good intermediate-level textbook for undergraduate applied statistics in data science?

Question

I will be teaching an applied statistics course for the first time and the main audience will be 2nd and 3rd year undergraduates, mostly data science majors. They will have an intro statistics course as a pre-requisite that covers really basic topics (e.g., graphs, quantitative vs. categorical data, simple linear regression, probability, some CI and hypothesis testing). This second course will pick up where the first one leaves off and ideally would cover the following topics: review of CIs and hypothesis testing, ANOVA, goodness of fit tests, maximum likelihood, simple and multiple linear regression, logistic regression, nonparametric testing and also get into some Bayesian statistics as well as GLMs and GEEs time permitting. It would be great if the textbook also came with examples in R. It's been difficult to find a textbook that covers all these topics sufficiently and isn't too heavy on theory - since the students will mostly be interested in application. Does anyone have any good recommendations?

Answer 1

I challenge the notion of not covering the theory just because the students don't care. As our moderator, WHuber, writes in his profile, "The mathematics are not there for the joy of the analyst but because they are essential to the solution." Checking out what is written about data science on the Internet, your data science majors could use some theory.

Answer 2

One book that I am looking at for a similar purpose is Modern Data Science with R. It looks very interesting, although it will need supplication for some of the more advanced topics you mention.

Answer 3

Statistical Sleuth by Ramsey and Schafer seems to cover almost everything you've mentioned and at the appropriate level. I had less background in statistics than your students have when I first read this, and I found it accessible.

Answer 4

Julian Faraway Linear Models with R is an intermediate text. It is brief, dense and has R code on practically every page. It covers topics like regularization (featured as cover art) and imputation but stops short of mixed effects. Caveat emptor: his "hierarchical" models are not at all what you think they are.

John F. Monahan's aptly titled A Primer on Linear Models has zero computational content. Still, writing a "lab companion" around this beautiful little book would, in my opinion, not be a waste of time.