Parallel and Other Simulations in R Made Easy: An End-to-End Study

Published on Feb 24, 2016in Journal of Statistical Software11.65
· DOI :10.18637/jss.v069.i04
Marius Hofert16
Estimated H-index: 16
Martin Mächler16
Estimated H-index: 16
It is shown how to set up, conduct, and analyze large simulation studies with the new R package simsalapar (= simulations simplified and launched parallel). A simulation study typically starts with determining a collection of input variables and their values on which the study depends. Computations are desired for all combinations of these variables. If conducting these computations sequentially is too time-consuming, parallel computing can be applied over all combinations of select variables. The final result object of a simulation study is typically an array. From this array, summary statistics can be derived and presented in terms of flat contingency or LATEX tables or visualized in terms of matrix-like figures. The R package simsalapar provides several tools to achieve the above tasks. Warnings and errors are dealt with correctly, various seeding methods are available, and run time is measured. Furthermore, tools for analyzing the results via tables or graphics are provided. In contrast to rather minimal examples typically found in R packages or vignettes, an end-to-end, not-so-minimal simulation problem from the realm of quantitative risk management is given. The concepts presented and solutions provided by simsalapar may be of interest to students, researchers, and practitioners as a how-to for conducting realistic, large-scale simulation studies in R.
  • References (14)
  • Citations (3)
#2Steve WestonH-Index: 3
60 Citations
126k Citations
62 CitationsSource
122 CitationsSource
395 CitationsSource
#1Manuel J. A. Eugster (LMU: Ludwig Maximilian University of Munich)H-Index: 13
#2Jochen Knaus (University Medical Center Freiburg)H-Index: 3
Last.Esmeralda Vicedo (LMU: Ludwig Maximilian University of Munich)H-Index: 7
view all 5 authors...
14 CitationsSource
#1Andreas AlfonsH-Index: 8
#2Matthias TemplH-Index: 17
Last.Peter FilzmoserH-Index: 45
view all 3 authors...
25 CitationsSource
#1Hadley WickhamH-Index: 25
7,925 Citations
#1Deepayan SarkarH-Index: 15
825 Citations
#1Alexander J. McNeilH-Index: 33
#2Rdiger FreyH-Index: 1
Last.Paul EmbrechtsH-Index: 51
view all 3 authors...
1,851 Citations
Cited By3
#1Marie-Pier Côté (Laval University)H-Index: 4
#2Christian Genest (McGill University)H-Index: 42
Last.Marek Omelka (Charles University in Prague)H-Index: 15
view all 3 authors...
1 CitationsSource
#1Alba Martinez-Ruiz (Catholic University of the Most Holy Conception)
#2Cristina Montañola-Sales (Barcelona Supercomputing Center)H-Index: 4
#1Christian Hering (University of Ulm)H-Index: 3
#2Marius Hofert (TUM: Technische Universität München)H-Index: 16
10 CitationsSource