Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Duke University

Data Analysis and Statistical Inference

Duke University via Coursera

This course may be unavailable.

Overview

Prepare for a new career with $100 off Coursera Plus
Gear up for jobs in high-demand fields: data analytics, digital marketing, and more.
The Coursera course, Data Analysis and Statistical Inference has been revised and is now offered as part of Coursera Specialization “Statistics with R”. This Specialization consists of 4 courses and a capstone project. The courses can be taken separately:
  • Introduction to Probability and Data (began in April 2016)
  • Inferential Statistics (begins in May 2016)
  • Linear Regression and Modeling (begins in June 2016)
  • Bayesian Statistics (begins in July 2016) A completely new course, with additional faculty!
  • Statistics Capstone Project (August 2016) (for learners who have passed the 4 previous courses, and earned certificate)
You may enroll in a single course, or all of them, but each requires the knowledge and techniques from the previous courses. The assignments in these courses have suggested but not required deadlines, so you can work at your own schedule. Please check the Specialization page for other answers to your questions, and peek at the first course. We hope to see you in our new courses. The Statistics with R team.
___________________________________________________
The goals of this course are as follows:
  1. Recognize the importance of data collection, identify limitations in data collection methods, and determine how they affect the scope of inference.
  2. Use statistical software (R) to summarize data numerically and visually, and to perform data analysis.
  3. Have a conceptual understanding of the unified nature of statistical inference.
  4. Apply estimation and testing methods (confidence intervals and hypothesis tests) to analyze single variables and the relationship between two variables in order to understand natural phenomena and make data-based decisions.
  5. Model and investigate relationships between two or more variables within a regression framework.
  6. Interpret results correctly, effectively, and in context without relying on statistical jargon.
  7. Critique data-based claims and evaluate data-based decisions.
  8. Complete a research project that employs simple statistical inference and modeling techniques.

Syllabus

Week 1: Unit 1 - Introduction to data
  • Part 1 – Designing studies
  • Part 2 – Exploratory data analysis
  • Part 3 – Introduction to inference via simulation
Week 2: Unit 2 - Probability and distributions
  • Part 1 – Defining probability
  • Part 2 – Conditional probability
  • Part 3 – Normal distribution
  • Part 4 – Binomial distribution
Week 3: Unit 3 - Foundations for inference
  • Part 1 – Variability in estimates and the Central Limit Theorem
  • Part 2 – Confidence intervals
  • Part 3 – Hypothesis tests
Week 4: Finish up Unit 3 + Midterm
  • Part 4 – Inference for other estimators
  • Part 5 - Decision errors, significance, and confidence
Week 5: Unit 4 - Inference for numerical variables
  • Part 1 – t-inference
  • Part 2 – Power
  • Part 3 – Comparing three or more means (ANOVA)
  • Part 4 – Simulation based inference for means
Week 6: Unit 5 - Inference for categorical variables
  • Part 1 – Single proportion
  • Part 2 – Comparing two proportions
  • Part 3 – Inference for proportions via simulation
  • Part 4 – Comparing three or more proportions (Chi-square)
Week 7: Unit 6 - Introduction to linear regression
  • Part 1 – Relationship between two numerical variables
  • Part 2 – Linear regression with a single predictor
  • Part 3 – Outliers in linear regression
  • Part 4 – Inference for linear regression
Week 8: Unit 7 - Multiple linear regression
  • Part 1 – Regression with multiple predictors
  • Part 2 – Inference for multiple linear regression
  • Part 3 – Model selection
  • Part 4 – Model diagnostics
Week 9: Review / catch-up week
  • Bayesian vs. frequentist inference
Week 10: Final exam

Taught by

Mine Çetinkaya-Rundel

Reviews

4.6 rating, based on 41 Class Central reviews

Start your review of Data Analysis and Statistical Inference

  • Anonymous
    Time consuming, but this course is well worth the money on signature track! This will give you a very solid understanding of statistic, which is the basic of so many other fields: experimental research, lean, and machine learning just to name a field.

    Unmissable if you want to broaden your knowledge on how to do things with scientific rigor.
  • Life is Study
    Duke’s Data Analysis and Statistical Inference on Coursera is an introduction to statistics with an optional computational component using the R programming language. The course runs about 8 weeks and covers a considerable amount of ground in that t…
  • Bart
    Great, great course. A well balanced mixture of theory, examples, labs and to learn software and projects to test your skills in the 'real' world. The teacher explains the concepts very clearly. The course layout and order of topics is excellent. T…
  • I've had plenty (cough) of time to forget the basic statistical inference I did at high school. This was a great refresher (if a little repetitive - hypothesis tests vary mainly in relatively minor-seeming details). With a little prior exposure, it'…
  • A wonderful course on data analysis and statistical inference as well as the use of R (and R Studio, although there is the option for students to complete the assignments online using a DataCamp platform). I found the exercises and especially the project an extremely interesting endeavour, and the provision of an open-courseware textbook is a very nice gesture by the instructor.

