H d

1 R/S method 0.9323121 0.4323121

2 Simple R/S Hurst estimation 0.8383356 0.3383356
3 Corrected R over S Hurst exponent 0.9852728 0.4852728
4 Differenced aggregated variance method 1.532846 1.032846
5 Aggregated variance method 0.8654437 0.3654437
6 Absolute values (moments) method 0.9390823 0.4390823
7 Periodogram and cumulated periodogram 1.54849 1.04849
method
8 Boxed (modified) peridogram method 1.480201 0.9802006
9 Higuchi's method 0.9686715 0.4686715
10 Hurst coefficient by Robinson's 0.9999007 0.4999007
11 estimates the long memory prarameter using 0.9177692 0.4177692
wavelets
12 Whittle estimator for fractional Gaussian noise 0.989925 0.49
13 Geweke and Porter-Hudak (GPH) 1.051468
14  Reisen (1994) estimator 0.257038
15 maximum likelihood estimators of the 0.4996334
parameters of a fractionally-differenced
ARIMA
16 Semiparametric local Whittle estimator 0.9692414
17 Exact MLE 0.995 0.495

Arfima models based on R/S method

Best model of these subset of ARMA models are marked by yellow color

ar ma sigmaa log_likelhood akiki_aic adj_aic bayesian_bic ljung_box

1 0 0 0.0003821587 1718.859 -3433.718 -3433.701 -3424.665 0
2 0 1 0.0001928528 1952.595 -3899.19 -3899.154 -3885.61 0
3 0 2 0.0001501287 2038.532 -4069.064 -4069.005 -4050.958 0
4 0 3 0.0001296592 2089.007 -4168.015 -4167.926 -4145.382 0
5 0 4 0.0001215925 2111.419 -4210.838 -4210.714 -4183.679 0
6 1 0 0.0001055537 2158.089 -4310.178 -4310.143 -4296.599 0.0429851
7 1 1 0.0001043767 2162.405 -4316.811 -4316.752 -4298.705 0.2103699
8 1 2 0.0001036374 2165.316 -4320.632 -4320.544 -4298 0.2610785
9 1 3 0.0001034381 2166.462 -4320.925 -4320.801 -4293.766 0.1949256
10 1 4 0.0001025047 2170.016 -4326.033 -4325.867 -4294.347 0.5714623
11 2 0 0.0001046311 2161.578 -4315.157 -4315.098 -4297.051 0.1685158
12 2 1 0.0001020792 2170.422 -4330.844 -4330.756 -4308.212 0.7845029
13 2 2 0.0001022231 2170.441 -4328.883 -4328.759 -4301.724 0.7238185
14 2 3 0.0001023749 2170.442 -4326.885 -4326.719 -4295.199 0.6390551
15 2 4 0.0001024934 2170.57 -4325.139 -4324.926 -4288.927 0.5972437
16 3 0 0.0001040633 2163.928 -4317.856 -4317.768 -4295.224 0.2394404
17 3 1 0.0001022248 2170.441 -4328.882 -4328.758 -4301.723 0.7208716
18 3 2 0.0001023772 2170.432 -4326.864 -4326.698 -4295.179 0.6354881
19 3 3 0.000102506 2170.504 -4325.007 -4324.794 -4288.795 0.5583051
20 3 4 0.0001024403 2171.222 -4324.445 -4324.177 -4283.706 0.6400946
21 4 0 0.0001040882 2164.348 -4316.695 -4316.571 -4289.536 0.183883
22 4 1 0.0001023721 2170.452 -4326.903 -4326.737 -4295.218 0.6402956
23 4 2 0.0001023599 2170.997 -4325.994 -4325.78 -4289.782 0.6792085
24 4 3 0.000101223 2173.454 -4328.908 -4328.64 -4288.169 0.655355
25 4 4 0.0001025418 2171.395 -4322.789 -4322.462 -4277.524 0.5941576

ARMA (3,0.432,1) Coefficients

 Conditional-Sum-of-Squares & Maximum Likelihood Estimation
Estimate S.E t.value p.value Lag
MU -0.00344 0.0055 -0.625 5.32e-01 1
AR 1 1.61726 0.0635 25.453 0.00e+00 1
AR 2 -0.61749 0.0743 -8.312 5.12e-16 2
AR 3 -0.00784 0.0429 -0.183 8.55e-01 3
MA 1 -0.88134 0.0505 -17.445 1.42e-56 1

ARIMA(4,0,3) model is estimated for variable: dHRS

Conditional-Sum-of-Squares & Maximum Likelihood Estimation

Estimate S.E t.value p.value Lag
MU -0.00363 0.00645 -0.564 5.73e-01 1
AR 1 0.78039 0.04659 16.749 0.00e+00 1
AR 2 -0.19648 0.00982 -20.005 2.89e-70 2
AR 3 1.06146 0.01144 92.810 0.00e+00 3
AR 4 -0.66072 0.04731 -13.964 4.08e-39 4
MA 1 -0.03270 0.02924 -1.118 2.64e-01 1
MA 2 0.21160 0.02781 7.610 9.24e-14 2
MA 3 -0.90434 0.02919 -30.984 8.53e-132 3

Arfima models based on Simple R/S Hurst estimation

Best model of these subset of ARMA models are marked by yellow color

ar ma sigmaa log_likelhood akiki_aic adj_aic bayesian_bic ljung_box

1 0 0 0.0006377975 1543.948 -3083.896 -3083.878 -3074.843 0
2 0 1 0.0002713663 1835.838 -3665.676 -3665.64 -3652.096 0
3 0 2 0.000187315 1962.786 -3917.573 -3917.514 -3899.467 0
4 0 3 0.0001512699 2036.173 -4062.347 -4062.258 -4039.714 0
5 0 4 0.00013577 2073.553 -4135.106 -4134.982 -4107.947 0
6 1 0 0.0001041204 2162.493 -4318.987 -4318.951 -4305.407 0.2267121
7 1 1 0.0001036871 2164.413 -4320.826 -4320.767 -4302.72 0.2691774
8 1 2 0.0001031282 2166.747 -4323.493 -4323.405 -4300.861 0.272274
9 1 3 0.0001030258 2167.58 -4323.161 -4323.036 -4296.002 0.2027159
10 1 4 0.0001022086 2170.767 -4327.535 -4327.369 -4295.849 0.5127033
11 2 0 0.0001037808 2164.106 -4320.211 -4320.152 -4302.105 0.2628653
12 2 1 0.0001017387 2171.322 -4332.644 -4332.556 -4310.012 0.7711273
13 2 2 0.00010187 2171.386 -4330.771 -4330.647 -4303.612 0.6978167
14 2 3 0.0001020182 2171.389 -4328.779 -4328.613 -4297.093 0.6130425
15 2 4 0.000101978 2172.026 -4328.052 -4327.839 -4291.84 0.6668756
16 3 0 0.0001033756 2165.936 -4321.872 -4321.783 -4299.239 0.2736957
17 3 1 0.0001018682 2171.39 -4330.78 -4330.655 -4303.621 0.6982603
18 3 2 0.000101883 2171.842 -4329.683 -4329.517 -4297.998 0.7160641
19 3 3 0.0001020245 2171.871 -4327.741 -4327.528 -4291.529 0.6351223
20 3 4 0.0001020767 2172.194 -4326.388 -4326.12 -4285.649 0.6186295
21 4 0 0.0001034196 2166.292 -4320.583 -4320.459 -4293.424 0.2035264
22 4 1 0.0001020197 2171.389 -4328.779 -4328.613 -4297.093 0.6117439
23 4 2 0.0001020226 2171.877 -4327.754 -4327.54 -4291.542 0.6391399
24 4 3 0.0001015401 2173.694 -4329.388 -4329.121 -4288.65 0.6071574
25 4 4 0.00010211 2172.582 -4325.164 -4324.837 -4279.899 0.6219628

