Simulation from R-Pareto processes
Arguments
- n
number of observations
- shape
shape tail index of Pareto variable
- risk
string indicating risk functional.
- siteindex
integer between 1 and d specifying the index of the site or variable
- d
dimension of sample
- param
parameter vector for the logistic, bilogistic, negative bilogistic and extremal Dirichlet (Coles and Tawn) model. Parameter matrix for the Dirichlet mixture. Degree of freedoms for extremal student model. See Details.
- sigma
covariance matrix for Brown-Resnick and extremal Student-t distributions. Symmetric matrix of squared coefficients \(\lambda^2\) for the Husler-Reiss model, with zero diagonal elements.
- model
for multivariate extreme value distributions, users can choose between 1-parameter logistic and negative logistic, asymmetric logistic and negative logistic, bilogistic, Husler-Reiss, extremal Dirichlet model (Coles and Tawn) or the Dirichlet mixture. Spatial models include the Brown-Resnick, Smith, Schlather and extremal Student max-stable processes. Max linear models are also supported
- weights
vector of length
m
for them
mixture components that sum to one. For the"maxlin"
model, weights should be a matrix withd
columns that represent the weight of the components and whose column sum to one (if provided, this argument overridesasy
).- vario
semivariogram function whose first argument must be distance. Used only if provided in conjunction with
coord
and ifsigma
is missing- coord
d
byk
matrix of coordinates, used as input in the variogramvario
or as parameter for the Smith model. Ifgrid
isTRUE
, unique entries should be supplied.- ...
additional arguments for the
vario
function
Value
an n
by d
sample from the R-Pareto process, with attributes
accept.rate
if the procedure uses rejection sampling.
Details
For riskf=max
and riskf=min
, the procedure uses rejection sampling based on Pareto variates
sampled from sum
and may be slow if d
is large.
Examples
rparp(n=10, risk = 'site', siteindex=2, d=3, param=2.5, model='log')
#> [,1] [,2] [,3]
#> [1,] 1.5105721 2.062201 3.8114402
#> [2,] 0.8278662 10.194357 0.6829412
#> [3,] 4.6320032 3.569126 6.0419012
#> [4,] 0.2875454 1.522112 0.2000385
#> [5,] 3.2483324 3.627769 4.5665723
#> [6,] 3.8668812 7.218984 2.9432878
#> [7,] 0.8773408 1.567841 0.5226220
#> [8,] 2.1739006 1.431146 1.6115397
#> [9,] 0.5602710 1.180479 0.4143992
#> [10,] 1.1366353 1.338458 0.9827565
rparp(n=10, risk = 'min', d=3, param=2.5, model='neglog')
#> [,1] [,2] [,3]
#> [1,] 33.651282 32.628657 36.777860
#> [2,] 2.289407 1.320429 1.082012
#> [3,] 3.890172 4.142920 3.105207
#> [4,] 17.213907 44.376318 25.882896
#> [5,] 1.003407 4.835356 4.503946
#> [6,] 1.735442 2.468705 1.749003
#> [7,] 3.783245 7.845791 5.585949
#> [8,] 18.959474 28.104456 4.498391
#> [9,] 2.505521 2.831427 2.555628
#> [10,] 3.590155 4.091380 4.485327
#> attr(,"accept.rate")
#> [1] 0.06034483
rparp(n=10, risk = 'max', d=4, param=c(0.2,0.1,0.9,0.5), model='bilog')
#> [,1] [,2] [,3] [,4]
#> [1,] 5.615579e-01 7.241260e-01 7.52868001 6.990548e-01
#> [2,] 4.247099e-09 5.490106e-09 1.53206026 5.865514e-09
#> [3,] 9.049350e-09 8.407775e-09 1.43406741 2.951890e-09
