14  Sampling and Statistical Inference

In the first three modules, you learned how to collect, organize, and describe data. You mastered the language of descriptive statistics and probability theory. Now comes the leap to statistical inference—the art and science of using a sample to draw conclusions about an entire population.

Statistical inference rests on a single foundation: random sampling. Chapter 13 introduces five probability sampling methods and explains why random selection is the gateway to valid inference. The chapters that follow teach you to estimate population parameters from a sample (estimation) and to test hypotheses about populations (hypothesis testing).

This module marks a fundamental shift in the book. From here forward, every formula, every test, every confidence interval assumes that your sample was drawn randomly from the population. If that assumption fails—if the sample is biased or non-representative—all the inference that follows is worthless. This is why sampling method matters so much.

By the end of this module, you will understand how samples represent populations, how to quantify uncertainty in estimates, and how to test whether observed patterns in data reflect true population differences or mere random chance.