ARMA (2,0.338,1) Coefficients

Conditional-Sum-of-Squares & Maximum Likelihood Estimation

Estimate S.E t.value p.value Lag
MU -0.0045 0.00846 -0.532 5.95e-01 1
AR 1 1.7003 0.06605 25.744 0.00e+00 1
AR 2 -0.7055 0.06350 -11.111 1.81e-26 2
MA 1 -0.8793 0.04891 -17.978 2.12e-59 1

Arfima models based Corrected R over S Hurst exponent

Best model of these subset of ARMA models are marked by yellow color

ar ma sigmaa log_likelhood akiki_aic adj_aic bayesian_bic ljung_box

1 0 0 0.000297679 1804.173 -3604.346 -3604.328 -3595.293 0
2 0 1 0.0001658188 2004.229 -4002.459 -4002.423 -3988.879 0
3 0 2 0.0001364991 2071.111 -4134.223 -4134.164 -4116.117 0
4 0 3 0.0001216529 2110.86 -4211.72 -4211.631 -4189.087 0
5 0 4 0.0001162579 2126.833 -4241.666 -4241.542 -4214.507 0
6 1 0 0.0001060771 2156.528 -4307.056 -4307.021 -4293.477 0.01228535
7 1 1 0.000104588 2161.84 -4315.679 -4315.62 -4297.573 0.1943759
8 1 2 0.000103836 2164.786 -4319.571 -4319.483 -4296.939 0.273709
9 1 3 0.0001036108 2166.012 -4320.025 -4319.901 -4292.866 0.2037187
10 1 4 0.0001026618 2169.613 -4325.226 -4325.06 -4293.54 0.6180658
11 2 0 0.0001049221 2160.756 -4313.511 -4313.452 -4295.406 0.1267386
12 2 1 0.0001023179 2169.746 -4329.491 -4329.403 -4306.859 0.7737155
13 2 2 0.0001024396 2169.84 -4327.679 -4327.555 -4300.52 0.7344621
14 2 3 0.0001025891 2169.851 -4325.702 -4325.536 -4294.017 0.650249
15 2 4 0.0001025705 2170.411 -4324.823 -4324.609 -4288.611 0.6864008
16 3 0 0.0001043221 2163.206 -4316.411 -4316.323 -4293.779 0.2258034
17 3 1 0.0001024404 2169.841 -4327.683 -4327.559 -4300.524 0.7308539
18 3 2 0.0001025976 2169.823 -4325.646 -4325.48 -4293.961 0.6423399
19 3 3 0.0001025786 2170.384 -4324.767 -4324.554 -4288.555 0.6858241
20 3 4 0.0001026581 2170.621 -4323.242 -4322.975 -4282.504 0.6486737
21 4 0 0.0001043549 2163.599 -4315.199 -4315.075 -4288.04 0.1797353
22 4 1 0.0001025838 2169.867 -4325.733 -4325.567 -4294.048 0.6538732
23 4 2 0.0001025643 2170.433 -4324.866 -4324.653 -4288.654 0.6983457
24 4 3 0.0001019628 2172.546 -4327.093 -4326.825 -4286.354 0.6738507
25 4 4 0.0001027731 2170.748 -4321.496 -4321.169 -4276.231 0.5913491

ARIMA(2,1) model is estimated for variable: dcorr_RS

Conditional-Sum-of-Squares & Maximum Likelihood Estimation

Estimate S.E t.value p.value Lag
MU -0.00241 0.00429 -0.562 5.74e-01 1
AR 1 1.57257 0.06411 24.529 0.00e+00 1
AR 2 -0.58295 0.05931 -9.828 2.10e-21 2
MA 1 -0.88063 0.04557 -19.325 1.24e-66 1

Arfima models based Aggregated variance method

Best model of these subset of ARMA models are marked by yellow color

ar ma sigmaa log_likelhood akiki_aic adj_aic bayesian_bic ljung_box

1 0 0 0.0005456243 1597.253 -3190.506 -3190.488 -3181.453 0
2 0 1 0.0002434907 1872.89 -3739.781 -3739.745 -3726.201 0
3 0 2 0.0001744508 1987.138 -3966.276 -3966.217 -3948.17 0
4 0 3 0.0001438513 2053.406 -4096.812 -4096.723 -4074.18 0
5 0 4 0.0001309337 2086.004 -4160.007 -4159.883 -4132.848 0
6 1 0 0.000104575 2161.086 -4316.173 -4316.137 -4302.593 0.1557805
7 1 1 0.0001039234 2163.714 -4319.427 -4319.368 -4301.321 0.2478733
8 1 2 0.0001032942 2166.274 -4322.549 -4322.46 -4299.916 0.264821
9 1 3 0.0001031588 2167.215 -4322.43 -4322.306 -4295.271 0.1970259
10 1 4 0.000102298 2170.544 -4327.087 -4326.921 -4295.402 0.5266202
11 2 0 0.0001040606 2163.265 -4318.531 -4318.472 -4300.425 0.2340652
12 2 1 0.000101821 2171.118 -4332.237 -4332.148 -4309.604 0.7815118
13 2 2 0.0001019732 2171.116 -4330.231 -4330.107 -4303.072 0.7092111
14 2 3 0.0001021182 2171.132 -4328.265 -4328.099 -4296.579 0.6206177
15 2 4 0.0001020812 2171.753 -4327.507 -4327.293 -4291.295 0.6712955
16 3 0 0.0001035976 2165.281 -4320.563 -4320.474 -4297.93 0.262056
17 3 1 0.0001019902 2171.058 -4330.117 -4329.992 -4302.958 0.7088522
18 3 2 0.0001021148 2171.143 -4328.287 -4328.121 -4296.601 0.6204216
19 3 3 0.0001022505 2171.184 -4326.368 -4326.155 -4290.156 0.5394648
20 3 4 0.0001021768 2171.931 -4325.861 -4325.594 -4285.123 0.6265083
21 4 0 0.0001036322 2165.668 -4319.337 -4319.212 -4292.178 0.1953855
22 4 1 0.0001021163 2171.136 -4328.272 -4328.106 -4296.587 0.6213743
23 4 2 0.000102115 2171.641 -4327.282 -4327.069 -4291.07 0.6542132
24 4 3 0.0001016519 2173.466 -4328.931 -4328.664 -4288.193 0.6377877
25 4 4 0.0001022346 2172.243 -4324.487 -4324.159 -4279.222 0.6144612

