# 学生对 约翰霍普金斯大学 提供的 统计推断 的评价和反馈

4.2
4,219 个评分
853 条评论

## 课程概述

Statistical inference is the process of drawing conclusions about populations or scientific truths from data. There are many modes of performing inference including statistical modeling, data oriented strategies and explicit use of designs and randomization in analyses. Furthermore, there are broad theories (frequentists, Bayesian, likelihood, design based, …) and numerous complexities (missing data, observed and unobserved confounding, biases) for performing inference. A practitioner can often be left in a debilitating maze of techniques, philosophies and nuance. This course presents the fundamentals of inference in a practical approach for getting things done. After taking this course, students will understand the broad directions of statistical inference and use this information for making informed choices in analyzing data....

## 热门审阅

JA
Oct 25, 2018

Course is compressed with lots of statistical concepts. Which is very good as most must know concepts are imparted. Lots of extra reading is required to gain all insights. Very good motivating start .

MI
Sep 24, 2020

the teachers were awesome in this course. I liked this course a lot.Understood it properly.Thanks to all the beloved teachers and mentors who toiled hard to make these course easy to handle.Gracious!

## 751 - 统计推断 的 775 个评论（共 820 个）

Feb 24, 2016

Homework, lectures, and the quiz are completely out of sync. Bayes rule is introduced and appears in the homework but no where else. Things appear on the quiz that aren't in the home work or lecture. This was put together from scraps of another lecture, but in an incoherent fashion. When Caffo tells the viewer that they'll need to use other resources, he wasn't kidding. I dropped this the first time when I kept introducing things that completely had not been introduced, took another stats class, then came back and aced it. I don't mind accelerated learning or using other resources, but there's guide for which concepts are needed and where coverage for them can be found. This leaves little recourse but to know stats already, or go learn it before taking this course. Otherwise you don't know enough to even go find the pieces you need. Incidentally, the dude who does the lectures for Khan Academy does a fantastic job and the lectures are a joy to watch, though some people might prefer something that moves less slowly and carefully and perhaps they would prefer something that glosses over the fundamental concepts more. If that's the case, I can't say enough good things about Biostatistical Analysis by Zar but thoroughly, logically categorizing statistical methods with short, clear examples, references to the original research, and building up one concept after another in logical order. The chapters are short, but the first 16 or so should give you a good enough foundation to deal with about any intro stats class. As it is, Caffo's presentation needs some serious testing and remodeling, but there's no indication that it'll match what Khan Academy did regardless of how much work goes in. At best, it's a bitter pill you can swallow if you already know the concepts.

Mar 28, 2021

I hate this course. The instructor's way of explaining things was not that good. Could not understand most of the concepts.

This course was

very, very, very disappointing to me. It were hard to complete, hard to follow the slides. Wouldn't recommend for those learning stats.

A lot of the concepts, although simple when you think about it and used pretty much every day, I felt it were really difficult to understand at first. Wikipedia and some other online sources, and youtube videos, were more helpful but I think the real issue lay in the teaching style.

Brian seemed a very intelligent person, but he does not teach well. His way of explaining things was really bad: he speaks too fast (sometimes he changes terms...), he skips from slide to slide very quickly, he often do not provide adequate explanations.

Nov 11, 2017

The instructor is horrible. He does not understand what it takes to explain mathematical ideas clearly. I do not even understand what kind of audience the instructor is trying to target. For the most part, formulas are not derived but just thrown at you. So, watching this course is definitely going to be a waste of time for someone who (like me) want to understand all mathematical details behind the statistical concepts. At the same time, he is explaining thing using very formal language (probably borrowed from some bad math textbook), so do not expect that you will be able to learn things at least at the conceptual level. have a solid background in statistics, so all the ideas covered in this class are familiar to me. Fortunately, I did not have to learn them from Brian's class.

Apr 3, 2018

I thave a M.Sc in Economics and after not using Statistics for a while I took the course to refresh my knowledge. My conclusion is that this module is a waste of time! The teaching skills of the Tutor are not very good (to say it mildly). All the needed materials are there (in theory), but when it comes to statistics, one cannot emphasize enough how important it is to give illustrative examples and plots. This was not done here, either at all, or very badly. When lecturing Statistic, what I want to see is someone drawing a lot of Graphs and explaingn how and why curves shift and how that changes the numbers and tests. This is how intuition is build for what is going on. Otherwise it only becomes dry Stat...

Feb 27, 2016

This course, which is part of Data Science Specialization Course, which is a BEGINNER specialization, doesn't explain as it should to BEGINNERS. They try to explain, complex topics in 3 minutes ... If I didn't need the certificate, I would definitely not waste my time on this course. Youtube videos from khan academy or Brandon Foltz (Statistics 101) are much more valuable, you really get the topic and they are free. The professors didn't want to spend time preparing good material, from my point of view, the preparation is very poor.

The course is more oriented to teach you to be a "data monkey". You know the code you need to write, but you don't get what are you doing ... Where do these formulas come from?

Jan 27, 2016

Very disappointed with how the transition from the old Coursera platform to the new platform has been handled: lots of instances of the "see lecture X" in the quizzes where the reference is now just wrong because the lectures got renumbered, an almost complete lack of community TA/mentors, and no explanations from anyone as to how the new platform works.

Perhaps the worst of all has been the almost complete lack of acknowledgement of any problems from the folks at JHU. This feels like it's just been dumped on the students without any real testing or any appropriate resources to sort out any problems.

Apr 17, 2016

Content covered in this course was hard to learn, both because it was pitched at a level that realistically was more akin to a wrap up of content already covered (when in fact it was all new content) and because the instructor, Brian Caffo, has not a style that was conducive to teaching.

