Stochastic Process Simulation Engine for R
A modular, research-grade simulator for stochastic processes with variance reduction, parallel execution, and rich visualization.
# From source tarball
install.packages("StochSimR_1.0.0.tar.gz", repos = NULL, type = "source")
# Or from local directory
devtools::install_local("path/to/StochSimR")library(StochSimR)
# Simulate and visualise Brownian motion
paths <- sim_brownian(T_max = 1, n_steps = 1000, n_paths = 100)
plot_paths(paths, show_mean = TRUE, show_bands = TRUE)
# Stock price model (GBM)
stock <- sim_gbm(T_max = 1, n_steps = 252, mu = 0.08, sigma = 0.25,
x0 = 100, n_paths = 50)
plot_paths(stock)
plot_distribution(stock)
path_summary(stock)See vignette("introduction", package = "StochSimR") for the full tutorial.
| Process | Function | Methods |
|---|---|---|
| Poisson | sim_poisson() |
exact, thinning |
| Brownian Motion | sim_brownian() |
exact, bridge |
| Markov Chain | sim_markov() |
exact |
| Geometric Brownian Motion | sim_gbm() |
exact, euler |
| Ornstein-Uhlenbeck | sim_ou() |
exact, euler |
| Levy Processes | sim_levy() |
stable, gamma, NIG, variance-gamma |
| Jump-Diffusion | sim_jump_diffusion() |
euler |
| Hawkes Process | sim_hawkes() |
ogata thinning |
MIT