RSS Matters

RSS Logo

RSS’s Top R Package and Software List

Link to the last RSS article here: Fulfilling the Need for Speed: A brief introduction to parallel processing in the R environment. -- Ed.

By Dr. Richard Herrington, Research and Statistical Support Consultant

There has been a trend in publishing “Top 10” lists of the most essential R packages. We would be remiss to not include our own “Top” list of essential R packages that we believe are critical for users who are beginning to use R. We include packages that are both data manipulation oriented and also modeling oriented.  Most if not all of these packages can be found at:

http://cran.r-project.org/web/packages/available_packages_by_name.html

These distinctions are somewhat arbitrary;  we list the packages that we have had the most experience with and have found useful.

Data Manipulation and Modeling

  • Hmisc   
  • MASS   
  • car   
  • Zelig   
  • plyr   
  • stringr   
  • reshape2 

Packages Oriented Toward Graphical Rendering and Report Generation

  • gplots   
  • ggplot2   
  • lattice   
  • latticeExtra   
  • rgl  
  • igraph  
  • knitr

Packages Oriented Primarily Towards Modeling

 Linear, nonlinear and random effects regression 

  • nlme 
  • lme4  
  • mgcv  
  • effects   

Psychometric packages 

 

  • sem  
  • lavaan   
  • lava   
  • mirt  
  • aspect  
  • caTools  
  • mokken  
  • psych

Model selection and time series imputation 

 

  • rpart 
  • rrp 
  • forecast 
  • leaps
  • relaimpo
  • relimp
  • MARSS 
  • strucchange
  • mvtnorm

Supporting Software Installations

We would also include as essential the set of compilation tools -  Rtools, found at: http://cran.r-project.org/bin/windows/Rtools/. Rtools is required if you are interesting in compiling an existing R pacakges or creating your own R package.

And lets not forget the wonderful R IDE Rstudio found at:  https://www.rstudio.com/ide/

Until next time, this concludes our short, but essential list of R tools.  

Originally published April 2014 -- Please note that information published in Benchmarks Online is likely to degrade over time, especially links to various Websites. To make sure you have the most current information on a specific topic, it may be best to search the UNT Website - http://www.unt.edu . You can also consult the UNT Helpdesk - http://www.unt.edu/helpdesk/. Questions and comments should be directed to benchmarks@unt.edu.