ARIMA(2,1) model is estimated for variable: dagg_var

Conditional-Sum-of-Squares & Maximum Likelihood Estimation

Estimate S.E t.value p.value Lag
MU -0.00421 0.00749 -0.562 5.74e-01 1
AR 1 1.67674 0.06538 25.644 0.00e+00 1
AR 2 -0.68270 0.06253 -10.918 1.11e-25 2
MA 1 -0.87845 0.04785 -18.359 1.97e-61 1

Arfima models based on Absolute values (moments) method

Best model of these subset of ARMA models are marked by yellow color

ar ma sigmaa log_likelhood akiki_aic adj_aic bayesian_bic ljung_box

1 0 0 0.0003695364 1730.329 -3456.658 -3456.641 -3447.605 0
2 0 1 0.0001888588 1959.749 -3913.499 -3913.464 -3899.919 0
3 0 2 0.000148147 2043.08 -4078.161 -4078.102 -4060.055 0
4 0 3 0.0001284958 2092.097 -4174.194 -4174.106 -4151.562 0
5 0 4 0.0001208207 2113.606 -4215.212 -4215.088 -4188.053 0
6 1 0 0.0001056352 2157.843 -4309.686 -4309.65 -4296.106 0.0368694
7 1 1 0.0001044114 2162.309 -4316.618 -4316.559 -4298.512 0.207672
8 1 2 0.0001036664 2165.238 -4320.475 -4320.386 -4297.843 0.2624048
9 1 3 0.0001034624 2166.398 -4320.796 -4320.672 -4293.637 0.1954522
10 1 4 0.0001025252 2169.964 -4325.929 -4325.763 -4294.243 0.5772525
11 2 0 0.000104677 2161.445 -4314.891 -4314.832 -4296.785 0.1625052
12 2 1 0.0001021078 2170.341 -4330.681 -4330.593 -4308.049 0.7840559
13 2 2 0.0001022511 2170.367 -4328.734 -4328.61 -4301.575 0.72393
14 2 3 0.000102401 2170.371 -4326.743 -4326.577 -4295.057 0.6410251
15 2 4 0.0001023776 2170.948 -4325.897 -4325.683 -4289.685 0.6807436
16 3 0 0.0001041024 2163.817 -4317.634 -4317.545 -4295.001 0.2374902
17 3 1 0.0001022518 2170.366 -4328.733 -4328.608 -4301.574 0.7224435
18 3 2 0.0001023253 2170.621 -4327.242 -4327.076 -4295.556 0.6904024
19 3 3 0.0001023942 2170.896 -4325.791 -4325.578 -4289.58 0.6735615
20 3 4 0.0001024672 2171.151 -4324.301 -4324.034 -4283.563 0.6413715
21 4 0 0.0001041274 2164.236 -4316.471 -4316.347 -4289.312 0.1831542
22 4 1 0.0001023986 2170.379 -4326.757 -4326.591 -4295.072 0.6422447
23 4 2 0.0001023851 2170.928 -4325.855 -4325.641 -4289.643 0.6813354
24 4 3 0.0001013797 2173.429 -4328.858 -4328.59 -4288.119 0.6477311
25 4 4 0.0001025693 2171.318 -4322.636 -4322.309 -4277.371 0.6006827

ARIMA(2,1) model is estimated for variable: dabs_val

Conditional-Sum-of-Squares & Maximum Likelihood Estimation
Estimate S.E t.value p.value Lag
MU -0.0033 0.00537 -0.615 5.39e-01 1
AR 1 1.6132 0.06427 25.102 0.00e+00 1
AR 2 -0.6216 0.06036 -10.298 3.30e-23 2
MA 1 -0.8791 0.04594 -19.138 1.28e-65 1

Arfima models based on Higuchi method

Best model of these subset of ARMA models are marked by yellow color

ar ma sigmaa log_likelhood akiki_aic adj_aic bayesian_bic ljung_box

1 0 0 0.0003208899 1778.532 -3553.065 -3553.047 -3544.012 0
2 0 1 0.0001733216 1989.1 -3972.2 -3972.165 -3958.62 0
3 0 2 0.0001403343 2061.626 -4115.251 -4115.192 -4097.145 0
4 0 3 0.0001239056 2104.568 -4199.137 -4199.048 -4176.504 0
5 0 4 0.0001177647 2122.408 -4232.815 -4232.691 -4205.656 0
6 1 0 0.0001059425 2156.923 -4307.847 -4307.811 -4294.267 0.01825478
7 1 1 0.0001045361 2161.972 -4315.943 -4315.884 -4297.837 0.1980627
8 1 2 0.0001037807 2164.93 -4319.86 -4319.772 -4297.228 0.2680192
9 1 3 0.0001035612 2166.14 -4320.28 -4320.156 -4293.121 0.2000969
10 1 4 0.000102613 2169.739 -4325.478 -4325.312 -4293.793 0.6029808
11 2 0 0.0001048481 2160.959 -4313.918 -4313.859 -4295.812 0.1383843
12 2 1 0.0001022436 2169.963 -4329.927 -4329.838 -4307.294 0.7759187
13 2 2 0.0001023719 2170.034 -4328.068 -4327.944 -4300.909 0.7292939
14 2 3 0.0001025214 2170.039 -4326.079 -4325.913 -4294.393 0.6470827
15 2 4 0.0001025004 2170.605 -4325.209 -4324.995 -4288.997 0.6850683
16 3 0 0.0001042529 2163.395 -4316.789 -4316.701 -4294.157 0.2295997
17 3 1 0.0001023705 2170.033 -4328.065 -4327.941 -4300.906 0.7309232
18 3 2 0.0001025273 2170.019 -4326.037 -4325.871 -4294.352 0.6413185
19 3 3 0.000102654 2170.099 -4324.198 -4323.984 -4287.986 0.5652639
20 3 4 0.0001025909 2170.812 -4323.623 -4323.356 -4282.885 0.6444056
21 4 0 0.0001042816 2163.801 -4315.603 -4315.479 -4288.444 0.1806991
22 4 1 0.000102517 2170.053 -4326.106 -4325.94 -4294.421 0.6494313
23 4 2 0.0001024996 2170.614 -4325.228 -4325.014 -4289.016 0.692369
24 4 3 0.0001013484 2173.032 -4328.065 -4327.797 -4287.326 0.6670982
25 4 4 0.0001027003 2170.953 -4321.905 -4321.578 -4276.64 0.5941555

