Exercises

Practice the following exercises to revise the concept of reproducibility learned in this chapter:

• Review: When we created the data frame nothing, we combined a vector of 1,000 binomially distributed random variables, 1,000 normally distributed random variables, and a vector of two colors, red and white. Since all the columns in a data frame have to be the same length, how did R allow this? What is the property of vectors that allows this?

• Seek out, read, and attempt to understand the source code of some of your favorite R packages. What version control system is the author of the package using?

• Carefully review the analysis that was used as an example in this chapter. In what manner can this analysis be improved upon? Look at the distribution of the combined SAT scores in NYC schools. Why was modeling the SAT scores with a Gaussian likelihood function a (very) bad choice? What could we have done instead?

• If both a poor and a rich person are willing to buy a pair of sneakers for no...