Save for later

Statistical Inference

Data Science,

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.
Get Details and Enroll Now

OpenCourser is an affiliate partner of Coursera and may earn a commission when you buy through our links.

Get a Reminder

Send to:
Rating 3.6 based on 719 ratings
Length 5 weeks
Starts Jun 19 (50 weeks ago)
Cost $49
From Johns Hopkins University via Coursera
Instructors Roger D. Peng, PhD, Brian Caffo, PhD, Jeff Leek, PhD
Download Videos On all desktop and mobile devices
Language English
Subjects Data Science Mathematics
Tags Data Science Data Analysis Probability And Statistics

Get a Reminder

Send to:

Similar Courses

What people are saying

statistical inference

I believe the course could be improved by taking that approach in the other weeks Very good introduction course to statistical inference.

Course needs more hands on example on all statistical inference tools - trying to disconnect from the daily routine and dive right into stats was difficult.

Truly recomend This course was very helpful to remember so concepts of statistical inference.

excellent executive introduction A topic such as statistical inference is not complicated, and could be taught in a much more straight forward and comprehendible fashion.

A lot of time is needed to sort out the documentation between R-files, the book (Statistical Inference for Data Science) and the slides.

Great course that covers the basics of statistical inference.

nice provides a formal explanation of statistical inference and its practical application.

There is no doubt that Brian is extremely sharp and knowledgeable about statistical inference subjects.

Great intro to statistical inference.

This course is for beginners for statistical inference using R. Very well presented.Thank you guys Very basic.

Statistical Inference was my 6th course.

But Statistical Inference is a mixed bag for me.First, if you are thinking about this course, take some time reading the other reviews.

Presentation could be more engaging Statistical inference is one of the most useful things in data analysis.

2 Thumbs Up Not explained well, had to take another statistical inference course.

Read more

data science specialization

Statistical Inference is the sixth course in the Data Science specialization, and the first course in the analytical portion of the course (followed by Regression Models and Practical Machine Learning.

You'll need to complete this course for the JHU Data Science specialization but you will likely struggle if you don't already have a strong background in statistical inference.

Forced myself through this course :( The best course I've taken in Data Science Specialization.Thanks Professor Caffo!

This is one of the most important course in data science specialization series, everyone should take this course very attentive way, because it give very deep insight about the role of statistics in data science.

I'm in the data science specialization.

In my opinion, the optimal solution for the course would be to create a separate, longer course in PC and stats and require knowledge of the two for taking Data Science Specialization.

The only reason for enrolling is to complete the data science specialization, though it may make you reconsider continuing with it.

Have some duplicated video, and some swirl problems This course, which is part of Data Science Specialization Course, which is a BEGINNER specialization, doesn't explain as it should to BEGINNERS.

Worth every penny The class needs to be more accessible especially for non statisticians, I learned more from khan academy which got me through this class than the class itself Definitely the best and most useful course of the Data Science Specialization!

I am really thankful for the Data Science team for this course and all the Data Science Specialization!

This is my review for the entire Johns Hopkins Data Science specialization on Coursera.

Statistical Inference is the 6th course in the John Hopkins data science specialization track, which is basically an introduction to statistics in R. The course covers many different topics in the span of 4 weeks from basic probability and distributions to T tests, p values and statistical power.

This was obviously a weak course in data science specialization.

If you are going to complete data science specialization track , you will have another alternative from John Hopkins University.

Read more

khan academy

My advice: watch others videos (from Khan Academy for instance) in order to understand the basics concepts and then, come back to this course.

Had to go to other MOOC (specifically Khan Academy) to obtain proper understanding of the topic.

Some of the lessons on khan academy are much easier to follow.

I had to go re-watch most of the lessons on khan academy to understand the principles.

It took me three months to go through the basics in Khan Academy before attempting it - and after that it was straight forward.

Khan Academy is a great place to start, and Udacity has a great class that gives a good intuitive understanding.

