Cover of Statistical Foundations for Data Scientists
DRM-free · Yours to keep forever
Data Science & ML

Statistical Foundations for Data Scientists

Inference, experimentation and A/B testing done right

By Houssam Kodad

PDF 196 pages Beginner English

One-time purchase

€24.95

VAT included
where applicable

Download sample
  • Instant download after purchase
  • Readable on any device
  • Free updates to this edition
  • Secure checkout

About this book

What's inside

Plenty of data scientists can train a model but stumble when asked whether a result is real. This book rebuilds the statistical foundations that matter day to day: sampling, uncertainty, hypothesis testing and — above all — running and reading experiments. It's written for practitioners who want intuition and correct practice, not proofs, so you can design an A/B test that survives scrutiny.

What you'll learn

Skills you'll walk away with

  • Reason about sampling, variance and the standard error
  • Build and interpret confidence intervals correctly
  • Run hypothesis tests without common misinterpretations
  • Design A/B tests with adequate power and sample size
  • Avoid peeking, p-hacking and multiple-comparison traps
  • Choose the right test for proportions, means and counts
  • Communicate uncertainty to non-technical stakeholders

Table of contents

9 chapters
  1. 01

    Thinking in Distributions

    • · Populations and samples
    • · Variance and the standard error
    • · The central limit theorem in practice
  2. 02

    Estimation and Confidence

    • · Point estimates and bias
    • · Confidence intervals
    • · Bootstrapping uncertainty
  3. 03

    Hypothesis Testing Without Myths

    • · Null and alternative framing
    • · What a p-value is and is not
    • · Type I and Type II errors
  4. 04

    Choosing the Right Test

    • · Means, proportions and counts
    • · Parametric vs non-parametric
    • · Paired and unpaired designs
  5. 05

    Designing an A/B Test

    • · Hypotheses and metrics
    • · Power and sample size
    • · Randomisation pitfalls
  6. 06

    Analysing an Experiment

    • · Effect size and intervals
    • · Segmentation and Simpson’s paradox
    • · Guardrail metrics
  7. 07

    The Ways Experiments Lie

    • · Peeking and early stopping
    • · Multiple comparisons
    • · Novelty and network effects
  8. 08

    Beyond the Basic Test

    • · Sequential testing
    • · CUPED and variance reduction
    • · Bayesian A/B testing
  9. 09

    Communicating Results

    • · Decisions under uncertainty
    • · Visualising effects
    • · Writing a trustworthy readout

This is the full chapter list — exactly what you'll receive in the PDF.