STAT 108 Regression Analysis

    Syllabus

    LECTURE: MWF 4:10 - 5:00 p.m., WELLMN 234. Recordings will be posted in Media Gallery on Canvas.

    DISCUSSION: B01: R 10:00-10:50 a.m., CRUESS 107; B02: R 11:00-11:50 a.m., WELLMN 115. Recordings will be posted in Media Gallery on Canvas.

    INSTRUCTOR: Prof. Jiming Jiang, 4228 MSB, jimjiang@ucdavis.edu; Office hours: T 10:00 a.m. - 12:00 p.m. or by appt. The office hours will be REMOTE; check canvas for the link.

    TEACHING ASSISTANTS: Ms. Yuanyuan Li, yynli@ucdavis.edu, Office hours: R 2:00 - 4:00 p.m., REMOTE

    TEXT: Applied Linear Statistical Models by Kutner et al. (5th ed.), ISBN: 0-07-238688-6.

    REQUIREMENTS:
  • HOMEWORK: Homework will be assigned in class and collected online each Friday (starting the second week). The lowest two homework grades will be dropped in calculating the overall homework score. No late homework.

  • PROJECT: There will be two projects involving computer data analysis. Each project is due in two weeks. Although we recommend that you use R to complete the projects, use of other softwares is also allowed. The TA is responsible in providing instructions for R.

  • MIDTERM: There will be an online midterm exam. Exam date: Wed., May 4, 2022, 4:10-5:00 p.m. (lecture time). One page of notes (both sides, regular-size paper) is allowed.

  • FINAL: There will be an online final exam. Exam date: Thu., June 9, 2022, 10:00 a.m. - 12:00 p.m. Two page of notes (both sides, regular-size papers) are allowed.


    • GRADES:
    FINAL 40%, MIDTERM 20%, PROJECT 20% (10% each), HOMEWORK 20%. Grade Disputes will not be considered until the end of the quarter. Submit a copy of the disputed course work, with a note indicating the total number of points in questions and your rationale. If the total points in question will change your letter grade (including +/-), your rationale will be considered.

    TOPICS:
  • Introduction

  • Simple linear regression

  • Inference in regression and correlation analysis

  • Diagnostics and remedial measures

  • Simultaneous inference

  • Matrix expressions

  • Multiple linear regression

  • Quantitative and qualitative predictors

  • Variable selection

  • More on diagnostics and remedial measures