Skip to content

icon
Quality Score

Content Quality
/
Video Quality
/
Qualified Instructor
/
Course Pace
/
Course Depth & Coverage
/

Overall Score : 80 / 100

icon
Course Description

Welcome to the Advanced Linear Models for Data Science Class 1: Least Squares. This class is an introduction to least squares from a linear algebraic and mathematical perspective. Before beginning the class make sure that you have the following:- A basic understanding of linear algebra and multivariate calculus.- A basic understanding of statistics and regression models.- At least a little familiarity with proof based mathematics.- Basic knowledge of the R programming language.After taking this course, students will have a firm foundation in a linear algebraic treatment of regression modeling. This will greatly augment applied data scientists' general understanding of regression models.

icon
Instructor Details

placeholder

Brian Caffo, PhD is a professor in the Department of statistics at the Johns Hopkins University Bloomberg School of Public Health. He graduated from the Department of Statistics at the University of Florida in 2001. He works in the fields of computational statistics and neuroinformatics and co-created the SMART ( www.smart-stats.org) working group. He has been the recipient of the Presidential Early Career Award for Scientist ( PECASE) and Engineers and Bloomberg School of Public Health Golden Apple and AMTRA teaching awards.

icon
More courses by Brian Caffo

Free

Free

icon
Reviews

4.0

25 reviews in total

Select a bar to show only those reviews.Select the bar again to show every rating.

By Sean C on 29-Oct-19

I was expecting more practical examples in R.

By Gustavo F on 10-Sep-19

El curso es bueno, sin embargo me gustaría que pusieran notas sobre las ecuaciones o un pequeño resumen, ya que yo al menos no tengo dinero para comprar los materiales.

By Ryan G on 12-Jun-19

The coding videos with R are outdated. But this is to be expected since R is open-source and changing rapidly. The code videos should be updated frequently to coincide with the latest release of R and R Studio. I like that code example content is placed into separate videos. The videos are very clear and easy to see. If lecture segments are re-worked, I'd suggest writing in a single column, and keeping the new content always in the center of the screen. There is some inconsistencies in the notation, and some content is repeated too often. But it's not like salt: too much isn't nearly as bad as not enough.

By Emanuel N on 9-Mar-19

The teacher is like explaining to himself with no idea of who is in the other side. He knows the material but the course is just so boring and not becuse of the material itself but because of the way it is tought.

By Zitong W on 15-Feb-19

Not an advanced level course.

By Chad W L on 17-Apr-18

Very good

By John C on 5-Mar-18

Very thorough and rigorous. A great review for me.

By Andrea G on 11-Feb-18

This course is very interesting and Professor Caffo is very good at teaching. The proposed material is not very well organised and even if there are multiple sources available (videos, book, YT videos) they all say the exact same things (literally): it isn't helpful, only redundant. Moreover, I felt a lack of context: yes, it is only a 6 weeks course and yes there is a strict relationship with at least other 5 courses on Coursera (as a prerequisite) so it may be hard to contextualise. Nevertheless the material seems to be taken here and there from other courses/specialisations so you often have the feeling that you are missing something that may have been said in a previous lesson that does not belong to this course (and I am not talking about basic linear algebra stuff) or you wonder "what are we trying to prove? And why?". Material desperately lacks homogeneity, and it's easy to lose focus. Last but not least: R is a prerequisite, which is a bit strange since the topic is very theoretical (and there are no practical references throughout the course). R is mainly used by the professor to prove that theory is right (Wouldn't be more interesting to take advantage of R's plotting capabilities to have a visual result of theory?) or there are quiz questions that require the usage of R to get the answer (Why? Am I supposed to learn R or Least Squares?). Sometimes you feel like this is not a standalone, focused course, but an appendix of other specialisations. Overall it's a good course, very interesting topic, made harder by material that is a bit collected here and there and put together without the care the subject would require. My suggestion is to enroll only after completing Statistical Inference and Regression Models (both by B. Caffo) so that language and context are the same.

By Jens L R on 7-Nov-17

Great, detailed walk-through of least squares. Linear Algebra is a must for this course. To follow the last part requires knowledge of matrix (eigen?)decomposition, which derailed me somewhat.

By Francisco R A on 4-Nov-17

The topics covered by this course were really relevant, and it allowed me to better understand many things I have been using blindly for years. That being said, the course preparation by the lecturer appears quite careless. The videos are difficult to follow, with the electronic pen not helpful to comprehend the handwriting and full of mistakes the lecturer needs to correct constantly. Moreover, the quizs have included errors apparently for a long time, as the forums reflect, and no one has corrected them so far. The book recommended for the course is still in a very poor state, not only unfinished but also full of mistakes, making the task of linking the content it includes with the lecturer's explanations challenging at times. Fortunately, I did not pay for it, as it can be obtained for free if the student desires. However, those who spend the money the platform recommends to pay will have heavy reasons to be upset.

By AC on 29-Jul-17

Great Course

By Roney A B on 6-Jun-17

Very helpful! Tanks!

Showing 12 of 25 reviews