tails for thselect.vmetricsthselect.egp for threshold selection with tests similar to Northop and Coleman routine.thselect.cbm for threshold selection with semiparametric bootstrap mean square error estimation of shape parameter.thselect.vmetric argument ci has been renamed to level (backward compatible).method for tstab.egp and tstab.gp now has "lrt" instead of "profile" (choice backward compatible).thselect.sdinfo gains an argument k to select the number of gaps, and returns a threshold thresh0 and k as part of the object output. The print method has been modified to reflect this.pegp did not work, and did not correctly handle lower.tail argument.degp and regp correctly handle the case shape=0 for models pt-beta and pt-gamma.thselect.mdps now return shape parameter (rather than reciprocal shape), consistent with other semiparametric methodsthselect.pickands now correctly handles user-provided threshold vectors.fit.egp fails to obtain standard errors.print method for thselect.egp is more explicit about the lack of threshold returned if the hypothesis is rejected at the highest threshold considered (which returns NA).thselect.ncpgp now passes ordered thresholds to inner function to avoid warning messages.shape.hill now provides more informative error messages when passing vectors of invalid number of exceedances k.Major release with breaking changes (mostly function names and arguments) for more coherence. Many functions now flagged as deprecated, but changes to the syntax are often backward compatible.
fit.wgpd and suggested weights Stein_weights.fit.shape and specific routines shape.hill, shape.erm, shape.genjack, shape.lthill, shape.trunhill, shape.rbm, shape.moment, shape.pickands, shape.osz, shape.genquant and shape.vries.fit.rho (four estimators available, via rho.dk, rho.fagh, rho.gbw and rho.ghp).gpd.lmom.kjtail) and through xdep.eta.qweissman)dgeoaniso for geometric anisotropy, using the parametrization of Rai and Brown (2025)maxstable for changes of parameters for GEV.egp.pll). This also affects the plotting routines. The nomenclature has been modified for argument 'model' in egp.fit, egp.ll and egp.retlev with backward compatibility.thselect.alrs, thselect.bab, thselect.cv, theselect.expgqt, thselect.gbw, thselect.mdps, thselect.mrl (which supersedes automrl), thselect.pec, thselect.pickands, thselect.rbm, thselect.samsee,tstab.hill, tstab.lthill (with different diagnostics), tstab.mrlPickandsXU is deprecated and replaced with shape.oszfit.gpd with method obre now returns ordered exceedances and weights.spunif now correctly handles missing values.gev and gp now fully vectorized with respect to arguments, including shape parameterconfint.eprof has an argument for boundary non-regular null distribution (for the most common case).fit.egp, egp.retlev, tstab.egp. The former now allows fixed parameters (for profiling).thselect. Their arguments are somewhat standardized, and they each have distinct plot and print methods with automatic selection.tstab.xdep., including xdep.chi, xdep.eta, xdep.chibar and xdep.asym. The first three call taildep, the last one supersedes xasym.lambdadep deprecated, replaced with adf to better comply with current nomenclature.automrl deprecated in favour of thselect.mrl.chibar removed in favour of xdep.chibar.extcoef for marginal transformation margtrans have been modified (backward compatible changes).fit.egp now includes alternative arguments to select the optimization routinejac has been replaced by jac_gpd_pareto to avoid ambiguitymaxstabtest) and independence via score (scoreindep) now renamed test.maxstab and test.scoreindepinfomat.test now thselect.sdinfo, vmetric now thselect.vmetric, W.diag now thselect.wseq, NC.diag now thselect.ncpgpxasym modified to make syntax more uniform.mvrnorm renamed to rmvnorm.adf now allow for values above 1 for bivariate angular dependence function..infomat needs not have data argument.gpd.ll and gpd.nll correctly return a non-NA value when xi=-1 (#18, reported by Paddy O'Toole)tstab.gpd now correctly works when input leads to boundary values, and profile likelihood intervals are now correctly truncated in the range of admissible valuesfit.gpd now relies on gpd.ll to return the negative log likelihood value nllhgp.tstab optimization bounds for profile confidence interval fixed.rparp failed when a single draw was accepted (due to matrix being cast to vectors)fit.extgp now handles model 0 (generalized Pareto), fixing #17gev and gp distribution functions (d/p/q/r) introduced to remove dependency on evd package.taildep function now correctly check choice of estimators against list of methodslikmgp and clikmgp for the logistic modeltaildep arguments leads to faster calculations with betacop option.nloptr dependency by Rsolnprmev, following Ballani and Schlather (2011)fit.gpd, fit.gev, etc.) now accept fixed parametersanova method for mev_gpd and mev_gev objectsrmev and rmevspec now accept a distance matrix in place of coordinates for spatial models.W.diag and NC.diag now have S3 plot and print