R version 4.2.1 (2022-06-23) -- "Funny-Looking Kid" Copyright (C) 2022 The R Foundation for Statistical Computing Platform: aarch64-apple-darwin20 (64-bit) R is free software and comes with ABSOLUTELY NO WARRANTY. You are welcome to redistribute it under certain conditions. Type 'license()' or 'licence()' for distribution details. Natural language support but running in an English locale R is a collaborative project with many contributors. Type 'contributors()' for more information and 'citation()' on how to cite R or R packages in publications. Type 'demo()' for some demos, 'help()' for on-line help, or 'help.start()' for an HTML browser interface to help. Type 'q()' to quit R. > pkgname <- "bootnet" > source(file.path(R.home("share"), "R", "examples-header.R")) > options(warn = 1) > library('bootnet') Loading required package: ggplot2 This is bootnet 1.5 For questions and issues, please see github.com/SachaEpskamp/bootnet. > > base::assign(".oldSearch", base::search(), pos = 'CheckExEnv') > base::assign(".old_wd", base::getwd(), pos = 'CheckExEnv') > cleanEx() > nameEx("bootInclude") > ### * bootInclude > > flush(stderr()); flush(stdout()) > > ### Name: bootInclude > ### Title: Inclusion proportion graph > ### Aliases: bootInclude > > ### ** Examples > > ## Not run: > ##D # BFI Extraversion data from psychTools package: > ##D library("psychTools") > ##D data(bfi) > ##D # Subset of data: > ##D bfiSub <- bfi[1:250,1:25] > ##D > ##D # Estimate ggmModSelect networks (not stepwise to increase speed): > ##D Network <- estimateNetwork(bfiSub], default = "ggmModSelect", corMethod = "cor", > ##D stepwise = FALSE) > ##D > ##D # Bootstrap 100 values, using 8 cores (100 to incease speed, preferably 1000+): > ##D boots <- bootnet(Network, nBoots = 100, nCores = 8) > ##D > ##D # Threshold network: > ##D Network_inclusion <- bootInclude(boots) > ##D > ##D # Plot: > ##D plot(Network_inclusion) > ## End(Not run) > > > > cleanEx() > nameEx("bootThreshold") > ### * bootThreshold > > flush(stderr()); flush(stdout()) > > ### Name: bootThreshold > ### Title: Threshold network based on bootstrapped intervals > ### Aliases: bootThreshold > > ### ** Examples > > ## Not run: > ##D # BFI Extraversion data from psychTools package: > ##D library("psychTools") > ##D data(bfi) > ##D bfiSub <- bfi[,1:25] > ##D > ##D # Estimate unregularized network: > ##D Network <- estimateNetwork(bfiSub, default = "pcor", corMethod = "cor") > ##D > ##D # Bootstrap 1000 values, using 8 cores: > ##D boots <- bootnet(Network, nBoots = 1000, nCores = 8) > ##D > ##D # Threshold network: > ##D Network_thresholded <- bootThreshold(boots) > ##D > ##D # Plot: > ##D plot(Network_thresholded) > ## End(Not run) > > > > cleanEx() > nameEx("bootnet") > ### * bootnet > > flush(stderr()); flush(stdout()) > > ### Name: bootnet > ### Title: Bootstrapped network estimation > ### Aliases: bootnet > > ### ** Examples > > # BFI Extraversion data from psychTools package: > library("psychTools") > data(bfi) > bfiSub <- bfi[,1:25] > > # Estimate network: > Network <- estimateNetwork(bfiSub, default = "EBICglasso") Estimating Network. Using package::function: - qgraph::EBICglasso for EBIC model selection - using glasso::glasso Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. > > # Centrality indices: > library("qgraph") > centralityPlot(Network) > > > > > cleanEx() detaching ‘package:qgraph’, ‘package:psychTools’ > nameEx("corStability") > ### * corStability > > flush(stderr()); flush(stdout()) > > ### Name: corStability > ### Title: Correlation stability coefficient > ### Aliases: corStability > > ### ** Examples > > ## Not run: > ##D # BFI Extraversion data from psychTools package: > ##D library("psychTools") > ##D data(bfi) > ##D bfiSub <- bfi[,1:25] > ##D > ##D # Estimate network: > ##D Network <- estimateNetwork(bfiSub, default = "EBICglasso") > ##D > ##D # Bootstrap 1000 values, using 8 cores: > ##D # Bootstrap 1000 values, using 8 cores: > ##D Results2 <- bootnet(Network, nBoots = 1000, nCores = 8, > ##D type = "case") > ##D > ##D # Compute CS-coefficients: > ##D corStability(Results2) > ## End(Not run) > > > > cleanEx() > nameEx("differenceTest") > ### * differenceTest > > flush(stderr()); flush(stdout()) > > ### Name: differenceTest > ### Title: Bootstrapped difference test > ### Aliases: differenceTest > > ### ** Examples > > ## Not run: > ##D # BFI Extraversion data from psychTools package: > ##D library("psychTools") > ##D data(bfi) > ##D bfiSub <- bfi[,1:25] > ##D > ##D # Estimate network: > ##D Network <- estimateNetwork(bfiSub, default = "EBICglasso") > ##D > ##D # Bootstrap 1000 values, using 8 cores: > ##D Results1 <- bootnet(Network, nBoots = 1000, nCores = 8) > ##D > ##D # Test for difference in strength between node "A1" and "C2": > ##D differenceTest(Results, "A1", "C2", "strength") > ##D > ##D # Test for difference between edge N1--N2 and N3--N4: > ##D differenceTest(Results, "N1--N2", "N3--N4", "edge") > ##D > ##D # Alternative: > ##D differenceTest(Results, x = "N1", x2 = "N2", y = "N3", > ##D y2 = "N4", measure = "edge") > ## End(Not run) > > > > cleanEx() > nameEx("estimateNetwork") > ### * estimateNetwork > > flush(stderr()); flush(stdout()) > > ### Name: estimateNetwork > ### Title: Estimate a network structure > ### Aliases: estimateNetwork bootnet_EBICglasso bootnet_pcor bootnet_cor > ### bootnet_IsingFit bootnet_IsingSampler bootnet_adalasso bootnet_huge > ### bootnet_mgm bootnet_relimp bootnet_TMFG bootnet_LoGo > ### bootnet_ggmModSelect bootnet_graphicalVAR bootnet_SVAR_lavaan > ### bootnet_piecewiseIsing bootnet_GGMncv > > ### ** Examples > > # BFI Extraversion data from psychTools package: > library("psychTools") > data(bfi) > bfiSub <- bfi[,1:25] > > # Estimate network: > Network <- estimateNetwork(bfiSub, default = "EBICglasso") Estimating Network. Using package::function: - qgraph::EBICglasso for EBIC model selection - using glasso::glasso Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. > > ## Not run: > ##D # Some pointers: > ##D print(Network) > ##D > ##D # Estimated network: > ##D plot(Network, layout = 'spring') > ##D > ##D # Centrality indices: > ##D library("qgraph") > ##D