texmex2.4.9 package

Statistical Modelling of Extreme Values

addExcesses

Annotate a threshold selection ggplot

AIC.evmOpt

Information Criteria

airPollution

Air pollution data, separately for summer and winter months

bootmex

Bootstrap a conditional multivariate extreme values model

chi

Measures of extremal dependence

copula

Calculate the copula of a matrix of variables

cv.evmOpt

Cross-validation for the shape parameter in an extreme values model

cv

Cross-validation for a model object

degp3

Density, cumulative density, quantiles and random number generation fo...

dgev

Density, cumulative density, quantiles and random number generation fo...

dglo

Generalized logistic distribution

dgpd

Density, cumulative density, quantiles and random number generation fo...

dgumbel

The Gumbel distribution

dot-exprel

Accurately compute (exp(x) - 1) / x

dot-log1mexp

Accurately compute log(1-exp(x))

dot-log1prel

Accurately compute log(1 + x) / x

dot-specfun.safe.product

Compute pmax(x y, -1) in such a way that zeros in x beat infinities in...

edf

Compute empirical distribution function

egp3RangeFit

Estimate the EGP3 distribution power parameter over a range of thresho...

endPoint

Calculate upper end point for a fitted extreme value model

evm

Extreme value modelling

evmBoot

Bootstrap an evmOpt fit

evmSim

MCMC simulation around an evmOpt fit

evmSimSetSeed

Set the seed from a fitted evmSim object.

extremalIndex

Extremal index estimation and automatic declustering

ggplot.copula

Fancy plotting for copulas

ggplot.declustered

Diagnostic plots for an declustered object

ggplot.evmBoot

Diagnostic plots for the replicate estimated parameter values in an ev...

ggplot.evmOpt

Diagnostic plots for an evm object

ggplot.evmSim

Diagnostic plots for the Markov chains in an evmSim object

ggplot.rl.evmOpt

Plotting function for return level estimation

gpd.prof

Profile likelihood based confidence intervals for GPD

gpdRangeFit

Estimate generalized Pareto distribution parameters over a range of va...

JointExceedanceCurve

Joint exceedance curves

logLik.evmOpt

Log-likelihood for evmOpt objects

makeReferenceMarginalDistribution

Provide full marginal reference distribution for for maringal transfor...

MCS

Multivariate conditional Spearman's rho

mex

Conditional multivariate extreme values modelling

mexDependence

Estimate the dependence parameters in a conditional multivariate extre...

mexMonteCarlo

Simulation from dependence models

mexRangeFit

Estimate dependence parameters in a conditional multivariate extreme v...

migpd

Fit multiple independent generalized Pareto models

migpdCoefs

Change values of parameters in a migpd object

mrl

Mean residual life plot

plot.copula

Plot copulas

plot.evmOpt

Plots for evmOpt objects

plot.evmSim

Plots for evmSim objects

predict.evmOpt

Predict return levels from extreme value models, or obtain the linear ...

print.evmOpt

Print evmOpt objects

rFrechet

Extreme Value random process generation.

rl

Return levels

rMaxAR

Extreme Value random process generation.

simulate.evmOpt

Simulate from a fitted evm object

texmex-package

Extreme value modelling

texmexFamily

Create families of distributions

thinAndBurn

Process Metropolis output from extreme value model fitting to discard ...

Statistical extreme value modelling of threshold excesses, maxima and multivariate extremes. Univariate models for threshold excesses and maxima are the Generalised Pareto, and Generalised Extreme Value model respectively. These models may be fitted by using maximum (optionally penalised-)likelihood, or Bayesian estimation, and both classes of models may be fitted with covariates in any/all model parameters. Model diagnostics support the fitting process. Graphical output for visualising fitted models and return level estimates is provided. For serially dependent sequences, the intervals declustering algorithm of Ferro and Segers (2003) <doi:10.1111/1467-9868.00401> is provided, with diagnostic support to aid selection of threshold and declustering horizon. Multivariate modelling is performed via the conditional approach of Heffernan and Tawn (2004) <doi:10.1111/j.1467-9868.2004.02050.x>, with graphical tools for threshold selection and to diagnose estimation convergence.