Course Title: EE 395c: Estimation Theory
Class Information: Fall 2010
Class time: 1600-1715 T R
Class location: Perkins 101
Instructor Information: Dr. Jeff Frolik
357 Votey
Phone: 802.656.0732
Office Hours: I have an open door policy and am around most the time; otherwise email for an appointment
Recommended Pre/Co-requisite: EE 270: Stochastic Processes, Graduate Standing in Engineering, Math or CS, Permission of Instructor.
Course Objective:
  • To study fundamentals associated with various estimation methods.
  • To apply one or more of the methods for a practical purpose.
  • Text: S. Kay, Fundamentals of Statistical Signal Processing: Estimation Theory

    Grading: Participation/Homework: 10%
    Exam I: 20%
    Exam II: 30%
    Quizzes: 20%
    Project: 20%

    Grade Scale: A [90, 100]
    B [80, 90]
    C [70, 80]
    D [60, 70]
    F [0, 60]
    breaks within above ranges are used to set +/-
    Tentative Topics: Cramer-Rao Lower Bound
    Maximum Likelihood Estimation
    Baysesian Estimation
    Kalman Filters
    General: All course materials will be provided through BlackBoard.

    Expect the first exam to be given in late-October and the second at the end of the semester. Both will be take home exams. At least one week notice will be given. Exams will have a comprehensive component. On exams, it is expected that the methodology needed to obtain a solution will be presented; just presenting a correct final answer will not garner full credit.

    You can expect quizzes to be given once a week in class. You will be allowed only one sheet of notes for the quiz unless otherwise notified in advance.

    Individually, students will develop a project throughout the semester in which one or more of the methods studied will be applied to a "practical" problem. Preferably, this problem will be related to the graduate student's own research. The project will consist of a proposal, a paper (IEEE format) and a technical presentation. Timeline (and details) for the deliverables will be provided in October.

    Throughout the semester, the instructor will give students feedback on how they are progressing the course.

    Plagiarism: Any students found giving and/or receiving assistance on Exams will receive a failing grade for the course. However, students are encouraged to work together and to exchange ideas when working on their experiments and presentations. Students must be sure to reference their work properly, including all web sources. UVM's policy on honesty is clearly defined and can be found at
    ADA: Students with disabilities should contact the instructor as soon as possible regarding necessary accommodations.