ARIMA(2,1) model is estimated for variable: dhig

Conditional-Sum-of-Squares & Maximum Likelihood Estimation

Estimate S.E t.value p.value Lag
MU -0.00266 0.00454 -0.586 5.58e-01 1
AR 1 1.58327 0.06505 24.339 0.00e+00 1
AR 2 -0.59341 0.06039 -9.827 2.13e-21 2
MA 1 -0.87680 0.04690 -18.695 3.12e-63 1

Arfima models based on Hurst coefficient by Robinson's

Best model of these subset of ARMA models are marked by yellow color

ar ma sigmaa log_likelhood akiki_aic adj_aic bayesian_bic ljung_box

1 0 0 0.0002793201 1825.912 -3647.823 -3647.806 -3638.77 0
2 0 1 0.000159839 2016.787 -4027.573 -4027.538 -4013.994 0
3 0 2 0.0001334113 2078.944 -4149.888 -4149.829 -4131.782 0
4 0 3 0.0001198414 2116.005 -4222.01 -4221.921 -4199.377 0
5 0 4 0.0001150424 2130.446 -4248.891 -4248.767 -4221.733 0
6 1 0 0.0001061719 2156.256 -4306.511 -4306.476 -4292.932 0.008768833
7 1 1 0.0001046229 2161.758 -4315.515 -4315.456 -4297.409 0.1921727
8 1 2 0.0001038797 2164.674 -4319.348 -4319.26 -4296.716 0.2797673
9 1 3 0.0001036516 2165.909 -4319.818 -4319.694 -4292.659 0.2083206
10 1 4 0.0001027046 2169.501 -4325.003 -4324.837 -4293.318 0.6315301
11 2 0 0.0001049738 2160.62 -4313.239 -4313.18 -4295.133 0.1177497
12 2 1 0.0001023881 2169.548 -4329.097 -4329.008 -4306.464 0.7675839
13 2 2 0.0001024999 2169.674 -4327.348 -4327.224 -4300.189 0.7349394
14 2 3 0.000102649 2169.683 -4325.366 -4325.2 -4293.68 0.6528562
15 2 4 0.000102632 2170.239 -4324.477 -4324.264 -4288.265 0.6875792
16 3 0 0.0001043738 2163.069 -4316.137 -4316.049 -4293.505 0.2229833
17 3 1 0.000102501 2169.671 -4327.341 -4327.217 -4300.182 0.7329887
18 3 2 0.0001026583 2169.655 -4325.31 -4325.144 -4293.624 0.6449953
19 3 3 0.0001027814 2169.745 -4323.489 -4323.276 -4287.277 0.5716443
20 3 4 0.0001027195 2170.447 -4322.895 -4322.627 -4282.156 0.6511906
21 4 0 0.0001044113 2163.447 -4314.895 -4314.77 -4287.736 0.1792801
22 4 1 0.0001026446 2169.7 -4325.4 -4325.234 -4293.714 0.6552109
23 4 2 0.0001026229 2170.271 -4324.542 -4324.328 -4288.33 0.7016443
24 4 3 0.0001015558 2172.611 -4327.222 -4326.955 -4286.484 0.6307234
25 4 4 0.000102854 2170.512 -4321.023 -4320.696 -4275.758 0.5624527

ARIMA(2,1) model is estimated for variable: drob

Conditional-Sum-of-Squares & Maximum Likelihood Estimation

Estimate S.E t.value p.value Lag
MU -0.00242 0.00396 -0.612 5.41e-01 1
AR 1 1.55663 0.06492 23.976 0.00e+00 1
AR 2 -0.56814 0.05960 -9.533 2.67e-20 2
MA 1 -0.87882 0.04663 -18.847 4.74e-64 1

Arfima models based on wavelet

Best model of these subset of ARMA models are marked by yellow color

ar ma sigmaa log_likelhood akiki_aic adj_aic bayesian_bic ljung_box

1 0 0 0.0004114005 1693.68 -3383.36 -3383.342 -3374.307 0
2 0 1 0.0002020524 1936.664 -3867.328 -3867.293 -3853.749 0
3 0 2 0.0001546546 2028.366 -4048.731 -4048.672 -4030.625 0
4 0 3 0.0001323134 2082.061 -4154.123 -4154.034 -4131.49 0
5 0 4 0.0001233494 2106.492 -4200.983 -4200.859 -4173.824 0
6 1 0 0.0001053659 2158.659 -4311.318 -4311.283 -4297.739 0.05918951
7 1 1 0.0001042954 2162.635 -4317.27 -4317.211 -4299.164 0.2169743
8 1 2 0.0001035715 2165.498 -4320.995 -4320.906 -4298.363 0.2603602
9 1 3 0.0001033833 2166.608 -4321.216 -4321.092 -4294.057 0.194071
10 1 4 0.0001024606 2170.129 -4326.258 -4326.092 -4294.572 0.5598877
11 2 0 0.0001045244 2161.889 -4315.779 -4315.72 -4297.673 0.1819554
12 2 1 0.0001020177 2170.592 -4331.185 -4331.096 -4308.552 0.7859572
13 2 2 0.000102166 2170.599 -4329.199 -4329.075 -4302.04 0.7196394
14 2 3 0.0001023166 2170.603 -4327.206 -4327.04 -4295.52 0.6346722
15 2 4 0.00010229 2171.188 -4326.377 -4326.163 -4290.165 0.678466
16 3 0 0.0001039739 2164.185 -4318.369 -4318.281 -4295.737 0.2438625
17 3 1 0.0001021674 2170.599 -4329.197 -4329.073 -4302.038 0.7178943
18 3 2 0.0001023183 2170.595 -4327.19 -4327.024 -4295.504 0.6327272
19 3 3 0.0001023107 2171.12 -4326.24 -4326.027 -4290.028 0.669066
20 3 4 0.0001023819 2171.382 -4324.765 -4324.497 -4284.026 0.6371464
21 4 0 0.0001039991 2164.603 -4317.206 -4317.082 -4290.047 0.1856734
22 4 1 0.0001023255 2170.568 -4327.137 -4326.971 -4295.451 0.6378258
23 4 2 0.0001023043 2171.145 -4326.291 -4326.077 -4290.079 0.6733871
24 4 3 0.0001017521 2173.191 -4328.383 -4328.115 -4287.644 0.6644464
25 4 4 0.0001024752 2171.576 -4323.152 -4322.824 -4277.887 0.5997168

