Chevron Left
Вернуться к Байесовская статистика

Отзывы учащихся о курсе Байесовская статистика от партнера Университет Дьюка

3.8
звезд
Оценки: 763
Рецензии: 247

О курсе

This course describes Bayesian statistics, in which one's inferences about parameters or hypotheses are updated as evidence accumulates. You will learn to use Bayes’ rule to transform prior probabilities into posterior probabilities, and be introduced to the underlying theory and perspective of the Bayesian paradigm. The course will apply Bayesian methods to several practical problems, to show end-to-end Bayesian analyses that move from framing the question to building models to eliciting prior probabilities to implementing in R (free statistical software) the final posterior distribution. Additionally, the course will introduce credible regions, Bayesian comparisons of means and proportions, Bayesian regression and inference using multiple models, and discussion of Bayesian prediction. We assume learners in this course have background knowledge equivalent to what is covered in the earlier three courses in this specialization: "Introduction to Probability and Data," "Inferential Statistics," and "Linear Regression and Modeling."...

Лучшие рецензии

RR
20 сент. 2017 г.

Great course. Difficult to apprehend sometimes as the Frequentist paradigm is learned first but once you get it, it is really amazing to see the believe update in action with data.

GH
9 апр. 2018 г.

I like this course a lot. Explanations are clear and much of the (unnecessarily heavyweight) maths is glossed over. I particularly liked the sections on Bayesian model selection.

Фильтр по:

176–200 из 240 отзывов о курсе Байесовская статистика

автор: Derrick Y

4 дек. 2016 г.

Good course, but need more details.

автор: Xinyi L

14 авг. 2017 г.

not very interested

автор: Kshitij T

4 янв. 2018 г.

tough course.

автор: Vivian Y Q

12 окт. 2017 г.

huge jump

автор: Thomas C

4 авг. 2021 г.

Unfortunately I found this course to be inferior to the Inferential Statistics course. Below are some comments which will hopefully help you to improve the course.

- The lectures more or less repeated the textbook verbatim. When learning, it's helpful to be exposed to different examples. The lectures did not help if I didn't understand something from the textbook.

- The textbook was filled with spelling and grammatical errors, which affected my understanding at times. Ditto for the supplementary materials (although I did appreciate their presence).

- The pop-up windows for the questions during the lectures were poorly formatted (at least using Chrome).

- I would recommend redesigning the course. Begin by clarifying the philosophical differences between Inferential and Bayesian statistics. E.g. discuss the likelihood principle, the conditionality principle, etc. I had to look this stuff up myself to understand the fundamental differences between the two approaches.

- An explicit guide of when to apply different priors would have been useful. E.g. I have this data, I have this belief about it, I want to get this type of answer, so which prior should I use?

- I think a deep-dive on a smaller amount of material would have been better. It would have been helpful to slowly and deliberately go through each step of Bayesian inference, rather than rushing through a larger number of examples.

- Similar to the point above, it would have been helpful if you did not wrap the R functions. Instead, show us the source code and explain what each line does.

- The amount of time spent on Bayesian regression was puzzling, as the results were noted to be numerically equivalent to frequentist regression. Why not teach us something new, and only highlight the difference in interpretation?

Thank you, and I hope you can improve this course in the future. I would not recommend it at this point, although I would recommend the frequentist course.

автор: Zhao L

4 авг. 2016 г.

This course covers a good amount of bayesian statistics. However, the presentation/videos starting from week 2 really sucks. They change instructors for difference topics and obviously some instructors are not very good at explaining other than reading the material.

The videos skipped many medium steps that are actually very crucial for understanding the concepts. And no suggested reading materials at all either. Also the quiz are not very well designed either. For example, some quiz are much more simpler than the course material, which makes it not helpful at all to understand the course material itself. While some times it is the opposite.

The first three courses in this specialization are very good, but somehow this course are way below the quality of the previous ones.

автор: Witold W

26 сент. 2017 г.

Tons of interesting material. However, presented in a way which is hard to take, and harder to remember, especially if you are used to the exceptionally high standards of Coursera. The slides, which I am used to work with, are a big let down. They are hard to follow, erratic, lack thoroughness and are incomplete. It does not make it better that they refer you all the time to additional material. Also the lectures are disappointing. The lecturers do not interact with the slides, they don't explain. I wished I could have taken more from the course since I think that the topic is relevant and interesting. Really disappointed. I do hope that there will more MOOC's teaching Bayesian statistics soon.

автор: Camilo M

10 янв. 2021 г.

I think the course was for something more extended and, therefore, more understandable. A lot of reading material (which is appreciated) prior to the videos take a long time to start learning. I had hoped that by doing the laboratory of Week 3, I could go deeper into the concepts and understand many of the things that were more complex to assimilate, but the impossibility of executing certain functions and thus delay the test of the laboratory, was frustrating; this limits my continuity with week 4 and does not give me certainty that week 4 and 5, in the laboratory of R, is well designed and without problems. I think it has a lot of potential and opportunities for improvement.