Khan Academy, DataCamp, Udacity, Duke (Coursera), and Columbia (edX) all have great courses.

Youtube videos from khan academy or Brandon Foltz (Statistics 101) are much more valuable, you really get the topic and they are free.

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.

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.

And by some, I mean do the whole thing on Khan Academy first.

In parallel I checked out Khan Academy and it was easier to understand.

Most other sources (Khan Academy, Stattrek, Stats textbooks etc) were used and preferred to complete course, to completion of the Data Sciences specialization.

Read more

difficult to follow

Even with a good foundation of statistics it was difficult to follow when examples are presented quickly and referenced back to material covered in prior lectures or even weeks as if they ought to be totally fresh in the student's mind.

The lectures were almost completely useless - I had to look up videos from youtube and other sources for every single lecture to learn the concept, and then rewatch the lecture - even then the instructor was difficult to follow.

I had some difficult to follow the lessons, because the professor is kind of reading the material and not building the concepts during class time.

If I wasn't already familiar with statistics, I would find the lectures and course book difficult to follow.

The slides are very difficult to follow.

This course is very difficult to follow, not because the topics are hard or too technical but mostly due to lecturer's poor job in explaining and creating a narrative.

Perhaps I'm holding the video lectures to too high of a standard set by Roger Peng in previous courses, but the videos are difficult to follow.

I am sure, but in a way for me it is difficult to follow.

To add to this challenge, the style of presentation is very verbose, and it is too difficult to follow the densely packed slides and the delivery without feeling stressed.

A bit difficult to follow the lectures at times.

Read more

hypothesis testing

The course covers probability, variance, distributions (normal, binomial, poisson), hypothesis testing and p-values, power, multiple comparisons, and finally resampling.

I'd had statistics back at the university but I never understood the underlying principle of hypothesis testing.

focussing mostly on hypothesis testing and p-values.

One gets exposure to topics in intro and intermediate statistic and starts to grasp how intricate the web of statistics it all the while the focus is on Hypothesis testing which is one cornerstones of statistics.

Important for those who are either going to take the Regression analysis or those who are working with data and want to do same basic hypothesis testing.

One gets to learn how to use R to perform the hypothesis testing.

It'd be a little steep of a learning curve for someone new to hypothesis testing/confidence intervals in four weeks.

I finally understand hypothesis testing and confidence intervals after taking several classes on this topic.

I have learned concepts of random variables and hypothesis testing.

Read more

machine learning

After taking the Applied Data Science in Python Specialization, I have a feeling like this course and Regression Models can just be merged, while logistics regression could just be transferred to the machine learning course.

It will help you out a lot in the regression and machine learning The subject of the course is very interesting and the professor is very competent.

I would say that this course is the most difficult among this specialization (practical machine learning is much easier than this).

Machine Learning?

These lectures on statistics, regression and machine learning are where the rubber hits the road after a lot of prep work to learn R and principles/tools of data science taught in earlier classes.

The materials offered from this course is far away enough from understand the content :( In my opinion, this course is fundamental to Statistics and therefore Machine Learning.

Instead, it seemed to be one long list of formulae after another with very little in the way of interpretation or intuition as Andrew Ng does so well in his Machine Learning class.

Read more

data analysis

I thought the course material was great but I think the grading criteria for the assignment should be more rigorous and check for proper methodology/application of techniques, just because I'd like to know that my approach to a given data analysis is sound and that the conclusions I draw from running tests, p-value adjustment, calculating power, etc.

This is a very important subject in data analysis and these poor explained classes could make lot of people give up the specialization.

If you’re looking for a good introduction to statistics that uses R, try Duke’s Data Analysis and Statistical Inference.

I can spend my time on Duke's Data Analysis and Statistical Inference which was highly recommended on coursera forums.

Take the one from University of Texas on EDX called Foundations of Data Analysis.