centralityPlot(Network) > ##D > ##D # BIC model selection: > ##D Network_BIC <- estimateNetwork(bfiSub, default = "EBICglasso", tuning = 0) > ##D > ##D # Ising model: > ##D Network_BIC <- estimateNetwork(bfiSub, default = "IsingFit") > ## End(Not run) > > > > cleanEx() detaching ‘package:psychTools’ > nameEx("netSimulator") > ### * netSimulator > > flush(stderr()); flush(stdout()) > > ### Name: netSimulator > ### Title: Network Estimation Performance > ### Aliases: netSimulator replicationSimulator > > ### ** Examples > > # 5-node GGM chain graph: > trueNetwork <- genGGM(5) > > # Simulate: > Res <- netSimulator(trueNetwork, nReps = 10) 'default' and 'dataGenerator' are missing. Setting default = 'EBICglasso' Setting 'dataGenerator = ggmGenerator(ordinal = FALSE)' Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Note: Network with lowest lambda selected as best network: assumption of sparsity might be violated. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. An empty network was selected to be the best fitting network. Possibly set 'lambda.min.ratio' higher to search more sparse networks. You can also change the 'gamma' parameter to improve sensitivity (at the cost of specificity). Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. An empty network was selected to be the best fitting network. Possibly set 'lambda.min.ratio' higher to search more sparse networks. You can also change the 'gamma' parameter to improve sensitivity (at the cost of specificity). An empty network was selected to be the best fitting network. Possibly set 'lambda.min.ratio' higher to search more sparse networks. You can also change the 'gamma' parameter to improve sensitivity (at the cost of specificity). Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. An empty network was selected to be the best fitting network. Possibly set 'lambda.min.ratio' higher to search more sparse networks. You can also change the 'gamma' parameter to improve sensitivity (at the cost of specificity). An empty network was selected to be the best fitting network. Possibly set 'lambda.min.ratio' higher to search more sparse networks. You can also change the 'gamma' parameter to improve sensitivity (at the cost of specificity). Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Note: Network with lowest lambda selected as best network: assumption of sparsity might be violated. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Note: Network with lowest lambda selected as best network: assumption of sparsity might be violated. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. Warning in EBICglassoCore(S = S, n = n, gamma = gamma, penalize.diagonal = penalize.diagonal, : A dense regularized network was selected (lambda < 0.1 * lambda.max). Recent work indicates a possible drop in specificity. Interpret the presence of the smallest edges with care. Setting threshold = TRUE will enforce higher specificity, at the cost of sensitivity. > > # Results: > Res === netSimulator Results === Mean (SD) values per varied levels: nCases default ExpectedInfluence MaxFalseEdgeWidth bias 