Statistics
Lessons in this chapter
About Statistics
Statistics introduces the idea of drawing conclusions about a large group by carefully studying a smaller piece of it, and comparing two groups using the same tools.
Understand populations and samples defines a population as the entire group being studied and a sample as a smaller subset actually measured or surveyed, and introduces why a random sample — one where every member of the population has an equal chance of being chosen — is far more trustworthy than a convenient or biased one.
Use random samples to draw inferences about a population takes measurements from a random sample and uses them to estimate something about the whole population, along with the idea that different random samples from the same population will produce somewhat different estimates, which is why multiple samples give a more reliable picture than just one.
Compare populations closes the chapter by using sample data from two different populations — like the heights of two different grades — to judge whether an observed difference between them is a real, meaningful difference or could just be due to normal sample-to-sample variation.
Frequently asked questions
A population is the entire group being studied — every 7th grader in a school district, for example. A sample is a smaller subset of that population that’s actually measured or surveyed, like 50 randomly chosen 7th graders from that district. Understand Populations and Samples introduces both terms together since the rest of the chapter depends on telling them apart.
A random sample gives every member of the population an equal chance of being chosen, which means the sample is likely to reflect the population’s real mix — not skewed toward any particular group. A non-random sample, like only surveying kids in one classroom, risks representing just that one group’s characteristics instead of the whole population’s.
Surveying only students who show up early to school about how much they like waking up early — that sample systematically leaves out students who’d answer differently, so the results wouldn’t reflect the actual student population’s opinion. Understand Populations and Samples has kids evaluate examples like this to build an instinct for spotting bias.
Take a measurement or proportion from the random sample and use it as an estimate for the whole population — if 30 out of 50 randomly sampled students prefer a certain lunch option, that same 60% is used as an estimate for the entire student population, not just those 50 students. Use Random Samples to Draw Inferences About a Population has kids make and justify estimates this way.
Because a sample is only a piece of the population, not the whole thing — by chance, one random sample of 50 students might include slightly more of one preference than another random sample of 50 different students would, even though both samples were chosen fairly. This natural variation is exactly why looking at multiple samples, rather than trusting just one, gives a more reliable estimate.
Compare a measure of center, like the mean, from a sample of each population, and judge whether the difference between them is large relative to the natural variability within each sample — a small difference that’s within the range samples normally vary by isn’t strong evidence of a real difference, while a large difference is. Compare Populations has kids reason through this with real sample data from two groups.