ARIMA(2,1) model is estimated for variable: dwavlet

Conditional-Sum-of-Squares & Maximum Likelihood Estimation

Estimate S.E t.value p.value Lag
MU -0.00353 0.00589 -0.6 5.49e-01 1
AR 1 1.63127 0.06456 25.3 0.00e+00 1
AR 2 -0.63895 0.06098 -10.5 6.47e-24 2
MA 1 -0.87828 0.04644 -18.9 2.11e-64 1

Arfima models based on Whittle estimator

Best model of these subset of ARMA models are marked by yellow color

ar ma sigmaa log_likelhood akiki_aic adj_aic bayesian_bic ljung_box

1 0 0 0.0002916386 1811.174 -3618.347 -3618.33 -3609.294 0
2 0 1 0.0001638559 2008.301 -4010.601 -4010.566 -3997.022 0
3 0 2 0.0001354886 2073.655 -4139.31 -4139.251 -4121.204 0
4 0 3 0.0001210598 2112.536 -4215.072 -4214.983 -4192.439 0
5 0 4 0.0001158603 2128.011 -4244.021 -4243.897 -4216.862 0
6 1 0 0.0001061097 2156.434 -4306.867 -4306.832 -4293.288 0.01101725
7 1 1 0.0001046002 2161.81 -4315.62 -4315.561 -4297.514 0.1935377
8 1 2 0.0001038505 2164.748 -4319.497 -4319.408 -4296.864 0.275553
9 1 3 0.0001036241 2165.979 -4319.957 -4319.833 -4292.798 0.2053408
10 1 4 0.0001026754 2169.577 -4325.155 -4324.989 -4293.469 0.6223365
11 2 0 0.0001049399 2160.708 -4313.416 -4313.357 -4295.31 0.1237427
12 2 1 0.0001023396 2169.684 -4329.367 -4329.279 -4306.735 0.7723511
13 2 2 0.000102459 2169.787 -4327.575 -4327.451 -4300.416 0.7350551
14 2 3 0.0001026074 2169.798 -4325.597 -4325.431 -4293.911 0.6517672
15 2 4 0.0001025899 2170.357 -4324.713 -4324.5 -4288.501 0.6864401
16 3 0 0.0001043395 2163.159 -4316.318 -4316.23 -4293.686 0.2248481
17 3 1 0.0001024601 2169.786 -4327.573 -4327.448 -4300.414 0.7311044
18 3 2 0.000102616 2169.773 -4325.546 -4325.38 -4293.861 0.6438736
19 3 3 0.0001027427 2169.853 -4323.706 -4323.492 -4287.494 0.5681266
20 3 4 0.0001026777 2170.567 -4323.133 -4322.866 -4282.395 0.6489281
21 4 0 0.0001043737 2163.548 -4315.097 -4314.973 -4287.938 0.1795603
22 4 1 0.000102604 2169.813 -4325.626 -4325.46 -4293.941 0.6532062
23 4 2 0.0001025824 2170.382 -4324.763 -4324.55 -4288.551 0.7009665
24 4 3 0.0001018677 2172.626 -4327.252 -4326.984 -4286.513 0.6474523
25 4 4 0.0001027974 2170.677 -4321.354 -4321.026 -4276.089 0.583621

ARIMA(2,1) model is estimated for variable: dwhittle_est

Conditional-Sum-of-Squares & Maximum Likelihood Estimation

Estimate S.E t.value p.value Lag
MU -0.00238 0.0042 -0.568 5.70e-01 1
AR 1 1.56839 0.0641 24.456 0.00e+00 1
AR 2 -0.57899 0.0592 -9.776 3.32e-21 2
MA 1 -0.88078 0.0456 -19.320 1.31e-66 1

Arfima models based on Reisen

Best model of these subset of ARMA models are marked by yellow color

ar ma sigmaa log_likelhood akiki_aic adj_aic bayesian_bic ljung_box

1 0 0 0.001054573 1372.218 -2740.436 -2740.418 -2731.383 0
2 0 1 0.0003938416 1708.516 -3411.033 -3410.997 -3397.453 0
3 0 2 0.0002409176 1876.657 -3745.313 -3745.254 -3727.207 0
4 0 3 0.0001814921 1973.765 -3937.53 -3937.442 -3914.898 0
5 0 4 0.0001551883 2027.685 -4043.37 -4043.245 -4016.211 0
6 1 0 0.0001027829 2166.648 -4327.296 -4327.26 -4313.716 0.4404017
7 1 1 0.0001028497 2166.928 -4325.856 -4325.797 -4307.75 0.357888
8 1 2 0.0001025528 2168.409 -4326.817 -4326.729 -4304.185 0.3234167
9 1 3 0.0001025636 2168.869 -4325.738 -4325.614 -4298.58 0.2406508
10 1 4 0.0001019243 2171.48 -4328.96 -4328.794 -4297.275 0.498709
11 2 0 0.0001028606 2166.891 -4325.781 -4325.722 -4307.675 0.3591755
12 2 1 0.0001016052 2171.539 -4333.078 -4332.989 -4310.445 0.6841174
13 2 2 0.0001016101 2172.022 -4332.044 -4331.92 -4304.885 0.6666061
14 2 3 0.0001017575 2172.029 -4330.059 -4329.893 -4298.373 0.5808205
15 2 4 0.0001016988 2172.724 -4329.449 -4329.235 -4293.237 0.6513427
16 3 0 0.000102653 2168.077 -4326.153 -4326.065 -4303.521 0.3255223
17 3 1 0.0001028595 2167.896 -4323.791 -4323.667 -4296.632 0.2789149
18 3 2 0.0001016422 2172.42 -4330.839 -4330.673 -4299.154 0.6783341
19 3 3 0.0001017804 2172.454 -4328.908 -4328.694 -4292.696 0.5925057
20 3 4 0.0001018047 2172.869 -4327.738 -4327.471 -4287 0.5925108
21 4 0 0.0001027368 2168.302 -4324.605 -4324.481 -4297.446 0.2475247
22 4 1 0.0001017531 2172.049 -4330.097 -4329.931 -4298.412 0.582555
23 4 2 0.0001017809 2172.457 -4328.914 -4328.7 -4292.702 0.5912432
24 4 3 0.000100528 2175.451 -4332.901 -4332.634 -4292.163 0.5192418
25 4 4 0.0001019109 2173.023 -4326.046 -4325.718 -4280.781 0.5125658

ARIMA(2,1) model is estimated for variable: dsperio

Conditional-Sum-of-Squares & Maximum Likelihood Estimation

Estimate S.E t.value p.value Lag
MU -0.00692 0.0123 -0.56 5.75e-01 1
AR 1 1.76667 0.0708 24.96 0.00e+00 1
AR 2 -0.77012 0.0689 -11.18 9.07e-27 2
MA 1 -0.88275 0.0558 -15.83 2.90e-48 1

