Learn by Source
Johns Hopkins University · on Coursera

Statistical Inference

4.4(12,000) on Coursera·380K enrolled
Intermediate 54 hours English Specialization
SkillsStatisticsHypothesis testingConfidence intervalsProbabilityBayesian statisticsStatistical inference

Is this course right for you?

Our take
A rigorous grounding in statistical inference for serious data work, part of Johns Hopkins' Data Science specialization. It is free to audit.

Good for: data learners who want a rigorous grounding in statistical inference.

Skip if: you want a gentle, applied-only course, or you are uncomfortable with maths.

It builds from probability, expectation and variance through the central limit theorem, confidence intervals, hypothesis tests and p-values, all implemented in R on real examples. It is good on the critical-thinking side too, tackling the common misreadings of p-values and significance.

It is mathematical and not a gentle applied-only course, so if you are uncomfortable with maths or want tool-first training, start elsewhere. The certificate needs a paid Coursera subscription; the free audit covers the learning. The statistics is foundational and still relevant.

Comparison · LBS

Compare alternatives for Statistical Inference

Same topic, different options. We surface the trade-offs others hide so you can pick the course that actually fits your time, budget, and goals.
Coursera4.4(12,000)
Statistical Inference
Price
Paid
Free to audit, paid certificate
Duration
54 hrs
Level
Intermediate
Certificate
Specialization
Coursera4.9(39,000)
Machine Learning Specialization
Price
Free
Audit free · Certificate on subscription
Duration
86 hrs
Level
Intermediate
Certificate
Specialization
View course →
DataCamp4.7(14,800)
Data Scientist with Python Career Track
Price
Paid
Subscription, billed monthly
Duration
88 hrs
Level
Beginner
Certificate
Specialization
View course →
Coursera4.5(20,000)
R Programming
Price
Paid
Free to audit, paid certificate
Duration
57 hrs
Level
Beginner
Certificate
Specialization
View course →
Prices & availability can change — confirm on the provider's site. We're not affiliated with any single provider.

About this course

Part of the Johns Hopkins Data Science Specialization, this course covers statistical inference from first principles: probability theory, expected values and variance, common distributions, the central limit theorem, confidence intervals, hypothesis tests, and p-values.

Browse all Data Science courses Browse all Coursera courses

Instructor

BC
Brian Caffo / Roger Peng
Coursera instructor
380K+ learners10 courses4.4 instructor rating

Taught by Brian Caffo, Johns Hopkins biostatistics professor and prolific Coursera instructor known for rigorous yet accessible statistical education.

Frequently asked questions

Yes — this is one of the tougher courses in its specialization, and learners regularly name it, alongside R Programming, as a difficulty spike. If your maths is rusty or you are new to statistics, expect to pause often, look things up, and rewatch segments to keep pace. It is doable, but not a course you can coast through passively while half-paying attention.

A reasonable comfort with maths and some prior exposure to statistics really help, plus basic R, since the examples use it. It is not aimed at beginners: without a foundation in probability and statistical thinking, the notation and derivations become a steep, frustrating climb rather than a challenging-but-fair one. Shore up those basics first if they feel shaky, and the course becomes far more rewarding.

Yes. It is the sixth course in Johns Hopkins' ten-course Data Science specialization. You can take it alone, but it assumes the statistical and R grounding that the earlier courses in that sequence are meant to provide — so arriving without either that background or equivalent knowledge from elsewhere is the usual reason people find it lands harder than they expected.

Instructor Brian Caffo is rigorous and mathematically inclined, which some learners genuinely love and others find dry. If you want to truly understand the theory behind statistical inference — rather than apply methods by rote — it rewards the effort handsomely. If you were hoping for quick, intuitive shortcuts, it can feel heavy and slow, so it helps to know which kind of learner you are before starting.

Yes, you can audit the videos on Coursera at no cost. The graded quizzes and projects, along with the certificate, need a subscription, though financial aid is available if you apply and explain your circumstances. If you want the theory and the lectures rather than the credential, auditing gives you the core teaching — just without the graded practice that helps the harder ideas cement.
Paid
Free to audit, paid certificate
Enroll now