1 50 EBICglasso 0.0000000 NA 0.166666667 2 50 EBICglasso 0.2848376 NA 0.091364983 3 50 EBICglasso 0.3899784 NA 0.128516776 4 50 EBICglasso 0.4631448 0.64423086 0.112406801 5 50 EBICglasso 0.6469572 NA 0.074555504 6 50 EBICglasso 0.8875777 0.41909411 0.058238640 7 100 EBICglasso 0.7362187 NA 0.079407411 8 100 EBICglasso 0.8475424 NA 0.052994722 9 100 EBICglasso 0.8609028 0.23074814 0.065408665 10 100 EBICglasso 0.8750629 0.22312063 0.059641983 11 100 EBICglasso 0.8902879 0.28150683 0.094710013 12 100 EBICglasso 0.9018910 0.12641941 0.059324246 13 100 EBICglasso 0.9464951 0.51631145 0.061602489 14 100 EBICglasso 0.9549263 0.27114382 0.061070974 15 100 EBICglasso 0.9751011 0.14600706 0.040234153 16 100 EBICglasso 0.9797132 0.26092141 0.065220992 17 250 EBICglasso 0.9318838 0.03248169 0.033484450 18 250 EBICglasso 0.9363721 0.29471291 0.042420152 19 250 EBICglasso 0.9369179 0.36132678 0.037915199 20 250 EBICglasso 0.9537680 0.11301088 0.033409377 21 250 EBICglasso 0.9674657 0.37999934 0.048707695 22 250 EBICglasso 0.9692016 0.24040952 0.031418919 23 250 EBICglasso 0.9753039 0.37781384 0.051458545 24 250 EBICglasso 0.9793212 0.10035613 0.030859342 25 250 EBICglasso 0.9815215 0.26541630 0.044982819 26 250 EBICglasso 0.9882739 0.10649683 0.033891939 27 500 EBICglasso 0.9565585 0.14176516 0.035042832 28 500 EBICglasso 0.9601197 0.05871878 0.032747200 29 500 EBICglasso 0.9725498 0.05344261 0.025515715 30 500 EBICglasso 0.9883173 0.13036197 0.015844700 31 500 EBICglasso 0.9917542 0.10353023 0.021588333 32 500 EBICglasso 0.9927947 0.04126639 0.028304596 33 500 EBICglasso 0.9935499 0.19254554 0.033140151 34 500 EBICglasso 0.9954097 0.06387285 0.012449263 35 500 EBICglasso 0.9974058 0.01933903 0.009384670 36 500 EBICglasso 0.9978169 0.04728012 0.009937402 37 1000 EBICglasso 0.9892801 0.08751225 0.018605122 38 1000 EBICglasso 0.9903248 0.08869119 0.021753171 39 1000 EBICglasso 0.9910515 0.07214640 0.022309475 40 1000 EBICglasso 0.9931642 0.10367068 0.015356471 41 1000 EBICglasso 0.9958335 0.10264578 0.012632718 42 1000 EBICglasso 0.9961207 0.03804010 0.012940696 43 1000 EBICglasso 0.9963354 NA 0.009528464 44 1000 EBICglasso 0.9969016 0.09955331 0.021211838 45 1000 EBICglasso 0.9969770 0.02514242 0.008867833 46 1000 EBICglasso 0.9975148 NA 0.010034745 47 2500 EBICglasso 0.9895891 0.08366283 0.013264427 48 2500 EBICglasso 0.9929911 0.15548633 0.018217969 49 2500 EBICglasso 0.9950838 0.09226244 0.019179659 50 2500 EBICglasso 0.9961148 NA 0.008757737 51 2500 EBICglasso 0.9975048 0.06596282 0.012382641 52 2500 EBICglasso 0.9978824 0.01463139 0.010634863 53 2500 EBICglasso 0.9980366 0.04714682 0.009231693 54 2500 EBICglasso 0.9986108 0.05284255 0.009879395 55 2500 EBICglasso 0.9988746 0.03367892 0.007909647 56 2500 EBICglasso 0.9991271 0.07421443 0.011178258 sensitivity specificity correlation strength closeness betweenness 1 0 (0) 1 (0) 0 (0) 0 (0) 0 (0) 0 (0) 2 0.6 (NA) 1 (NA) 0.75 (NA) -0.36 (NA) 0 (NA) 0 (NA) 3 0.4 (NA) 1 (NA) 0.67 (NA) 0.57 (NA) 0 (NA) 0 (NA) 4 1 (NA) 0.6 (NA) 0.78 (NA) 0.36 (NA) -0.25 (NA) 0 (NA) 5 0.8 (NA) 1 (NA) 0.88 (NA) 0.9 (NA) 