Highly recommend this course.

The python codes are amazing.

سهلة التعلم لتحليل البيانات

very nice and informative

Excelente curso!!!

Excellent Cousre.

Very satisfied.

Extremely Good

Great course.

Good Course

very good

Excellent

thanks

Greate!

brutal

good

شكرا

good

good

good

good

I really don't see the reason for all the hate for this course and the specialization.

Pros:

Robust syllabus on statistics and mathematics that covers all the important concepts in inferential stats

Ample example python notebook files for students to reference

High quality lectures and content

Manageable assignments and quizzes

Lots of guided examples (week4) and excellent readings written by UoM on statistics and data analysis theory and practices.

Student forum support from lecturers is excellent

Cons (minus 1 star):

While the material in this course is good, we should be given some notes with formulas and diagrams to accompany us at the start of week 2 and 3 (the hardest ones)

A person without a background in python will struggle in this specialization because you need to have programing skill and experience and the introductory practices are not enough.

You need to have some prior experience with stats or a pre-college/college year 1 text book to accompany you if this is your first time learning stats. The start-middle phase content at each chapter is explained and NOT skipped, but it could use more elaboration. I had to source elsewhere on the internet for the gaps in my knowledge (which were easily found). It is just missing a few elementary level explanations (how to calculate P values and what tests to use in different scenarios) to understand the more complex topics. I learned hypothesis testing in high school and had to refer to my textbooks for a few explanations and diagrams.

Summary:

Very satisfied with this course for what I got out of it, I gained multiple skills and a lot of familiarity with theory and examples.

Just like the other two courses of this specialization I believe the content offered here is great and the main methods used for statistical inference are well explained and even possibly more important, the interpretation of results is really hammered home here which is great. A few things that weren't covered thoroughly enough (if at all) in my opinion are QQplots (maybe this is more related to course 1...) and Chi-square tests (what are they and when do we use them?). Also it would have been nice to take a little bit more time to explain the differences in using t-tests and z-tests and why we would choose one over the other. I do believe the structure of the notebooks could be improved, maybe listing all of the possible functions that can be used for statistical inference for each type of scenario (e.g. functions applicable for mean of population proportion). As always, I would have loved for answers to be provided for the "extra practice" notebooks.

This course gives a lot of important concepts such as confidences intervals, p-values and hypothesis testing, but I think it is short in terms of using it in real life because the explanations rely on examples that always fulfil the same conditions and in real life it is not possible to have always the same conditions for a problem you want to study. It would be nice if the course could be complemented (in a deep way) with applications of complex samples and non-probability samples, not only single random sample. Also, python codes are not explained in a deep way.

The teaching team is great. But the assignments are not very helpful. And yes, this is more a statistics course than a python course. The application with python, which I am more interested in, seems just the supplementary portions to the lectures of concepts of statistics. There is not much introduction to how we use python to perform statistics, how we debug, and how we interpret the outcomes of programs.