Arfima models based on maximum likelihood estimators

Best model of these subset of ARMA models are marked by yellow color

ar ma sigmaa log_likelhood akiki_aic adj_aic bayesian_bic ljung_box

1 0 0 0.0002796393 1825.522 -3647.044 -3647.026 -3637.991 0
2 0 1 0.0001599433 2016.564 -4027.127 -4027.092 -4013.548 0
3 0 2 0.0001334654 2078.805 -4149.61 -4149.551 -4131.504 0
4 0 3 0.0001198731 2115.914 -4221.828 -4221.74 -4199.196 0
5 0 4 0.0001150637 2130.382 -4248.764 -4248.64 -4221.605 0
6 1 0 0.0001061704 2156.26 -4306.52 -4306.485 -4292.94 0.008821603
7 1 1 0.0001046224 2161.759 -4315.518 -4315.459 -4297.412 0.1922026
8 1 2 0.0001038788 2164.676 -4319.352 -4319.264 -4296.72 0.2793923
9 1 3 0.0001036507 2165.911 -4319.822 -4319.698 -4292.663 0.2075422
10 1 4 0.0001027038 2169.504 -4325.007 -4324.841 -4293.322 0.631282
11 2 0 0.000104973 2160.622 -4313.243 -4313.184 -4295.137 0.1179024
12 2 1 0.0001023855 2169.553 -4329.106 -4329.018 -4306.474 0.7688886
13 2 2 0.0001024998 2169.673 -4327.346 -4327.221 -4300.187 0.735611
14 2 3 0.0001026479 2169.687 -4325.373 -4325.207 -4293.688 0.6526008
15 2 4 0.0001026309 2170.242 -4324.484 -4324.27 -4288.272 0.6875694
16 3 0 0.000104373 2163.071 -4316.142 -4316.053 -4293.509 0.2230292
17 3 1 0.0001024998 2169.674 -4327.348 -4327.223 -4300.189 0.7330032
18 3 2 0.000102658 2169.653 -4325.306 -4325.14 -4293.62 0.6443767
19 3 3 0.0001027823 2169.743 -4323.485 -4323.272 -4287.274 0.5703124
20 3 4 0.0001027248 2170.438 -4322.877 -4322.609 -4282.138 0.6415444
21 4 0 0.0001044103 2163.45 -4314.9 -4314.776 -4287.741 0.1792848
22 4 1 0.0001026441 2169.702 -4325.404 -4325.238 -4293.719 0.6545764
23 4 2 0.0001026218 2170.274 -4324.548 -4324.334 -4288.336 0.7015843
24 4 3 0.0001016218 2172.5 -4327 -4326.732 -4286.261 0.6678678
25 4 4 0.0001028373 2170.566 -4321.132 -4320.805 -4275.867 0.5857551
 ARIMA(2,1) model is estimated for variable: dfrac

Conditional-Sum-of-Squares & Maximum Likelihood Estimation

Estimate S.E t.value p.value Lag
MU -0.00249 0.00401 -0.622 5.34e-01 1
AR 1 1.55786 0.06470 24.079 0.00e+00 1
AR 2 -0.56913 0.05945 -9.574 1.88e-20 2
MA 1 -0.87981 0.04630 -19.001 6.98e-65 1

Arfima models based on Exact likelihood estimators

Best model of these subset of ARMA models are marked by yellow color

ar ma sigmaa log_likelhood akiki_aic adj_aic bayesian_bic ljung_box

1 0 0 0.0002852662 1818.718 -3633.437 -3633.419 -3624.384 0
2 0 1 0.0001617803 2012.659 -4019.318 -4019.283 -4005.739 0
3 0 2 0.0001344168 2076.374 -4144.747 -4144.688 -4126.641 0
4 0 3 0.000120431 2114.322 -4218.644 -4218.555 -4196.011 0
5 0 4 0.0001154384 2129.265 -4246.529 -4246.405 -4219.37 0
6 1 0 0.0001061427 2156.339 -4306.678 -4306.642 -4293.098 0.009799088
7 1 1 0.0001046123 2161.782 -4315.563 -4315.504 -4297.457 0.1927802
8 1 2 0.0001038656 2164.71 -4319.42 -4319.331 -4296.787 0.2776309
9 1 3 0.0001036378 2165.944 -4319.888 -4319.764 -4292.729 0.2067494
10 1 4 0.0001026903 2169.539 -4325.078 -4324.912 -4293.392 0.6269916
11 2 0 0.0001049579 2160.661 -4313.321 -4313.262 -4295.215 0.1206183
12 2 1 0.0001023642 2169.616 -4329.231 -4329.142 -4306.599 0.7697634
13 2 2 0.0001024803 2169.727 -4327.454 -4327.33 -4300.295 0.7355639
14 2 3 0.0001026286 2169.741 -4325.481 -4325.315 -4293.796 0.6514892
15 2 4 0.0001026114 2170.297 -4324.593 -4324.38 -4288.381 0.6873531
16 3 0 0.0001043575 2163.111 -4316.223 -4316.134 -4293.59 0.2238663
17 3 1 0.0001024803 2169.728 -4327.456 -4327.332 -4300.297 0.7327194
18 3 2 0.0001026375 2169.713 -4325.427 -4325.261 -4293.741 0.644568
19 3 3 0.0001027634 2169.796 -4323.591 -4323.377 -4287.379 0.5689257
20 3 4 0.0001027 2170.504 -4323.008 -4322.74 -4282.269 0.6492047
21 4 0 0.0001043933 2163.496 -4314.991 -4314.867 -4287.832 0.1794078
22 4 1 0.0001026234 2169.756 -4325.513 -4325.347 -4293.827 0.6558843
23 4 2 0.000102603 2170.326 -4324.651 -4324.438 -4288.439 0.7011167
24 4 3 0.0001019372 2172.535 -4327.07 -4326.803 -4286.332 0.6507321
25 4 4 0.0001028529 2170.506 -4321.012 -4320.685 -4275.747 0.5586601

ARIMA(2,1) model is estimated for variable: dexact_lik

Conditional-Sum-of-Squares & Maximum Likelihood Estimation

Estimate S.E t.value p.value Lag

MU -0.0025 0.00407 -0.613 5.4e-01 1
AR 1 1.5612 0.06490 24.055 0.0e+00 1
AR 2 -0.5724 0.05971 -9.586 1.7e-20 2
MA 1 -0.8789 0.04658 -18.869 3.6e-64 1

Bootstraping
 Residuals based on ARMA(2,1) of R/S method data

Residuals

1e-04

0e+00

-1e-04

0 100 200 300 400 500

80
0.10
60
0.05
count
ACF

40
0.00
20
-0.05
0
0 5 10 15 20 25 -1e-04 0e+00 1e-04 2e-04
Lag residuals

NORM QQ PLOT
3
SS.1 Ordered Data

Confidence Intervals: 95%

1
-1 0
-3

-3 -2 -1 0 1 2 3

Normal Quantiles

Box-Ljung test from booted residuals

2.5% 97.5%
Test 16.63061 6.797138 33.640306
Pvalue 0.2793432 0.0007699301 0.8707057463

