Outline

This follow-up course deals with the following topics:

1. Statistical inference
2. Linear models
3. Generalised linear models
4. Data validation and editing
5. Imputation

Previous experience with R is required.

Course schedule

Preparing your machine for the course

Dear all,

The below steps guide you through installing both R as well as the necessary additions.

We look forward to see you all in Banja Luka,

Anne and Jolien

System requirements

Bring a laptop computer to the course and make sure that you have full write access and administrator rights to the machine. We will explore programming and compiling in this course. This means that you need full access to your machine. Some corporate laptops come with limited access for their users, we therefore advice you to bring a personal laptop computer, if you have one.

1. Install R

R can be obtained here. We won’t use R directly in the course, but rather call R through RStudio. Therefore it needs to be installed.

2. Install RStudio Desktop

Rstudio is an Integrated Development Environment (IDE). It can be obtained as stand-alone software here. The free and open source RStudio Desktop version is sufficient.

3. Start RStudio and install the following packages.

Execute the following lines of code in the console window:

install.packages(c("tidyverse", "micemd", "jomo", "pan", 
                 "lme4", "knitr", "rmarkdown", "plotly",
                 "devtools", "boot", "class", "car", "MASS", 
                 "ISLR", "DAAG", "mice", "mitml", "miceadds",
                 "Ecdat", "Ecfun", "MEMSS", "VIM", "simputation",
                 "naniar","visdat", "UpSetR", "DAAG", "magrittr",
                 "haven", "Matrix", "lattice", "data.table", "grid",
                 "colorspace", "stringi", "stringdist", "editrules", 
                 "deducorrect", "rex"), 
                 dependencies = TRUE)

If you are not sure where to execute code, use the following figure to identify the console:

Just copy and paste the installation command and press the return key. When asked

Do you want to install from sources the package which needs 
compilation? (Yes/no/cancel)

type Yes in the console and press the return key.

Tuesday’s materials

We adapt the course as we go. To ensure that you work with the latest iteration of the course materials, we advice all course participants to access the materials online.

• Part A: Repetition

  • Lecture A
  • Lecture A Handout
  • Practical A
  • Impractical A

• Part B: Statistical Inference

  • Lecture B
  • Lecture B Handout
  • Practical B
  • Impractical B

All lectures are in html format. Practicals are walkthrough files that guide you through the exercises. Impractical files contain the exercises, without walkthrough, explanations and solutions.

Useful references

• The R project homepage
• CRAN task view for official statistics
• CRAN area for contributed documentation No longer actively maintained, but a lot of good resources
• Some places to find the R community:
  • #rstats hashtag
  • Rweekly
  • R-bloggers
  • Stack Overflow A good place to ask questions. Check if your question has been answered before, and make sure to phrase it carefully and correctly.
• Pipes in R

Wednesday’s materials

We adapt the course as we go. To ensure that you work with the latest iteration of the course materials, we advice all course participants to access the materials online.

• Part C: R Linear Models

  • Lecture C
  • Lecture C Handout
  • Practical C
  • Impractical C
  • Extra Lecture M Handout
  • Extra Practical M
  • Extra Impractical M
  • Nurse dataset

• Part D: Generalized Linear Models

  • Lecture D
  • Lecture D Handout
  • Practical D
  • Impractical D
  • Extra Practical
  • Data: cabinet, benefits

All lectures are in html format. Practicals are are provided both as naked questions but also with ample explanations and solutions - choose according to your taste!

Useful references

• Practical Regression and Anova using R by Julian Faraway

Thursday’s materials

We adapt the course as we go. To ensure that you work with the latest iteration of the course materials, we advice all course participants to access the materials online.

• Part E: Data Validation and Editing

  • Lecture E
  • Practical E
  • Impractical E
  • Data for the practical: bands.txt, unnamed.xls, people.txt, peoplerules.txt, dirty_iris.txt

• Part F: Imputation

  • Lecture F
  • Lecture F Handout
  • Practical F
  • Impractical F

All lectures are in html format. Practicals are walkthrough files that guide you through the exercises. Impractical files contain the exercises, without walkthrough, explanations and solutions.

Useful references

• Data validation
  • An introduction to data cleaning with R
  • Mark van der Loo has given several talks and workshops on this, with slides available from his GitHub
• Imputation
  • Flexible Imputation of Missing Data: written by Stef van Buuren, uses the mice package.
  • Applied Missing Data Analysis: book on missing data and imputation in R and SPSS.
  • Visualization of Missingness Patterns: Tutorial for the naniar package that does nice visualizations of missingness patterns.
  • Tutorial: Tutorial describing the use of 5 different R-packages for missing data imputation.
  • Tutorial: Another tutorial on missing data in R.
  • Tutorial: a set of tutorials for the mice package.

What to do after the course

The following references are currently available for free, either as pdfs or as extensive webpages (written with RMarkdown and bookdown). They are all very useful and we highly recommend them.

• R for Data Science: written by Hadley Wickham and Garrett Grolemund this book relies almost exclusively on the tidyverse approach to data analysis. Many highly effective tools will be right at your fingertips after reading this book and working through the many exercises.
• Hands-On Programming with R: a great read by Garrett Grolemund emphasizing programming techniques with R.
• Advanced R: You want to gain deeper knowledge of R and you want to learn from one of the most influential R contributors. This one is for you!
• Introduction to Statistical Learning: an introductory book on statistical learning, with applications in R. The R code is somewhat old-style and you might be able to find newer packages for the tasks, but ths is a solid read well worth the effort.
• Data Analysis and Graphics Using R: a detailed book that covers a lot about categorical data analysis and fitting glms in R.
• Happy Git and GitHub for the useR: a great introduction to version control using Git and GitHub together with RStudio. Written by Jenny Bryan in a very concise style. Highly recommended!