The videos, readings, and labs were not sufficient for me to feel prepared for the assessments. I ended up using outside resources just to understand what was being presented here. There was really no explanation of why you would use certain tools or the underlying statistics principles; the course assumes a lot of the learner (both in statistics and Python) considering it's aimed at beginners. I believe this is a newer course, so hopefully it will continue to be revised, but I was disappointed in the content compared to other IBM courses I've taken through Coursera.

I did not like this course.

1. Neither Statistics nor Python bits of it are properly explained 2. What get's presented in videos does not always go together with what is then asked in tests and labs 3. Some of the videos are quite incoherent 4. To this day I have no idea if in my final assessment (peer-graded) I used all the correct methods and arrived at correct conclusions. No way to verify if obtained values actually matched expected outcome. Sure I presented something and arrived at conclusions based on what I had fed Python but was it correct? 5. Some evaluation criteria for evaluating peers did not match what was asked during the task.

Overall I felt it was quite messy and statistics concepts as well as python code were not nicely explained or working together.

There are mistakes in examples, in assignments, and final project! Creators never respond in Help section.

At first, I find this course to be somewhat challenging at first since I don't have any prior knowledge in statistic, but after a few lecture and some self study later, I have gain a pretty good understanding of statistics and its application in Data Science.

I especially like the final assignment as it give me a feel for what being a Data Scientist is like. It also make me go through all of the previous lab for reference. By doing so, I have a chance to review the things I have learnt and get a deeper understanding of the material. I can't speak for everyone but if you are completely new to statistic like me and planning to break into Data Science field, I think this course might be a good starting point for you.

I enjoyed taking this course and found it was well explained. Having been out of school for a long time and not using stats in my daily job, I found that I had to listen to the videos over and over again to fully understand the concepts introduced. I also struggled initially with python as it was a new concept for me. I recommend it for others, take it slowly and try to revisit the videos and readings and ensure you follow and thoroughly complete the lab exercises as this will help with the project.

This course was seamlessly easy to understand and follow. During my undergraduate studies, I struggled with statistics which made me a bit worried taking the course.

I am glad I pushed passed my fear and took the course , as it has sparked my interest to learn statistics, how it applies to data and making business decisions.

Thanks Aije and Murtaza - I look forward to taking more courses from you both on here.

I really enjoyed taking this course. It was really easy to follow and I absolutely loved how the course was put together. I will recommend anyone looking to use Python for Data Science to take this course.

Amazing course . Very easy to follow . Definitely improved on my python skills . Would 100% recommend .

Challenging for non statiticians

The course felt disjointed at times and there was a lack of clear explanations. The expectations for the final project (formatting, etc.) could have been stated more clearly to reflect the marking rubric. The final project was otherwise nice and quite summative.

This felt boring and a bit outdated. Some guides were no longer up to date or relevant. Instructors sometimes felt robotic. First module did not feel useful. Mod staff on discussion forums were not always helpful, and sometimes took weeks to respond. Looking forward to signing up for Google's new Advanced Data Analytics program as a refresher. Their previous basic Analytics program was much more enjoyable and personable.

I found some of the explanations to be quite poor. Often the instructor starts off by detailing the steps for a certain test before you even know what the test is or why you would do it. I often had to go google the topic and read and take my own notes to be able to do the assignments or pass the tests.

Many of the concepts mentioned in the lectures or the quizzes are never clearly defined. Quizzes test concepts never mentioned in class, and one question contradicts what was taught in class.

It is an incomplete and disorganized course, some quiz questions were not even explained in the lessons compared to other courses I have taken. I would not recommend it

All IBM courses need to be removed from Coursera until they can fix them, and Coursera gets a promise that the INSTRUCTORS actually involve themselves in the forums. Anybody who paid for these courses should be refunded their money due to the extreme poor quality. I thought this IBM course would be different than the others, but they went right back into the speed through and not explaining the more complex topics again. The final project asks us to add titles to our statistical graphs, but this was never taught in either the videos or labs. The evaulation metrics are also mismatched with what the actual assignment states. This is 100% unacceptable.

I really enjoyed the course. However, one has to keep in mind that the concepts presented are very basic.

for example, regression is a highly complicated topic and interpretation of the results needs more in depth analysis, however, for an introductory look into the topic the course is very well structured

Excellent course to help clear doubts for the level of statistics needed for data science. It a great experience. well done IBM!

Being a Mechanical Engineer, I already knew Normal Distribution but don't know the T-test, ANOVA, etc. This course covers pretty much about doing statistics using Python but you should know statistics before doing this course. The course is great it also help you learn a bit of Seaborn visualization library.

I would recommend to do some course on Statistics first then do this course for implementing statistics in Python. The Quiz, Assignment and Lectures were good. Only thing which was bad was it didn't explain the value we got in the summary of results of statistical tests we performed. Also the explaination was very brief.

Good course, many subjects are covered. But be careful if you're totally new to statistics and hypothesis testing, this course is rather fit as a refresher.

Unfortunately the lecture slides are not available for download and some of the transcripts need serious amendments. In all Jupyter labs the kernel did not connect for a long time and attempts to export notebooks as pdf threw internal server errors. Such things are disturbing and could be prevented with proper monitoring and proper technical setup. The peer review in week 6 must be performed without having the approved solutions; this is not very professional.

Overall, the course gave me a brief but informative look at the basics of statistics with Python. Once again, the many practical exercises were very nice. However, the speed of the p-value and regression was a bit too ambitious for me. Would have appreciated some more details there or a good link to somewhat short and informative. But as said, overall, another very informative course.