Country or region and language

    Choose your country or region and your language.

    Suggested for you

      All countries and regions

        Choose your character

        It shows in the top bar and on your profile. Change it any time.

        Courses / Data and analytics tools

        Statistics for data roles

        The statistics analysts and data scientists use, worked in Python on real-looking data.

        Start lesson 1Practice interviewTake the assessmentPractice the first unit of every course. No account needed.
        27lessons
        140checked exercises
        3projects, cases and exams
        Prepares you for The statistics rounds of data analyst and data scientist interviews

        What you will be able to do

        • Choose between the mean and the median, and report spread with the right standard deviation
        • Spot outliers with percentiles, z-scores and the IQR rule
        • Measure correlation with Pearson and Spearman, and say what it can't prove
        • Work out normal, binomial and Poisson probabilities without off-by-one mistakes
        • Explain the standard error and plan a sample size
        • Build confidence intervals for means, rates and medians, and read them correctly
        • Choose and run the right test: Welch, paired, proportions, chi-square or a rank test
        • Plan an A/B test's sample size, check its split and read it to a decision

        Who it is for

        You work with data and never took a statistics class
        Each lesson starts from a business question and the few lines of pandas and SciPy that answer it, on data that behaves like real data.
        You learned statistics on paper
        You'll do the same calculations in Python, with the library calls analysts use and the traps they hit: sample formulas, tails and the wrong interval.
        You have a data analyst or data scientist interview coming
        The statistics round checks exactly these basics, and the course has a set of screen questions to practice them.

        What you can practice free

        Unit 1, Describe data: 5 lessons and 26 checked exercises, with no account or card.

        Start the free unit

        The rest of the course opens with a One Course or All Access plan. See plans and prices

        Keep going in Statistics for data roles

        Choose access here. Your course is already selected.

        One Course

        Every lesson, project and mock exam in Statistics for data roles.

        Loading price/ month

        Billed monthly. Cancel any time.

        All Access

        Every course, exam and project, plus the Interview Hub.

        Loading price/ month

        Billed monthly. Cancel any time.

        Projects, case studies and mock exams

        Learn the statistics behind analyst and data scientist work by doing it in a Python notebook in your browser, with pandas, SciPy and statsmodels. You start by describing data, then work with distributions, sampling and confidence intervals. Every exercise uses data from a small fictional business, and every answer is checked twice: on the lesson data and on a second dataset you never see, so the method has to be right, not only the number.

        Beginner

        FreeNo account or card needed. Every lesson in this unit is yours to practice.

        Describe data

        Center, spread, percentiles, z-scores and correlation, and when each one misleads.

        5 lessons

        Distributions and sampling

        Normal, binomial and Poisson probabilities, standard errors and the sampling distribution.

        4 lessons

        Confidence intervals

        Intervals for means, proportions and any statistic, then easy interview questions.

        5 lessons

        Intermediate

        Hypothesis tests

        One-sample, Welch and paired t-tests, tests for rates, chi-square and rank tests, and many tests at once.

        8 lessons

        A/B testing

        Power and sample size, the pitfalls that wreck tests, a checkout test readout, and medium interview questions.

        5 lessons

        Common questions

        Do I need to install Python?

        No. Python, pandas, SciPy and statsmodels run in your browser in a notebook like Jupyter. Nothing is installed and nothing runs on our servers.

        Is it free?

        The first unit is free and needs no account. The rest of the course opens with a One Course or All Access plan, and the pricing page shows every plan and its price.

        How are my answers checked?

        Each exercise names the results it wants, such as both ends of an interval or a probability. Your code's results are compared with the answer's, a known mistake gets a message that names it, and your code runs again on a second dataset you never see, so the method has to be right, not only the number.

        Does it cover hypothesis tests and A/B testing?

        Yes. The Intermediate level covers one-sample, Welch and paired t-tests, tests for conversion rates, chi-square and rank tests, multiple comparisons, power and sample size, sample ratio mismatch and peeking, and ends with a full checkout test readout. Regression is the next part of the course.

        How long does the course take?

        About 9 hours if you do every lesson once. Most lessons take 15 to 20 minutes.

        Your Work Gym account

        Save your progress and pick up on another device. Your browser's progress comes with you.

        or

        You can keep practicing without an account.

        Change your plan

        Checking the price

        Help and feedback

        Ask a question, tell us what is not working, or share an idea. We reply by email.

        What is it about?

        We use it only to reply to you.