The instructor often would launch into a topic, and then speed through a calculation with basically no explanation.

In terms of time, this was one of the most intensive courses in the specialisation, and I'd recommend taking this course alone (not concurrently with other courses) for that very reason.

Mar 12, 2016

This is 3rd time I a trying this course. Labeling someone just reading the slides out loud as a course is ridiculous. I have to express that this is horrible, Please don't callout a course. Call it Audio Slides.

I have a Master's degree in engineering and have won scholarship all my life. This is the first time I am trying out on-line course. The courses were okay till I came to this sections mostly done by Brian Jaffe. Knowing and teaching is two different things, Brian! I will continue, with help from other materials outside the course. But I have ti rate this as 1 star.

Mar 20, 2016

The worst professor in this specialization. The subject really interesting, and I have been studying for a while in my Master's and PhD in engineering, so I could understand the bulk of the course. This is a very important subject in data analysis and these poor explained classes could make lot of people give up the specialization. Statistics involves much of mathematics and calculus which make it a natural challenge for most of the people. Please, improve these classes in order not to disappoint the student who want to become data scientists.

Mar 18, 2018

I found the lectures to be very lacking. The lecturer seems to make too many assumptions on what the student knows. The pacing is off on what is important to know, and what isn't. There should be more examples on how the information can be utilized in R. The quizzes should be restructured to require writing some form of R script to solve the problem. The swirl exercises don't help either. Furthermore, I was hoping that there would be more depth on how this may be utilized in a real world setting.

Jun 27, 2016

The lectures for this class are incredibly weak. Later lectures by the same professor are reasonable and decently structured. These lectures need to be redone. The quizzes are either out-of-order or expect you to do a lot of research on your own beyond the class notes and topics. The class project is unbelievably simple, and the final metric for the class project includes duplication and one portion of the grade assigned simply if you feel the person you're grading "tried".

Nov 21, 2017

I am finding this course to have a flavor where the material written on the slides are just read out loud. The content doesn't seem interesting. I was determined to complete the Specialization but I am leaving it as, unfortunately, I am feeling sleepy just by listening to the course material. This was not the case at all before taking this course. I hope the teaching methodology can be enhanced to make it more engaging. Thanks.

Dec 7, 2020

The lectures were largely incomprehensible, even though I have a maths background, albeit some years ago. I used the textbook (on Leanpub) as the Syllabus and sought other books/websites, in particular OpenStats. The assignment was challenging initially, but once I'd done it (and got full marks!) I really had learned something. Easily the most frustrating and hardest course of the Data Specialisation so far.

Mar 20, 2021

The lecturer is talking way too fast, simply reads off the slides and doesn't dive deep into any of the concepts behind all those definitions. You won't learn anything new here! So stay away from this course if you don't really need it for the Data Science specialization. There are way better alternatives even on Coursera (e.g. Inferential Statistics by Duke University)

Apr 4, 2016

Many videos lacked associated pdf slides so confusing to watch. Some topics on slides were not covered in videos. A supplemental video for those would be great even of optional.

Brian Cato is a good presenter, however, more examples needed to be done showing how to work out various statistical problems both by traditional method and using R.

Jan 17, 2016

Explanations not clear and feels like he's reading rather than explaining things.

Consecutive videos feel like they are disconnected. Videos stop in the middle of him talking something. Thank god for the swirl assignments which make things much clearer!

Also the course proceed very fast not giving enough time to the concepts.

Feb 6, 2021

Si estás haciendo las especialización de Data Science, te enfrentas a un módulo "duro". La filosofía de enseñanza del Prof Caffo dista mucho de la del Prof Peng (curso más amenos). Hay mucho que mejorar en el materíal del curso, a veces resulta dificil de comprender el objetivo de las explicaciones del profesor.

Sep 18, 2017

Very hard to follow, many of the maths symbols are not well explained. To little time spent on each concept and many concepts don't get a proper explanation. I had to re-learn almost every concept externally as I learnt little from the videos. Some of the lessons on khan academy are much easier to follow.

Dec 4, 2016

I've not found this course organized pedagogically speaking. The organization, insofar as "here is a list of stuff I'll be teaching" makes sense. But a lot of the "teaching" is ill suited for someone looking to learn with a minimal statistical background. It's incredibly frustrating and disheartening.

Jul 26, 2016

Terrible instruction in the videos and unclear directions. I'd avoid this course if possible, but it's required for the specialization. New videos should be shot and inspiration taken from more instructive and interesting guides, like The Cartoon Guide to Statistics by Gonick & Smith.

Mar 6, 2016

I really wanted to learn this stuff. I have almost no background in statistics. But the lectures didn't cover stuff with enough rigor and repetition for me to pick up much.

So I pretty much gamed the quizzes and project enough to get through the class. Rather disappointing.

Dec 17, 2016

Covers basic statistics (Mean, Variance, Simple Z and T tests). Not what I was expecting as Inference. Multiple testing of data is a sign of poor experimental design and should be avoided, not adjusted for. Bootstrapping is not a new idea and has been used in other fields.

Nov 21, 2017

Focused little on the programming side of probability, and the explanations of the material were so vague and assumed you knew so much about probability already, that I ended up using my college notes for the quizzes and projects more than the actual lecture video notes.

Jul 27, 2020

It is very hard for people with no previous statistics background to follow. Some key concepts are just one sentence mentioned in passing. I have to go on YouTube to learn first and come back. Then I will understand some of the things the instructors were talking about.

Apr 18, 2016

Do NOT recommend. Very poorly explained. Refers to some concepts without introducing, introduces others without explaining. Spends most of the time looking to the computer screen instead of toward you and reading the text instead of explaining in understandable manner.