Drawing Inferences from Large Samples
Building Strong Evidence from Diverse Individual Cases
One of the major contributions of statistics to modern thinking is the understanding that information on single, highly variable observations can be combined in great numbers to obtain very precise information about a population.
Although each individual is satisfied or not satisfied with his or her job, a sample survey can obtain accurate information about the population proportion that is satisfied.
Inferences are generalizations about a population that are made on the basis of a sample collected from the population. For instance, a researcher interested in the growth of pine trees plants 40 seedlings. The heights of these 40 plants would be a sample that is hopefully representative of the population consisting of all current and future seedlings that could be planted.
More specifically, we begin by modeling the population by a probability distribution which has a numerical feature of interest called a parameter. A random sample from the population distribution provides information ...