Parameters of model

2.5% 97.5%
AR1 6.906917e-01 5.548886e-01 0.8516573
AR2 1.435898e-01 -0.0851974 0.2912585
 MA1 5.936488e-01 5.548886e-01 0.8516573
AIC -3.889264e+03 -4.104479e+03 -3671.1501826

############################################################################################
############################################################################################
############################################################################################

Residuals based on ARMA(2,1) of Simple R/S Hurst estimation data

Residuals
2e-04
1e-04
0e+00
-1e-04
-2e-04
0 100 200 300 400 500

80

0.05 60
count
ACF

0.00 40

20
-0.05

0
0 5 10 15 20 25 -2e-04 -1e-04 0e+00 1e-04 2e-04
Lag residuals

NORM QQ PLOT
3
SS.1 Ordered Data

Confidence Intervals: 95%

1
0
-3 -2 -1

-3 -2 -1 0 1 2 3

Normal Quantiles

Box-Ljung test from booted residuals

2.5% 97.5%
Test 13.89374 5.641007 26.399964
Pvalue 0.4002813 0.009418313 0.933086117
 Parameters of the model

2.5% 97.5%
AR1 7.774462e-01 5.960248e-01 0.9560603
AR2 1.154426e-01 -8.495594e-02 0.2930129
MA1 4.927862e-01 3.237342e-01 0.6394557
AIC -3.734489e+03 -3.980862e+03 -3501.3292152

############################################################################################
############################################################################################
############################################################################################

Residuals based on ARMA(2,1) of corrected R/S Hurst estimation data

Residuals
0.00010
0.00005
0.00000
-0.00005
-0.00010
-0.00015
0 100 200 300 400 500

80
0.05
60
0.00
count
ACF

40
-0.05
20
-0.10

-0.15 0
0 5 10 15 20 25 -1e-04 0e+00 1e-04
Lag residuals

NORM QQ PLOT
3
SS.1 Ordered Data

2
1

Confidence Intervals: 95%

0
-3 -2 -1

-3 -2 -1 0 1 2 3

Normal Quantiles
 Box-Ljung test from booted residuals
2.5% 97.5%
Test 17.89987 7.803258 31.761128
Pvalue 0.2250675 0.001506183 0.800299882

Parameters of the model

2.5% 97.5%
AR1 6.420072e-01 5.141444e-01 0.7875929
AR2 1.570491e-01 -7.909992e-03 0.2965188
MA1 6.424186e-01 4.932269e-01 0.7604108
AIC -3.947491e+03 -4.129924e+03 -3750.7190320

############################################################################################
############################################################################################
############################################################################################

Residuals based on ARMA(2,1) of Aggregated variance method data

Residuals
1e-04

0e+00

-1e-04

-2e-04
0 100 200 300 400 500

80
0.05
60
0.00
count
ACF

40
-0.05

-0.10 20

-0.15 0
0 5 10 15 20 25 -2e-04 -1e-04 0e+00 1e-04 2e-04
Lag residuals
 NORM QQ PLOT
2
SS.1 Ordered Data

Confidence Intervals: 95%

0
-2 -1
-3

-3 -2 -1 0 1 2 3

Normal Quantiles

Box-Ljung test from booted residuals

2.5% 97.5%
Test 14.72726 6.142914 27.191140
Pvalue 0.3571946 0.007256783 0.908663059

Parameters of the model

2.5% 97.5%
AR1 7.515984e-01 5.837808e-01 0.9261066
AR2 1.278202e-01 -6.998541e-02 0.2945200
MA1 5.261396e-01 3.657086e-01 0.6622000
AIC -3.783442e+03 -4.015291e+03 -3556.8002937

############################################################################################
############################################################################################
############################################################################################

Residuals based on ARMA(2,1) of Absolute values (moments) method data

 Residuals
1e-04

0e+00

-1e-04

0 100 200 300 400 500

0.05 75
0.00

count
ACF

50
-0.05
-0.10 25

-0.15 0
0 5 10 15 20 25 -1e-04 0e+00 1e-04
Lag residuals

NORM QQ PLOT
2
SS.1 Ordered Data

Confidence Intervals: 95%

0
-2 -1
-3

-3 -2 -1 0 1 2 3

Normal Quantiles

Box-Ljung test from booted residuals

2.5% 97.5%
Test 16.80512 7.237966 30.347345
Pvalue 0.2645743 0.002484884 0.841458428

Parameters of the model

2.5% 97.5%
AR1 6.839370e-01 5.399272e-01 0.8402516
AR2 1.503393e-01 -2.637855e-02 0.2958939
MA1 6.033116e-01 4.558979e-01 0.7247393
AIC -3.893342e+03 -4.089852e+03 -3691.7051270

Bootstraping Residuals of models based on Higuchi's method data

 Residuals
0.00010
0.00005
0.00000
-0.00005
-0.00010
-0.00015
0 100 200 300 400 500

80
0.05
60

count
0.00
ACF

40
-0.05
20
-0.10
0
0 5 10 15 20 25 -1e-04 0e+00 1e-04
Lag residuals

NORM QQ PLOT
3
SS.1 Ordered Data

2
1

Confidence Intervals: 95%

0
-3 -2 -1

-3 -2 -1 0 1 2 3

Normal Quantiles

Box-Ljung test from booted residuals

2.5% 97.5%
Test 17.53069 7.663875 31.253652
Pvalue 0.2375717 0.001802586 0.810814422

Parameters of the model

2.5% 97.5%
AR1 6.571366e-01 5.243407e-01 0.8068296
AR2 1.552137e-01 -1.431136e-02 0.2975788
MA1 6.291160e-01 4.802561e-01 0.7511572
AIC -3.929188e+03 -4.114847e+03 -3728.9749638

#################################################################################
#################################################################################
#################################################################################

Bootstraping Residuals of models based Hurst coefficient by Robinson's

method data

Residuals
1e-04
5e-05
0e+00
-5e-05
-1e-04

0 100 200 300 400 500

0.05 60
0.00
count
ACF

40
-0.05
20
-0.10
0
0 5 10 15 20 25 -0.00015-0.00010-0.000050.000000.000050.00010
Lag residuals

NORM QQ PLOT
3
SS.1 Ordered Data

2
1

Confidence Intervals: 95%

0
-3 -2 -1

-3 -2 -1 0 1 2 3

Normal Quantiles

Box-Ljung test from booted residuals

2.5% 97.5%
Test 18.19813 7.918023 32.211409
Pvalue 0.2156536 0.001283545 0.791455329

