🗓️ Session 10: Linear regression and experiments in R

Author

Affiliation

Claudius Gräbner-Radkowitsch

EUF and JKU

This session focuses on the practical implementation of linear regression models and on how to conduct the most common tasks associated with designing and implementing experiments in R.

This way it complements the more theoretical lectures. More precisely, we focus on the following topics:

• Implement simple and multiple linear regression in R
• Calculate and interpret \(R^2\) manually and using R functions
• Understand and demonstrate omitted variable bias
• Perform data transformations to linearize relationships
• Create effective visualizations using geom_smooth()
• Conduct basic model diagnostics
• Implement a power analysis in R

📚 Mandatory Reading

• The tutorial Linear Regression in R
  • Data sets used
• The tutorial Experiments in R
  • Data sets used

Further Reading

• Chapter 5 and Chapter 6 in Ismay and Kim (2020)

In-class exercises

• Work sheet
• Data sets
• Cheat Sheet

✍️ Coursework

• Complete the in-class exercises at home
• Do the exercises LinearRegression1 and LinearRegression2 from the DataScienceExercises package

TipQuick code for starting the exercises I

learnr::run_tutorial(
  name = "LinearRegression1", 
  package = "DataScienceExercises", 
  shiny_args=list("launch.browser"=TRUE))

TipQuick code for starting the exercises II

learnr::run_tutorial(
  name = "LinearRegression2", 
  package = "DataScienceExercises", 
  shiny_args=list("launch.browser"=TRUE))

References

Ismay, C. and Kim, A. Y.-S. (2020) Statistical inference via data science: A ModernDive, into R and the tidyverse, Boca Raton: CRC Press, Taylor and Francis Group, available at https://moderndive.com/index.html.