#> [4,] 4.397482e-01 5.616788e-01 0.04895930 1.297957e+00
#> [5,] 5.413925e-01 5.394913e-01 1.03096453 2.550636e-01
#> [6,] 7.770202e-01 8.359705e-01 0.34935358 1.565462e+00
#> [7,] 6.494626e-01 9.130293e-01 0.05727966 1.063859e+00
#> [8,] 1.797197e+00 2.673083e+00 1.96182400 1.714274e+00
#> [9,] 1.500466e+00 1.102379e+00 0.58961832 3.720106e+00
#> [10,] 1.606594e+00 2.410398e+00 0.90506318 3.345717e+00
#> attr(,"accept.rate")
#> [1] 0.5217391
rparp(n=10, risk = 'sum', d=3, param=c(0.8,1.2,0.6, -0.5), model='sdir')
#> [,1] [,2] [,3]
#> [1,] 9.104744e-05 2.071385e-04 1.6097458
#> [2,] 5.476041e-08 3.672983e-08 2.9336700
#> [3,] 9.973839e-01 1.472759e+00 0.1723525
#> [4,] 1.351353e+00 1.861590e+00 0.1766897
#> [5,] 2.347773e-05 4.848226e-05 1.2938706
#> [6,] 4.442986e-05 4.845116e-05 1.7039216
#> [7,] 4.365792e-04 4.318277e-04 1.1434435
#> [8,] 5.990411e-01 1.652170e+00 0.5050968
#> [9,] 6.962892e-01 3.485243e-01 0.1028635
#> [10,] 2.572016e-03 1.499202e-03 1.6158909
vario <- function(x, scale=0.5, alpha=0.8){ scale*x^alpha }
grid.coord <- as.matrix(expand.grid(runif(4), runif(4)))
rparp(n=10, risk = 'max', vario=vario, coord=grid.coord, model='br')
#> [,1] [,2] [,3] [,4] [,5] [,6] [,7]
#> [1,] 0.5528546 0.8751382 1.6173497 0.9656937 0.5154121 0.6764602 1.8710370
#> [2,] 0.9280015 1.1937342 1.3297882 1.1801997 0.7815639 0.7331329 0.7901323
#> [3,] 0.6274595 0.7155517 0.1400654 0.6796430 0.6718651 0.8651137 0.4186019
#> [4,] 1.4667472 1.4653086 1.6198180 1.3881891 2.0053048 1.9622947 2.8102139
#> [5,] 2.5137263 2.8814500 2.3622395 2.8055104 1.6969590 1.9390104 2.1811882
#> [6,] 0.5590363 0.5289341 1.0113552 0.5708733 0.4750926 0.3556360 2.6846267
#> [7,] 1.8931829 0.8590269 0.5054569 0.9543044 1.4664657 2.3200105 1.4442089
#> [8,] 0.5237581 0.2283091 0.8040367 0.2845403 0.5585327 0.5996641 1.7552698
#> [9,] 0.6597270 1.2522140 0.5133811 1.0038005 1.2805866 1.1756161 2.2335945
#> [10,] 0.6786599 0.4851475 1.6656314 0.3678618 0.5230716 0.8875996 0.7015881
#> [,8] [,9] [,10] [,11] [,12] [,13] [,14]
#> [1,] 0.8293672 0.9418955 1.1789628 1.0270113 1.1057200 0.5941734 0.4327573
#> [2,] 0.6969163 1.2321408 1.2240548 0.8597080 0.9896628 0.7095739 0.7067637
#> [3,] 0.7198967 0.8530125 0.6301378 0.1198791 0.8439146 0.8512862 1.1018493
#> [4,] 1.8458849 1.5147027 1.5736124 4.3638941 1.3615597 2.3475146 1.7560127
#> [5,] 2.2384305 2.2457703 3.4125943 2.1209164 3.6950584 1.0986633 1.3369853
#> [6,] 0.3435974 0.5490592 0.4009056 0.9220610 0.3967821 0.5385041 0.3011957
#> [7,] 1.8315710 0.9149645 1.1706802 0.7519990 1.2788392 2.5338628 1.9646215
#> [8,] 0.6168899 0.8926574 0.3584376 1.3454552 0.3299555 0.4365769 0.4102402
#> [9,] 1.0828572 0.7379972 1.2130437 1.1070612 1.0900599 1.6078698 1.8702422
#> [10,] 0.9793814 0.9013966 1.0245878 0.8860415 0.9826741 0.6466970 0.5603992
#> [,15] [,16]
#> [1,] 1.5861529 0.3990939
#> [2,] 0.6995806 0.7634090
#> [3,] 0.5690132 0.9920307
#> [4,] 2.7637642 2.0629867
#> [5,] 1.4554163 1.4246000
#> [6,] 1.6644094 0.4484652
#> [7,] 1.4124012 1.9674712
#> [8,] 1.4366822 0.4007914
#> [9,] 2.3090938 1.5884943
#> [10,] 0.5471703 0.7588555
#> attr(,"accept.rate")
#> [1] 0.09444444