Parameters of the model

2.5% 97.5%
AR1 6.286754e-01 5.047841e-01 0.7703548
AR2 1.580772e-01 -4.163829e-03 0.2945979
MA1 6.534523e-01 5.036965e-01 0.7684793
AIC -3.962625e+03 -4.143639e+03 -3764.7058543

Bootstraping Residuals of models based on wavelets method data

 Residuals
1e-04

0e+00

-1e-04

0 100 200 300 400 500

0.05 75
0.00

count
ACF

50
-0.05
25
-0.10

-0.15 0
0 5 10 15 20 25 -2e-04 -1e-04 0e+00 1e-04
Lag residuals

NORM QQ PLOT
2
SS.1 Ordered Data

Confidence Intervals: 95%

0
-1
-2
-3

-3 -2 -1 0 1 2 3

Normal Quantiles
+
Box-Ljung test from booted residuals

2.5% 97.5%
Test 16.23823 7.016654 29.722260
Pvalue 0.2877031 0.003140064 0.856505422

Parameters of the model

2.5% 97.5%
AR1 7.033313e-01 5.540026e-01 0.8642203
AR2 1.453689e-01 -3.772392e-02 0.2924376
MA1 5.829042e-01 4.352712e-01 0.7083001
AIC -3.864743e+03 -4.072002e+03 -3652.5594677

Bootstraping Residuals of models based on whittle estimation method data

 Residuals
1e-04
5e-05
0e+00
-5e-05
-1e-04

0 100 200 300 400 500

80
0.05
60

count
0.00
ACF

40
-0.05
20
-0.10
0
0 5 10 15 20 25 -0.00015
-0.00010
-0.000050.000000.000050.000100.00015
Lag residuals

NORM QQ PLOT
3
SS.1 Ordered Data

2
1

Confidence Intervals: 95%

0
-3 -2 -1

-3 -2 -1 0 1 2 3

Normal Quantiles

Box-Ljung test from booted residuals

2.5% 97.5%
Test 17.99749 7.874504 31.920417
Pvalue 0.2219154 0.001426526 0.794854306

Parameters of the model

2.5% 97.5%
AR1 6.377345e-01 5.116036e-01 0.7816570
AR2 1.574508e-01 -6.924777e-03 0.2954634
MA1 6.460420e-01 4.959410e-01 0.7634762
AIC -3.952402e+03 -4.134480e+03 -3755.1713432
Bootstraping Residuals of models based on Reisen (1994) estimator method data

Residuals
2e-04

0e+00

-2e-04

0 100 200 300 400 500

0.10
80
0.05
count 60
0.00
ACF

40
-0.05
20
-0.10
0
0 5 10 15 20 25 -4e-04 -2e-04 0e+00 2e-04
Lag residuals

NORM QQ PLOT
2
SS.1 Ordered Data

Confidence Intervals: 95%

0
-1
-2
-3

-3 -2 -1 0 1 2 3

Normal Quantiles

Box-Ljung test from booted residuals

2.5% 97.5%
Test 11.27202 4.27947 23.87999
Pvalue 0.5525025 0.02112873 0.97784895

Parameters of the model

2.5% 97.5%
AR1 8.628534e-01 6.519412e-01 1.061400e+00
AR2 6.189028e-02 -1.469874e-01 2.781494e-01
MA1 3.746726e-01 1.784752e-01 5.431621e-01
AIC -3.556147e+03 -3.834799e+03 -3.279806e+03

Bootstraping Residuals of models based on maximum likelihood estimators method

data

Residuals
1e-04
5e-05
0e+00
-5e-05
-1e-04

0 100 200 300 400 500

0.05 60
0.00
count
ACF

40
-0.05
20
-0.10
0
0 5 10 15 20 25 -0.00015-0.00010-0.000050.000000.000050.00010
Lag residuals

NORM QQ PLOT
3
SS.1 Ordered Data

2
1

Confidence Intervals: 95%

0
-3 -2 -1

-3 -2 -1 0 1 2 3

Normal Quantiles
Box-Ljung test from booted residuals

2.5% 97.5%
Test 18.19279 7.918649 32.179066
Pvalue 0.215815 0.001298456 0.791410165

Parameters of the model

2.5% 97.5%
AR1 6.288841e-01 5.033637e-01 0.7706521
AR2 1.580918e-01 -3.880022e-03 0.2945696
MA1 6.532830e-01 5.031989e-01 0.7683363
AIC -3.962356e+03 -4.143401e+03 -3764.4290836

Bootstraping Residuals of models based on Exact likelihood estimators method data

Residuals
1e-04
5e-05
0e+00
-5e-05
-1e-04

0 100 200 300 400 500

80
0.05
60
count

0.00
ACF

40
-0.05
20
-0.10
0
0 5 10 15 20 25 -0.00015-0.00010
-0.000050.000000.000050.00010
Lag residuals
 NORM QQ PLOT
3
SS.1 Ordered Data

2
1

Confidence Intervals: 95%

0
-3 -2 -1

-3 -2 -1 0 1 2 3

Normal Quantiles

Box-Ljung test from booted residuals

2.5% 97.5%
Test 18.101 7.897729 31.863793
Pvalue 0.2186455 0.001452472 0.793049910

Parameters of the model

2.5% 97.5%
AR1 6.331116e-01 5.080692e-01 0.7760175
AR2 1.578174e-01 -6.020978e-03 0.2951371

MA1 6.498532e-01 5.000558e-01 0.7655487

AIC -3.957655e+03 -4.139213e+03 -3759.9375368

Bootstrapping

d 0.025 0.975
1 R/S method 0.4655422 0.3574471 0.5724752

2 Simple R/S Hurst estimation 0.2779502 0.2172705 0.3362660

3 Corrected R over S Hurst exponent 0.3850719 0.3088434 0.4633897

4 Differenced aggregated variance method

5 Aggregated variance method 0.2109265 0.0283393- 0.3925340

6 Absolute values (moments) method 0.2858729 0.05436168 0.46410899

7 Periodogram and cumulated periodogram method

8 Boxed (modified) peridogram method
9 Higuchi's method 0.4679793 0.4673298 0.4685515

10 Hurst coefficient by Robinson's 0.4997278 0.4994094 0.4999519

11 estimates the long memory prarameter using wavelets 0.1782505 0.04640358 0.29911198

12 Whittle estimator for fractional Gaussian noise 0.489942 0.4899197 0.4899578

13 Geweke and Porter-Hudak (GPH)

14  Reisen (1994) estimator 0.0787622 0.0455969- 0.1944584

15 maximum likelihood estimators of the parameters of a 0.4995206 0.4994069 0.4996334

fractionally-differenced ARIMA
16 Semiparametric local Whittle estimator
17 Exact MLE 0.495 0.495 0.495