0.98 (NA) 0 (NA) 6 1 (NA) 0.8 (NA) 0.94 (NA) 0.73 (NA) 0.53 (NA) 0 (NA) 7 0.8 (NA) 1 (NA) 0.91 (NA) 0.81 (NA) 0.92 (NA) 0 (NA) 8 1 (NA) 1 (NA) 0.94 (NA) 0.08 (NA) -0.49 (NA) 0 (NA) 9 1 (NA) 0.6 (NA) 0.96 (NA) -0.6 (NA) -0.71 (NA) 0 (NA) 10 1 (NA) 0.4 (NA) 0.95 (NA) 0.84 (NA) 0.94 (NA) 0 (NA) 11 0.8 (NA) 0.8 (NA) 0.8 (NA) 0.15 (NA) 0.6 (NA) 0 (NA) 12 1 (NA) 0.6 (NA) 0.95 (NA) 0.76 (NA) 0.9 (NA) 0 (NA) 13 1 (NA) 0.2 (NA) 0.95 (NA) 0 (NA) -0.55 (NA) 0 (NA) 14 1 (NA) 0.4 (NA) 0.94 (NA) 0.24 (NA) 0.55 (NA) 0 (NA) 15 1 (NA) 0.8 (NA) 0.99 (NA) 0.59 (NA) 0.87 (NA) 0 (NA) 16 1 (NA) 0.4 (NA) 0.96 (NA) 0.41 (NA) 0.76 (NA) 0 (NA) 17 1 (NA) 0.6 (NA) 0.98 (NA) 0.32 (NA) 0.23 (NA) 0 (NA) 18 1 (NA) 0.8 (NA) 0.96 (NA) -0.81 (NA) -0.68 (NA) 0 (NA) 19 1 (NA) 0.6 (NA) 0.98 (NA) -0.56 (NA) 0.59 (NA) 0 (NA) 20 1 (NA) 0.8 (NA) 0.98 (NA) 0.17 (NA) 0.63 (NA) 0 (NA) 21 1 (NA) 0.6 (NA) 0.96 (NA) 0.63 (NA) 0.13 (NA) 0 (NA) 22 1 (NA) 0.6 (NA) 0.98 (NA) 0.79 (NA) 0.96 (NA) 0 (NA) 23 1 (NA) 0.2 (NA) 0.98 (NA) 0.31 (NA) -0.86 (NA) 0 (NA) 24 1 (NA) 0.6 (NA) 0.98 (NA) -0.19 (NA) -0.82 (NA) 0 (NA) 25 1 (NA) 0.4 (NA) 0.98 (NA) 0.77 (NA) 0.96 (NA) 0 (NA) 26 1 (NA) 0.6 (NA) 0.99 (NA) 0.28 (NA) 0.81 (NA) 0 (NA) 27 1 (NA) 0.4 (NA) 0.99 (NA) 0.7 (NA) 0.89 (NA) 0 (NA) 28 1 (NA) 0.8 (NA) 0.99 (NA) 0.89 (NA) 0.95 (NA) 0 (NA) 29 1 (NA) 0.4 (NA) 0.99 (NA) -0.19 (NA) 0.2 (NA) 0 (NA) 30 1 (NA) 0.8 (NA) 1 (NA) 0.34 (NA) 0.09 (NA) 0 (NA) 31 1 (NA) 0.8 (NA) 0.99 (NA) 0.18 (NA) 0.57 (NA) 0 (NA) 32 1 (NA) 0.8 (NA) 0.99 (NA) 0.33 (NA) 0.14 (NA) 0 (NA) 33 1 (NA) 0.4 (NA) 0.99 (NA) -0.27 (NA) 0.88 (NA) 0 (NA) 34 1 (NA) 0.4 (NA) 1 (NA) 0.99 (NA) 0.99 (NA) 0 (NA) 35 1 (NA) 0.8 (NA) 1 (NA) 0.79 (NA) 0.8 (NA) 0 (NA) 36 1 (NA) 0.6 (NA) 1 (NA) 0.79 (NA) 0.98 (NA) 0 (NA) 37 1 (NA) 0.6 (NA) 0.99 (NA) 0.86 (NA) 0.87 (NA) 0 (NA) 38 1 (NA) 0.6 (NA) 1 (NA) 0.71 (NA) 0.84 (NA) 0 (NA) 39 1 (NA) 0.2 (NA) 1 (NA) 0.68 (NA) 0.94 (NA) 0 (NA) 40 1 (NA) 0.4 (NA) 1 (NA) 0.79 (NA) 0.99 (NA) 0 (NA) 41 1 (NA) 0.6 (NA) 1 (NA) 0.92 (NA) 0.91 (NA) 0 (NA) 42 1 (NA) 0.6 (NA) 1 (NA) 0.79 (NA) 0.86 (NA) 0 (NA) 43 1 (NA) 1 (NA) 1 (NA) 0.81 (NA) 0.66 (NA) 0 (NA) 44 1 (NA) 0.6 (NA) 1 (NA) 0.49 (NA) 0.53 (NA) 0 (NA) 45 1 (NA) 0.2 (NA) 1 (NA) 0.91 (NA) 0.88 (NA) 0 (NA) 46 1 (NA) 1 (NA) 1 (NA) 0.88 (NA) 0.95 (NA) 0 (NA) 47 1 (NA) 0.6 (NA) 1 (NA) 0.38 (NA) -0.52 (NA) 0 (NA) 48 1 (NA) 0.2 (NA) 1 (NA) 0.66 (NA) 0.68 (NA) 0 (NA) 49 1 (NA) 0.4 (NA) 1 (NA) 0.72 (NA) 1 (NA) 0 (NA) 50 1 (NA) 1 (NA) 1 (NA) 0.94 (NA) 0.97 (NA) 0 (NA) 51 1 (NA) 0.4 (NA) 1 (NA) 0.6 (NA) 0.83 (NA) 0 (NA) 52 1 (NA) 0.8 (NA) 1 (NA) 0.91 (NA) 0.99 (NA) 0 (NA) 53 1 (NA) 0.4 (NA) 1 (NA) 0.9 (NA) 0.93 (NA) 0 (NA) 54 1 (NA) 0.6 (NA) 1 (NA) 0.84 (NA) 0.99 (NA) 0 (NA) 55 1 (NA) 0.8 (NA) 1 (NA) 0.96 (NA) 0.87 (NA) 0 (NA) 56 1 (NA) 0.6 (NA) 1 (NA) 0.93 (NA) 0.96 (NA) 0 (NA) Use plot(x) to plot results (nCases only), or as.data.frame(x) to see all results.> > > > > > cleanEx() > nameEx("null") > ### * null > > flush(stderr()); flush(stdout()) > > ### Name: null > ### Title: Returns NULL > ### Aliases: null > > ### ** Examples > > null("Not NULL") NULL > > > > ### *