Resources Related to the mosaic Package

This vignette describes related resources and materials useful for teaching statistics with a focus on modeling and computation.

Package Vignettes

The mosaic package includes a number of vignettes. These are available from within R, from cran.r-project.org/package=mosaic, or from www.mosaic-web.org/mosaic/.

• Minimal R describes a minimal set of R commands for use in Introductory Statistics and discusses why it is important to keep the set of commands small;

• Resampling methods in R demonstrates how to use the mosaic package to compute p-values for randomization tests and bootstrap confidence intervals in a number of common situations. The examples are based on the ``resampling bake off’’ at USCOTS 2011.

• ggformula/lattice conversion examples compares the lattice and ggformula formula interfaces for creating graphics.

• Less Volume, More Creativity, based on slides from an ICOTS 2014 workshop, introduces the mosaic package and related tools and describes some of the philosophy behind the design choices made in the mosaic package.

• Graphics with the mosaic package is gallery of plots made using tools from the mosaic package.

Auxiliary packages

Some features of the mosaic package are provided through auxiliary packages. These include:

• mosaicModel – implements high-level systems for working with statistical models: effect-size calculation, bootstrapped confidence intervals, prediction error, graphics for models with multiple inputs. The package contains an introductory vignette.
• mosaicCalc – provides the calculus components of mosaic, including integration, differentiation, and differential equation solving.

Install these packages using install.packages(c("mosaicCalc", "mosaicModel")).

Mosaic paper

Pruim R, Kaplan DT and Horton NJ (2017). The mosaic Package: Helping Students to ‘Think with Data’ Using R. The R Journal, 9(1), pp. 77-102. https://journal.r-project.org/archive/2017/RJ-2017-024/index.html.

Abstract: The mosaic package provides a simplified and systematic introduction to the core functionality related to descriptive statistics, visualization, modeling, and simulation-based inference required in first and second courses in statistics. This introduction to the package describes some of the guiding principles behind the design of the package and provides illustrative examples of several of the most important functions it implements. These can be combined to help students ‘think with data’ using R in their early course work, starting with simple, yet powerful, declarative commands.

Project MOSAIC Little Books

The following longer documents are available at github.com/ProjectMOSAIC/LittleBooks.

• Start Teaching Statistics Using R includes some strategies for teaching beginners, and introduction to the mosaic package, and some additional things that instructors should know about using R. (A spanish language translation can be found at https://github.com/fjaraavilaa/MOSAIC-LittleBooks-Spanish.)

• A Student’s Guide to R provides a brief introduction to the R commands needed for all the basic statistical procedures in an Intro Stats course.
  (A spanish language translation can be found at https://github.com/fjaraavilaa/MOSAIC-LittleBooks-Spanish.)

Textbook Related

• Statistical Modeling: A Fresh Approach (DT Kaplan, second edition)] is an introduction to statistics embracing a modeling approach and employing resampling methods. The mosaic package is used throughout.

  • www.mosaic-web.org/StatisticalModeling

• Foundations and Applications of Statistics: An Introduction Using R (R Pruim, second edition) is an R-infused probability and mathematical statistics text that emphasizes connections between probability and statistics. The first edition of the book predates the mosaic package, but much of the code originally in the fastR package has been moved into the mosaic package. The second edition is supported by the fastR2 package and uses ggformula for plotting.

  • https://bookstore.ams.org/amstext-28
  • www.ams.org/publications/authors/books/postpub/amstext-28

• Modern Data Science with R (BS Baumer, DT Kaplan, and NJ Horton) is an R-infused data science text that emphasizes conceptual understanding and computation.

  • http://mdsr-book.github.io/

• The Statistical Sleuth in R (NJ Horton) describes how to undertake analyses in R for the examples in the Third Edition of the Statistical Sleuth: A Course in Methods of Data Analysis (2013), by Fred Ramsey and Dan Schafer.

  • nhorton.people.amherst.edu/sleuth

• Introduction to the Practice of Statistics in R (NJ Horton and BS Baumer) describes how to undertake analyses in R that are introduced as examples in Introduction to the Practice of Statistics, by David Moore, George McCabe, and Bruce Craig.

  • 9th edition: nhorton.people.amherst.edu/ips9
  • 6th edition: nhorton.people.amherst.edu/ips6e

• Statistics: Unlocking the Power of Data (Lock, Lock, Lock, Lock, and Lock) is an introductory statistics textbook that embraces a resampling approach.

  An annotated companion to the examples in the book implemented using R can be found at

  • github.com/rpruim/Lock5withR/

  and the Lock5withR R package provides all the data sets used in the text.

  • lock5stat.com

• Stats: Data and Models (NJ Horton) describes how to undertake analyses in R for the examples in the Fourth Edition of Stats: Data and Models (2015), by Dick de Veaux, Paul Velleman, and Dave Bock.

  • nhorton.people.amherst.edu/sdm4

• Intro Stats (P Frenett and NJ Horton) describes how to undertake analyses in R for the examples in the Fourth and Fifth Editions of Intro Stats (2013), by Dick de Veaux, Paul Velleman, and Dave Bock.

  • 5th edition: nhorton.people.amherst.edu/is5
  • 4th edition: nhorton.people.amherst.edu/is4

• Introduction to Statistical Investigations (Tintle et al) is another introductory statistics textbook that embraces a resampling approach.

  An annotated companion to the examples in the book implemented using R can be found at

  • github.com/rpruim/ISIwithR/

  The ISIwithR R package provides all the data sets used in the text. Additional information about the book and the approach used there can be found at

  • www.isi-sats.com/isi/

Articles

• GW Cobb, “The introductory statistics course: a Ptolemaic curriculum?”, Technology Innovations in Statistics Education, 2007, 1(1), escholarship.org/uc/item/6hb3k0nz.

• Fieberg JR, Vitense K, Johnson DH. 2020. Resampling-based methods for biologists. PeerJ 8:e9089 https://doi.org/10.7717/peerj.9089

• NJ Horton, BS Baumer, and H Wickham, “Teaching precursors to data science in introductory and second courses in statistics,” CHANCE, 2015, 28(2):40-50, nhorton.people.amherst.edu/precursors

• NJ Horton, and J Hardin, “Teaching the next generation of statistics students to”Think With Data”: special issue on statistics and the undergraduate curriculum,” TAS, 2015, 69(4):259-265, https://amstat.tandfonline.com/doi/full/10.1080/00031305.2015.1094283

• D Nolan and D Temple Lang, “Computing in the statistics curricula”, The American Statistician, 2010, 64(2), www.stat.berkeley.edu/~statcur/Preprints/ComputingCurric3.pdf.

Other Resources

• Example R Code/Graphs Using NHANES by Amy Wagaman, https://awagaman.people.amherst.edu/stat230/Stat230CodeCompilationExampleCodeUsingNHANES.pdf