In this chapter, we take a brief tour of classical statistics (also called the frequentist approach) and show how we can use pandas together with stats packages, such as scipy.stats and statsmodels, to conduct statistical analyses. This chapter and the following ones are not intended to be a primer on statistics, but they just serve as an illustration of using pandas along with the stats packages. In the next chapter, we will examine an alternative approach to the classical view—Bayesian statistics. The various topics that are discussed in this chapter are as follows:
- Descriptive statistics and inferential statistics
- Measures of central tendency and variability
- Statistical hypothesis testing
- Z-test
- T-test
- Analysis of variance
- Confidence intervals
- Correlation and linear regression
In descriptive or summary statistics, we attempt to describe the features of a collection of data in a quantitative way. This is different from inferential or inductive statistics because its aim is to summarize a sample rather than use the data to infer or draw conclusions about the population from which the sample is drawn.