Summary

This chapter introduced us to the basics of probability and some ways it can be used with data science. We started with the absolute basics, like random variables, discrete versus continuous variables, and probability spaces. We saw how Bayes' law can be used to estimate conditional probabilities. We also saw how frequentist statistical methods rely on data, while Bayesian methods rely on intuition or beliefs. Perhaps confusingly, Bayes' law can be used with frequentist and Bayesian statistical methods.

We also examined several common probability distributions that can be used in data science, including the well-known normal or Gaussian distribution. Lastly, we looked at a few tenets of probability theory (the law of large numbers and the central limit theorem) as well as a few sampling techniques (random and bootstrap sampling).

In our next chapter, we'll take some of this knowledge and extend it to statistical testing. We'll see how this can be...