    For other learners, particularly those who are not particularly after a certificate and don't want to wait till the next offering of the course, it is also possible to cover the same course material through the DataCamp platform at your own leisure!
  • Anonymous
    Extremely time consuming. I work in a market research firm, have some familiarity, and perhaps because of that some misconceptions. The course is very very well organised by the instructor, much of the material follows each other, so no time wasted like some other online courses. Believe me you'll need every extra minute. Her videos are upbeat as well, never a dull moment. One thing make sure your math skills are up to par. My math skills need brushing up, but I'm used to data and programming so that took the edge off. I would say make sure you have the rest of your life organised while doing the course. Definitely worth every aching minute though.
  • Took the course,finished it but didnt pass,as igot a really bad grade in the midterm.The course is probably the best introductory-intermediate course available.Together with the book (Open Intro) makes a perfect start for anyone who wants to get serious with statistics.Time consuming,you really have to allow for lots of work and lots of reasoning,as exercises tend to be with lengthy descriptions,and the quizzes too. In all a pleasant experience (it would have been better if i d passed :):))...I seriously reccomend it,and i am waiting for the next iteration ,in order to gain the certificate,which i consider a valuable addition to anyone's skill kit.
  • One of the greatest courses I've taken so far. A great teacher, very much involved in exchanges with her students. A large variety of teaching approaches and tools. Lots of practice, through short tests, R-programming labs, and an in-depth project. A very lively forum, with lots of help to cope with difficulties. The course is not too difficult, but the variety of the proposed material requires that students get involved quite substantially. A very nice book available for free, with plenty of practice exercises.
  • Anonymous
    i have completed 5 weeks so far. and now i am dropping out of this course. its painfully slow and easy. I was looking to gain more knowledge on stats before i stats my ms program in analytics. I dont want to take away the credits from duke uni or Dr Mine Rundel. She has done great work . I went through her book os and read pdfs. this way i saved time. but now i am dropping out. ( I am from engineering background )
  • Very time consuming course still doesn't contain any proofs. All the time spent just to make you memorise quite simple concepts but not to understand why do they work.
    Don't wast your time, go through book and pdf slides and you will end up with the same knowledge many times faster.
  • Anonymous
    This course has a fairly high standard for passing (80%). Though this can be frustrating, it ultimately drives you to buckle down and learn the material. Those who cannot devote a decent amount of time to the course will feel lost if they have no former introduction to the topic. If you can devote the time, it is rewarding and very well taught. Highly recommended.
  • Anonymous
    This is definitely the best Coursera course I have ever done (and probably best MOOC). Very high quality materials, presented and explained extremely well and with a lot of real world practical examples which most stats courses do not have. It is a high workload and a high pass mark but you will get real, useful knowledge
  • Anonymous
    Thisi is one of the best course I ever took online or at university.

    The content is challenging but the professor explains it so well that it is a pleasure to come back for more every week.

    Its not easy, you have to work a lot to succeed but if you do, you will be very happy with this class.
  • Anonymous
    One of the very best courses - instructor was engaging, course material was challenging but extremely interesting. I find myself referring to this material repeatedly in my data science work.
  • Anonymous
    I took this course a while back before it changed format. From the other reviews, I see that that it is still a great course. I had no background in statistical inference but lots in programming before taking the course so the R programming was fairly trivial and I could concentrate on learning data analysis and statistical inference. The material was presented methodically and with many worked examples. This is not a 'fast-paced' course. If you need to cram material, this isn't the right course for that. This course teaches you the language of the scientific method - how to articulate a hypotheses that can be disproven. Like any language, the art of speaking it takes time and practice.
  • One of the best MOOCs out there, not really much to say besides that. Very time consuming if you choose to join the track with programming assignments. However, they are totally worth your time. The recommended exercises are also useful, and the final project was interesting as well. It's just the perfect MOOC (for me, at least).
  • Anonymous
    This course is just a stress to anyone taking this. I don't find it helpful and substantial. It doesn't help. The explanations are very vague and complex. The videos are not motivational and so boring. I wasted a lot of time in this course if only not because of my Degree I wouldn't have taken this curse!
  • Stacev
    Very good practical oriented course. All concepts clearly explained. Many useful examples from real world are demonstrated in detail. Flow is very smooth from basic to advanced topics.
  • Profile image for Chandana Sapparapu
    Chandana Sapparapu
    Dr.Mine is one of the best professors I've known. She can communicate arcane concepts very effectively and her passion is seen in every lecture.
  • Vlad Podgurschi

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.