Winsorized ARMA Estimation for Higher-Order Stochastic Volatility Models R package wARMASVp version 0.1.0 Estimation, simulation, hypothesis testing, and forecasting for univariate higher-order stochastic volatility SV(p) models. Supports Gaussian, Student-t, and Generalized Error Distribution (GED) innovations, with optional leverage effects. Estimation uses closed-form Winsorized ARMA-SV (W-ARMA-SV) moment-based methods that avoid numerical optimization. Hypothesis testing includes Local Monte Carlo (LMC) and Maximized Monte Carlo (MMC) procedures for leverage effects, heavy tails, and autoregressive order selection. Forecasting is based on Kalman filtering and smoothing. See Ahsan and Dufour (2021) <doi:10.1016/j.jeconom.2020.01.018>, Ahsan, Dufour, and Rodriguez Rondon (2025) for details. Software Imports: Rcpp (>= 1.0.0), gsignal, stats LinkingTo: Rcpp, RcppArmadillo Suggests: pso, GenSA, testthat (>= 3.0.0), knitr, rmarkdown Gabriel Rodriguez Rondon <gabriel.rodriguezrondon@mail.mcgill.ca> Comprehensive R Archive Network (CRAN) Gabriel Rodriguez Rondon [aut, cre] (ORCID: <https://orcid.org/0009-0005-3769-9921>), Nazmul Ahsan [aut], Jean-Marie Dufour [aut] GPL (>= 3) 2026-04-22 application/tgz https://CRAN.R-project.org/package=wARMASVp doi:10.32614/CRAN.package.wARMASVp