I found the lectures provided by the course "Data Analysis & Statistical Inference" helpful in understanding this subject.

Read more

waste of time

The lessons require intermediate level in statistics and it is a complete waste of time watching the videos without doing an initial course of statistics.

My conclusion is that this module is a waste of time!

I'm sorry to have to write a negative review but tbh these courses were simply a waste of time, especially when you consider the many excellent alternatives, like Data Analysis and Statistical Inference from Duke, Machine Learning and Statistical Learning from Stanford, and The Analytics Edge and Introduction to Probability from MIT.

I thought it could be a good opportunity to go over some basic statistic concepts in a short time but it turned out as a total waste of time.

Read more

regression models

For example, there was a lecture on the basics of knitr, but nothing related to creating a pdf from R. In the Regression Models class there is a lecture on basic notation.

This could be done is special sections of the book and lectures, as is done in the Regression Models class.

I am rating this after taking the 'Regression Models' course and in that course it is MUCH easier because he gives "real time" and visual examples of what, eg Residuals, mean or represent.

This was a very useful course in Statistical Inference where in all the fundamentals are taught in a very clear manner, setting the stage for the subsequent course on regression models.

Read more

practical applications

Could not see practical applications.

Good Very ilustrative and full of practical applications.

!too much emphasis on mathematical notations....where are the practical applications?lack of seemed more of a prose than a lecture....would not recommend to a beginner.Period 3.5 - Good, but I feel some of the explanations were over complicated a little compared to other coursers such as openintro to stats.

He tries to split the difference in going through the mechanics/mathematical theory and practical applications.

Read more

subject matter

I get that the subject matter is hard and so this isn't going to be easy to absorb regardless of how it is taught.

If, like me, you do not have an understanding of the subject matter then you may struggle to complete this in the time frame.

The course is being shaped to be able to reach those with little to no knowledge on the subject matter or for those who have found the subject matter difficult in the past.

This makes the learning experience a difficult one for people who are trying to acquire depth in the subject matter.

You can pass the course itself fairly easily by judicious use of google and the course ware but whether you really assimilate the subject matter and can make use of it is another matter entirely.

Read more

talking about

I was surprised to see that Brian mentioned the Central Limit Theorem; he definitely knows what he is talking about.

But most of the time he just throw us some result without properly setting the context and concepts, as if it was understood that we already know most of what he is talking about.

In general, I felt like the professor explaining too much on the mathematical meaning behind equations instead of talking about the real-world meaning of equation components, and why those calculation make sense.

I kept waiting for him to actually get to the explanation of what he is talking about, but he never does.

Read more


An overview of related careers and their average salaries in the US. Bars indicate income percentile.

Statistical Technician $39k

Assistant Statistical Research Specialist $60k

Statistical Support Specialist $63k

Statistical Programmer Trainee $63k

Senior Statistical Data Analyst (part time) $69k

Assistant Supervisor Statistical Programmer Analyst $71k

Statistical Programmer/ Clinical SAS Programmer Contractor $82k

Statistical Accounting Analyst $89k

Staff Statistical Analyst $97k

Quality Engineer - Statistical Evaluation and Validation Manager $97k

Senior Statistical/Clinical Programmer $98k

Associate Principal Statistical Programmer $161k

Write a review

Your opinion matters. Tell us what you think.

Rating 3.6 based on 719 ratings
Length 5 weeks
Starts Jun 19 (50 weeks ago)
Cost $49
From Johns Hopkins University via Coursera
Instructors Roger D. Peng, PhD, Brian Caffo, PhD, Jeff Leek, PhD
Download Videos On all desktop and mobile devices
Language English
Subjects Data Science Mathematics
Tags Data Science Data Analysis Probability And Statistics

Similar Courses

Sorted by relevance

Like this course?

Here's what to do next:

  • Save this course for later
  • Get more details from the course provider
  • Enroll in this course
Enroll Now