This chapter has introduced the idea of using sample data to make statistical inferences-that is, drawing conclusions about populations and processes by using sample data. We began by learning that a population is a set of existing units that we wish to study. We saw that, since many populations are too large to examine in their entirety, we often study a population by selecting a sample, which is a subset of the population units. Next we learned that, if the information contained in a sample is to accurately represent the population, then the sample should be randomly selected from the population, and we saw how random numbers (obtained from a random number table) can be used to select a random sample. We also learned that selecting a random sample requires a frame (that is, a list of all of the population units) and that, since a frame does not always exist, we sometimes select a systematic sample.

We continued this chapter by studying processes. We learned that to make statistical inferences about the population of all possible values of a variable that could be observed when using a process, the process must be in statistical control. We learned that a process is in statistical control if it does not exhibit any unusual process variations, and we demonstrated how we might sample a process and how to use a runs plot to try to judge whether a process is in control.

Next, in optional Section 1.4 we studied different types of quantitative and qualitative variables. We learned that there are two types of quantitative variables—ratio variables, which are measured on a scale such that ratios of its values are meaningful and there is an inherently defined zero value, and interval variables, for which ratios are not meaningful and there is no inherently defined zero value. We also saw that there are two types of qualitative variables—ordinal variables, for which there is a meaningful ordering of the categories, and nominative variables, for which there is no meaningful ordering of the categories.

We concluded this chapter with optional Section 1.5, which discusses survey sampling. We introduced stratified random sampling, in which we divide a population into groups (strata) and then select a random sample from each group. We also introduced multistage cluster sampling, which involves selecting a sample in stages, and we explained how to select a systematic sample. Finally, we discussed some potential problems encountered when conducting a sample survey—undercoverage, non-response, response bias, and slanted questions.