автор: Jorge A S

10 июня 2018 г.

The previous courses of the specialization were much better. This one is too fast paced and confusing. The math for this course is significantly harder than for the previous, but in my case it was not the math what was making it hard. The videos are hard to follow. I answered some of the quiz questions based on intuition and what looked reasonable rather than actually knowing how to solve them. Usually in the previous courses the project felt like the hardest part, but on this one the project felt like the easiest. What I did like about the course is that it has good breadth of topics in Bayesian statistics.

автор: Natalie R

5 сент. 2019 г.

This course, compared to the others in the specialization, was a bit of a mess. The lectures were hard to follow with fewer exercises to check your learning than in previous courses. The "text" seemed to just be a bad transcript of the lectures with all sorts of errors. The labs were confusing and sometimes included incorrect or outdated instructions that caused me to waste a lot of extra time trying to figure out what was wrong. I enjoyed doing the final project, though, and learned a lot doing that.

автор: Adara

4 дек. 2017 г.

The course presents interesting material but it is not easy to follow. It is a huge jump from the previous courses and requires far more hours to understand all the (math-heavy) material than the stated. The slides feel a bit chaotic and the language/sentences during the explanations could be much simpler. At times it feels that the instructors limit themselves to reading formulas one after another, making it hard to find a connection between them and how they are applied.

автор: Duane S

15 апр. 2017 г.

This course makes a valiant effort to provide as much coverage of Bayesian statistical methods as the prior three courses in the "Statistics in R" specialization do for Frequentist statistical methods, but the lack of supporting material (e.g. reading/text exercises directly paired with each lesson) really hampers this. The videos are quite informative, but if you don't catch on to the material based strictly on the videos, the weekly quizzes can be a bit frustrating.

автор: Deleted A

4 дек. 2019 г.

This course is far different from others in the series. Mathematical formulas and other concepts are introduced without any prior background. Even if the concept is understood the application part of it still remains a mystery on where to apply it, the course could have been more elaborate explaining these concepts in-depth rather than introducing without any prior background. Words such as prior families are used without introducing them properly.

автор: Matt H

26 авг. 2019 г.

Disappointing drop in quality compared to previous courses in the specialisation. Lectures are just a verbatim copy of the accompanying book, with no additional context, and course assignments/quizzes expect you to know material not covered in the course (e.g. while working on a quiz, I would go back to the textbook, CTRL+F on key terms from the quiz questions, only for them not to be anywhere in the course material).

автор: Gustavo L

26 апр. 2020 г.

This course was by far the hardest one of the series and I felt lost numerous times. The video lectures are brief and in my opinion bring more questions than answers. I am not sure about other students but I feel that this course needed 1- much more R-exercises. 2- many more examples per lecture for example, it could be better explored the lessons learned with multiple question quizzes.

автор: Kateryna M

15 июля 2017 г.

I think that some of the lectures in this unit are not constructed as well and clear as in previous units. This makes it harder to learn. I needed way more time than it is specified in the course to process and understand the course material. However, in the previous units I did not experience such issues

автор: Lucie L

15 авг. 2016 г.

This course clearly has come ambition to cover important topics on bayesian statistics, however, probably due to time limit, the lecturers have to skim through the contents without further, sometimes necessary explanations. As a result, the lectures are difficult to follow.

автор: Xiaoping L

2 нояб. 2016 г.

The professors know what they are doing but not good at making the concepts plain to the students who don't have the strong background. Most of the times I would just ask myself why they did this and that but later they don't provide enough explanations.

автор: Omar S

27 мар. 2020 г.

The instructors are not interactive at all, they are reading directly, it's very boring specially for first week, the instructor overlook most important issues and doesn't highlight them, however the reading material is useful.

автор: Léa E C B

17 мар. 2021 г.

Way too hard compared to the others courses, and very unclear. Plus since not a lot of people finish the course, you have to wait a long time to see your peer review exam approved.

автор: David O P

13 мая 2017 г.

Although the course is high quality, unless the other units, this one is way too difficult. The fact that it wasn't Mine who performed the whole course impacts significantly

автор: Joseph K

24 янв. 2017 г.

I would've saved a lot of time by knowing the R commands used in this course. It took so long to figure out things and I I didn't like the course because of that.

автор: Thomas P

18 авг. 2016 г.

Mismatch between assessment and course content. After not being able to pass the assessment, I've fallen behind on the course and I'm too busy to catch up.

автор: Haochen Z

25 авг. 2020 г.

After Week 2, there are large gaps between previous material and the futher teaching material which makes confusing and a bit hard to comprehend.

автор: Matti H

15 янв. 2017 г.

Good introduction to Bayesian concepts, but the course would benefit of some rethought of design of exercises.