Ask forty students how they come to school, then ask forty others.
3 lessons, about 1 h 25 min3 simulations10 problems3 practice questionsPython in every lesson
Two fair samples from the same population almost never give the same answer. A sample mean or a sample share changes from sample to sample, just by chance. This lesson names the parameter and the statistic, shows the scatter of many samples, and separates chance scatter from bias.
Take every possible sample of a given size, and the values of a statistic make a pattern: its sampling distribution. Its centre is the parameter, its spread is the standard error , and its shape becomes mound-shaped as the sample grows. Dice show all three exactly.
The standard error of a sample share is . It falls like one over the square root of the sample size, so four times as many people halve it. The size of the population hardly matters. This lesson shows the rule by simulation and uses it to plan a sample.
Log in to join the discussion.
Loading…
With Standard, you also open 12 more problems, 2 Python labs and 1 extra course. Everything you have used here stays free, always.