methodsxdat throughoutext.coef correctly handles arrays with missing values (reported by M. Jousset)fit.gev now uses the PWM solution of Hosking (1985) as starting valuegev.pll now returns confidence intervals for param = "quant" (reported by D. Dupuis)fit.pp, fit.gev and fit.rlarg now return correct MLE when solution lies on boundary (xi=-1) and are more robust to failure (gradients for nlminb return large values rather than NA which caused the algorithm to stop).fit.gpd(..., method = "obre") now returns additional failure messages if the algorithm drifts towards infeasible values.rparp now correctly handles xi=0W.diag and egp.fitrange include arguments for changing 'par' (#10)smith.penult now computes reciprocal hazard and it's derivative on the log scale (when possible) to avoid numerical overflow.rlarg.infomat incorrect sign for expected information for d=1rmev function did not work properly for alog and aneglog (reported by Michael Lalancette)egp.retlev now returns invisible object (new ordering and format).lax packagetaildep is multivariate equivalent to evd::chiplotrparpcs for simulating from elliptical Pareto processes associated with maxrgparp for simulation of generalized R Pareto processesspunif for semi-parametric transform to uniform (tail modelled using GP)rparp now has attributes to give acceptance rate of accept/reject procedure.extcoeffit.gev, fit.gpd, fit.rlarg and fit.pp for maximum likelihood estimationmev_ objectsW.diag function, use of expected information matrix, change to default tuning parametereskrain, maiquetia, nidd, venice, w1500mrmev with extremal Student family was incorrectrparp now has a hard bound to ensure the vector of simulated vectors fits in memory.ext.index: number of exceedances off by one, causing Inf in weight vector for lm (thanks to @MCristinaMiranda). Warnings now silenced by default.rmev, rparp, etc. now use coord instead of loc to avoid confusion with location parameter in rgparpismev, rootsolve (replaced with nleqslv routine) and numDeriv.smith.penult function has new arguments (backward compatible). The quantiles 'u' are now returned for Smith penultimate approximations with method = "pot"rparp for simulation from R-Pareto Processes via rejection samplinggev.pll and gpd.pll for penalized profile likelihood and tangent exponential model approximationschibar, angextrapo and lambdadep for bivariate and multivariate model estimation, based on work of Tawn et al.gev.mle and gpd.mle for maximum likelihood estimates of transformed parametersgev.abias and gpd.abias for asymptotic bias of block maxima for fixed sample sizes or fixed thresholdsrmev, rmevspec, etc. now only accept variogram functions vario that have distance as argumentrmev and rmevspec now faster due to refactoring of codesmith.penult now has a 'family' as argument for specifying distributions via a stringgev.tem and gpd.tem are now wrappers for gev.pll and gpd.pll, respectively. Routine should be more robustinfomat.test (thanks to P. Northrop)"br" now simulates from stationary version only if argument 'sigma' is provided, and otherwise samples intrinsically Gaussian processesinfomat.test'negdir' model to rmev familiesangmeas to include different weighting if the region of interest is 'max' or 'min'angmeas in the bivariate case that would cause the method to crashfit.egp with model egp2rmev, etc.: model "br" is now distinct from "hr"ext.index Extremal index estimates based on interexceedance and gap timesinfomat.test Information matrix test of Suveges and Davison (2010)gp.fit MCMCgp.fit ample changes to the function, in particular a fix for the printing method, handling of errors and inclusion of the Zhang (2010) method and MCMC algorithm for the latter. This function is still preliminary and may updated in the nearby future to include further possibilities."ef"aneglog, given that the later is not a valid DF according to Stephenson).rmev can now return arrays for random fields on regular grids ("hr","exstud" and "smith" models)."sm" only.rdirspec and rbilogspec to internal functions along with other functions.rPextstud setting arguments of newly created arma vector to zeroInitial submission
thames and cheeseborowindrmar1 for first-order maximum autoregressive processesgev.boot for Gaussian approximation to GEV, to be used in parametric bootstrap schemestest.blocksize, build.blocks, fit.gevblock, qqplot.blocksize for tests of max-stability based on comparison of block maxima, from Belzile and Davison (2026).test.unif) and quantile-quantile plots for uniforms with binomial confidence intervals (qqplot.unif).neval for thselect.vmetric replaced by pp to let users directly select probability points, as suggested in Collings et al. (2025)fit.gpd now allows for returnsamp parameter to disable return of vector of exceedances."pwm" implemented for fit.gpd.Rf_errorxdep.xindex is now more robust to boundary cases when theta=1, and returns upper confidence intervals even when the standard error cannot be obtained. The profile likelihood method also works for these cases.