Data Analytics
Four levels, twelve lessons, from a vague question to a defensible number
Analytics is the work between a question and a decision. Somebody asks why signups dropped, or whether the new checkout is better, or which customers are worth keeping - and the job is to turn that into something measurable, measure it honestly, and say what it means plainly enough to act on.
Overview
So this course spends its time on judgement rather than tools. The SQL and the statistics here are the small subset you will use constantly, taught alongside the mistakes that make a number look solid when it is not.
Introduction
It assumes you can write basic SQL - SELECT, WHERE, GROUP BY - and no statistics at all. Everything statistical is built up from scratch, in words first.
Every level is three lessons and a Level Check quiz, with an Expert Exam at the end. The examples are small tables you can read in your head rather than datasets to download, because the point is the reasoning rather than the arithmetic.
By the end you will be able to take a question like "is the new onboarding working", turn it into a metric you can defend, work out whether the difference you see is real, and present it in a form that survives someone disagreeing with it.
What you will be able to do
- Turn a vague business question into a metric with a precise definition
- Read a distribution rather than trusting an average
- Build cohorts and retention curves, and read what they are saying
- Judge whether a difference between two groups is real or noise
- Tell correlation from causation, and name the likely confounder
- Build a dashboard somebody keeps using after the first week
What each level covers
4 levels · 16 lessons
-
Level 1 - Basic
The shape of the work, and the statistics everybody already uses. The workflow first - what a question has to become before it can be answered - then the descriptive statistics that are reported daily and misread almost as often, and the handful of SQL that produces nearly every analytical answer.
4 lessons 40 min of reading
Start with From a Question to Something You Can Measure → -
Level 2 - Intermediate
Metrics, and the ways an average hides what you were looking for. Defining a metric precisely enough that two analysts compute the same number is harder than it sounds and worth doing properly. Then cohorts, which separate what changed from who changed, and segmentation, including the case where every segment moves one way and the total moves the other.
4 lessons 45 min of reading
Start with Defining a Metric That Survives Scrutiny → -
Level 3 - Advanced
Comparison, which is where confident wrong answers come from. Whether a difference between two groups is real, how big a sample has to be before the question can even be asked, and the gap between two things moving together and one causing the other - including how to name the confounder rather than gesture at it.
4 lessons 46 min of reading
Start with Comparing Two Groups Honestly → -
Level 4 - Expert
The operating side, which decides whether any of the earlier work keeps being useful. Dashboards that are still open in a month, definitions that drift without anyone noticing, and forecasts that are honest about what they do not know. Every one of these is a maintenance problem dressed as an analysis problem.
4 lessons 57 min of reading
Start with Dashboards People Actually Use →
Guides and articles
Longer reading about this subject, written alongside the course.
Before you start
- Basic SQL: SELECT, WHERE, GROUP BY
- No statistics assumed
Common questions
- What does the Data Analytics course cover?
- It is 4 levels and 16 lessons: Level 1 - Basic; Level 2 - Intermediate; Level 3 - Advanced; Level 4 - Expert. Each level ends with a quiz, and the last one is an exam over the whole course.
- How long does it take?
- About 188 minutes of reading and exercises - roughly 3.1 hours. It is self-paced with no cohort and no start date, so you can leave and come back and the site remembers where you were.
- What do I need to know first?
- Basic SQL: SELECT, WHERE, GROUP BY. No statistics assumed.
- Is it free?
- Yes. Every lesson, example and quiz in this course is free to read, and you do not need an account to read them. Signing in only adds progress tracking and quiz results.
- What will I be able to do afterwards?
- Turn a vague business question into a metric with a precise definition. Read a distribution rather than trusting an average. Build cohorts and retention curves, and read what they are saying. Judge whether a difference between two groups is real or noise. Tell correlation from causation, and name the likely confounder. Build a dashboard somebody keeps using after the first week.