1. Samples can already provide important information (such as average value) or unimportant information (such as sample serial number)
2. Construct statistics - extract useful information from the sample to study the distribution of the population
3. Commonly used statistics (sample mean, sample variance, sample standard deviation, k-order moment, k-order central moment)
4. The sample mean is not equal to the overall expectation (the sample mean is a random variable that depends on the sample value)