooks are highly recommended:
    1. G. A. F. Seber, Alan J. Lee (2003) Linear Regression Analysis, Wiley Series in Probability
    and Statistics.
    2. L. Wasserman (2010) All of Statistics, Springer Series in Statistics.
    Other recommended books:
    1. P. McCullagh, J.A. Nelder (1989), Generalized Linear Models, Chapman & Hall.
    2. L. Wasserman (2010) All of Nonparametrics, Springer Series in Statistics.

    What students will learn in this course?


    By the end of the this class, students will learn the basics of regression analysis such as linear
    regression, model selection and logistic regression, but we will also cover more advanced topics
    including generalized linear regression and nonparametric regression. Students will be given funda-
    mental grounding in the use of some widely used tools, but much of the energy of the course is focus
    on individual investigation and learning. Active participation in the class is very important. This
    class is more about the opportunity for individual and team discoveries than it is about mastering
    a fixed set of techniques.
    What activities will the course involve students in to help them practice and demon-
    strate their learning?

    1
    Midterms: There will be two midterm exams with problems reviewing the material (lectures
    and assignments) provided in this course throughout the full semester. The exams are close notes
    (including homeworks) and books but a two (one-sided) pages with formulas will be allowed. The
    midterms are designed to help students grasp standard regression analysis methodology which will
    further facilitate a deeper understanding in the application context. All students will take the
    midterm in the same day at the same time.
    Dates:
    Midterm 1: October 11th
    Midterm 2: November 16th
    Assignments: Assignments will include both theoretical and computer problems; the latter prob-
    lems will ask you carry out analysis of data sets and simulations using computer software. Keep in
    mind that you should not hand in raw computer output. Conclusions and interpretation of results
    are more important than good printouts. These assignments are intended to help you prepare for
    the midterm exams and final project. You are allowed (and encouraged) to work together with
    other students on homework, as long as you write up and turn in your own solutions. You are
    also allowed (and encouraged) to ask me questions, although you should try to think about the
    problems before asking. Late Homework will not be accepted.
    Project: This project is a requirement you must fulfill in order to pass this course. The general
    goal of the project is to provide you with experience in applying regression analysis methodology
    to real data. For this project, you and your team must find a data set on your own. The data
    cannot be a data set found in a textbook or been analyzed in detail and results published. This
    project will serve as a means for students to demonstrate what they understand and can do with
    the content of the course. There will be an oral presentation of the project (≈ 15 minutes). In
    grading, I will primarily look for a sensible approach to the problem, and clearly-made connections
    between your analyses and the substantive questions. You can use any computing equipment and
    any computing resources in the school, any written source material you can find, in or out of the
    school. However, replicating results which have been already published without referencing to the
    source of publication is subject to plagiarism. Plagiarizing is defined by Websters as “to steal and
    pass off (the ideas or words of another) as one’s own : use (another’s production) without crediting
    the source.” Be sure to document carefully your project work.
    Deadline to submit an abstract of the project: October 23rd, 2012.
    Deadline to submit the project work (report): December 7th, 2012.
    Class presentation dates: December 5th and December 7th, 2012.

    How will students be evaluated?


    The course will be letter graded. The grade for the course will be based on two midterms,
    a final project, and assignments during the semester - Midterm 1 25%, Midterm 2 25%, Project,
    presentation and class participation: 35%, Assignments: 15%.
    The final project grade is 40% the presentation grade and 60% the report grade. The presenta-
    tions and the reports will be graded by students in this class. Each project team will assign grades
    for all the presentations including its own presentation. The average over all the team grades will
    be the presentation grade. Each team will be in charge of reading and grading two or more reports.
    The report grade will be a weighted average between students’ grade and the instructor grade.
    Please refer to grading guidelines documents.

    2
    Objectives: A tentative list of specific topics in this course is as follows:
    Part 1: Simple Linear Regression

    1. Introduction

    2. Estimation

    3. Inference

    Part 2: Multiple Linear Regression

    1. Review of Linear Algebra

    2. Estimation

    3. Inference

    4. Diagnostics

    5. Misc Topics

    Part 3: Variance-Bias Decomposition and Variable Selection

    1. Bias-Variance Decomposition

    2. Model Selection Criteria

    3. Regularized Model Selection

    4. Variable Selection vs. Hypothesis Testing

    Part 4: Logistic Regression

    1. Model Estimation

    2. Logistic Regression With Replication

    Part 5: Generalized Linear Regression

    1. Models

    2. Overdispersion in GLM models

    3. Model Validation

    Part 6: Nonparametric Regression

    1. Smoothing

    2. Kernel Regression

    3. Local Polynomials

    4. Penalized Regression, Regularization and Splines

    5. Smoothing Using Orthogonal Functions

    You might also like