Course round 2019

Here, you will find information for the course round Fall 2019.¶

General Information
* The first part of the course coincides with the MSc level course EQ2810 Estimation theory, accelerated program course, 6 cr.
* Course responsible and examiner: Magnus Jansson
* Where: click on "Calendar" to find out.
* When: Period 1-(2) every odd year, see "Calendar" for the schedule.
* Course literature: "Fundamentals of Statistical Signal Processing: Estimation Theory," Kay, Steven M. ISBN 0133457117.
* Grading: Pass/Fail
Course requirements
* Weekly homework assignments, to be solved and reported individually
* Peer grading of homework assignments
* Two project assignments
* 48 hour take-home examination
Course contents can be learnt by cooperative discussions, but homework problems should be solvedindividually and handed in in due time for grading. Please recall the KTH rules for examination.¶

For passing the course we require 80% of the total score on homework and project assignments and 50% on exam as well as a serious completion of the peer grading task. ¶

Preliminary Schedule See KTH central schedule for EQ2810 for the official times and lecture rooms. The Calendar on this page should also be up to date. We have seven time-slots scheduled, Tuesdays 13.15-15.Preliminary we will use six of them for normal lectures:Lec. 1: Ch. 1-3 Lec. 2: Ch. 4-5 Lec. 3: Ch. 6-7 Lec. 4: Ch. 8-9 Lec. 5: Ch. 10-11 Lec. 6: Ch. 12,14,15Lec. 7: Reserve, project?We may need to add some slots later for project presentationsor the like.¶

Outline of the book Ch. 1: IntroductionCh. 2: Minimum Variance Unbiased EstimationCh. 3: Cramer Rao Lower BoundCh. 4: Linear ModelsCh. 5: General Minimum Variance Unbiased EstimationCh. 6: Best Linear Unbiased EstimatorsCh. 7: Maximum Likelihood EstimationCh. 8: Least SquaresCh. 9: Method of MomentsCh. 10: The Bayesian PhilosophyCh. 11: General Bayesian EstimatorsCh. 12: Linear Bayesian EstimatorsCh. 14: Summary of EstimatorsCh. 15: Extensions for Complex Data and Parameters¶

(Ch. 13: Kalman filtering - will not be covered in this course, see Adaptive signal processing or Optimal filtering courses)¶