Reanalyzing Hanania’s Survey Data
#Setup
library(pacman); p_load(bootnet, qgraph, igraph, dplyr, psych, ggplot2, EGAnet, lavaan, egg, qpcR, semPlot, OpenMx, mice, psychonetrics, NetworkToolbox, networkD3, magrittr)
#Automatic Kaiser-Guttman Test
KGA <- function(x){
SL = x$e.values
which.min(SL >= 1) - 1}
#Automatic Warne & Larsen (2014) Kaiser-Guttman revision
MAPA <- function(x, a = 0.05, s = 2, d = 3){
LE = x$e.values[x$factors]; LECIL = LE - abs((qnorm(a/s) * sqrt((2*LE^2)/(x$n.obs)))); LECIU = LE + abs((qnorm(a/s) * sqrt((2*LE^2)/(x$n.obs))))
DEC <- ifelse(LECIL < 1, "dropped.", "retained.")
S1 <- cat(paste("The smallest factor had an eigenvalue of", round((LE), d), "with a confidence interval of", round((LECIL), d), "to", round((LECIU), d), "so the factor should be", DEC))}
#Manual Warne & Larsen (2014) Kaiser-Guttman revision
MAPM <- function(x, a = 0.05, s = 2, d = 3, n){
LECIL = x - abs((qnorm(a/s) * sqrt((2*x^2)/(n)))); LECIU = x + abs((qnorm(a/s) * sqrt((2*x^2)/(n))))
DEC <- ifelse(LECIL < 1, "dropped.", "retained.")
S1 <- cat(paste("The smallest factor had an eigenvalue of", round((x), d), "with a confidence interval of", round((LECIL), d), "to", round((LECIU), d), "so the factor should be", DEC))}
#Automatic Percent of the Total Variance
PTV <- function(x){
TV = x$e.values/length(x$e.values)
return(TV)}
#Tucker's Congruence Coefficient
CONGO <- function(F1, F2) {
PHI = sum(F1*F2) / sqrt(sum(F1^2)*sum(F2^2))
return(PHI)}
#Total Variance of a Loading Vector
TVF <- function(x){
OUT <- sum((x^2)/length(x))
return(OUT)}
#Effective Dimensionality
estimate.ED <- function (x, sample.size = NULL, rel.values = NULL, cov.mat = FALSE, small.sample.c = FALSE, round.digits = 2, print.summary = TRUE) {
indefinite.matrix = FALSE
if (is.data.frame(x) == TRUE) {
sample.size = nrow(x)
if (cov.mat == FALSE) {
matrix = cor(x, use="pairwise.complete.obs")}
else matrix = cov(x, use="pairwise.complete.obs")}
else {
matrix = x
if ( ((sum(diag(matrix)) != nrow(matrix) ) | (var(diag(matrix)) != 0)) & (cov.mat == FALSE) ) {
matrix = cov2cor(matrix)}}
if ( (cov.mat == FALSE) & (is.null(rel.values) == FALSE) ) {
rel.matrix = sqrt(crossprod(t(rel.values), t(rel.values)))
diag(rel.matrix) = 1
matrix = matrix/rel.matrix}
output = list()
if (sum(eigen(matrix)$values < 0) > 0) {
indefinite.matrix = TRUE
matrix = nearPD(matrix, corr=!cov.mat)$mat}
eigen_val = sort(eigen(matrix)$values)
eigen_val.c = NULL
if (small.sample.c == TRUE) {
if (is.data.frame(x) == TRUE) {
if(cov.mat == FALSE) {
if(is.null(rel.values) == TRUE) {
suppress = file()
sink(file = suppress)
tmp = tau_estimate(as.matrix(scale(x)))
sink()
close(suppress)
eigen_val.c = tmp } else {
sink("NUL")
tmp = nlshrink_cov(as.matrix(scale(x)))
sink()
matrix.c = tmp/rel.matrix
if (sum(eigen(matrix.c)$values < 0) > 0) {
indefinite.matrix = TRUE
matrix.c = nearPD(matrix.c, corr=TRUE)$mat }
eigen_val.c = sort(eigen(matrix.c)$values)}} else {
suppress = file()
sink(file = suppress)
tmp = tau_estimate(as.matrix(x))
sink()
close(suppress)
eigen_val.c = tmp }}
else if (is.null(sample.size) == FALSE) {
eigen_val.rounded = round(eigen_val, 6)
eigen_val.c = eigen_val
function.body = paste(eigen_val.rounded[1],"/(",eigen_val.rounded[1],"-x)")
for(index in 2:length(eigen_val.rounded)) {
function.body = paste(function.body, "+",eigen_val.rounded[index],"/(",eigen_val.rounded[index],"-x)")}
function.body = paste(function.body,"-",sample.size)
eval(parse(text = paste("f = function(x) {", function.body,"}")))
unique.eigen = sum(!duplicated(eigen_val.rounded[eigen_val.rounded != 0]) )
mu_val = uniroot.all(f, interval=c(0, max(eigen_val.rounded)), n=10000000)
mu_val = mu_val[which( abs(f(mu_val)) %in% sort(abs(f(mu_val)))[1:unique.eigen] ) ]
mu.index = 1
for (index in 1:length(eigen_val.rounded)) {
if (eigen_val.rounded[index] != 0) {
if (duplicated(eigen_val.rounded)[index] == FALSE) {
eigen_val.c[index] = sample.size * (eigen_val.rounded[index] - mu_val[mu.index])
mu.index = mu.index + 1
} else {
eigen_val.c[index] = eigen_val.c[index-1]}}}}}
K = length(eigen_val)
eigen_sum = sum(eigen_val)
norm_eigen_val = eigen_val/eigen_sum
eigen_var = var(eigen_val)*((K-1)/K)
output$n1 = prod(norm_eigen_val^(-norm_eigen_val))
output$n2 = (eigen_sum^2)/sum(eigen_val^2)
output$nInf = eigen_sum/max(eigen_val)
output$nC = K - ((K^2)/(eigen_sum^2))*eigen_var
if ( (small.sample.c == TRUE) & (is.null(eigen_val.c) == FALSE) ) {
eigen_sum.c = sum(eigen_val.c)
norm_eigen_val.c = eigen_val.c/eigen_sum.c
eigen_var.c = var(eigen_val.c)*((K-1)/K)
output$n1.c = max(prod(norm_eigen_val.c^(-norm_eigen_val.c)), output$n1)
output$n2.c = max((eigen_sum.c^2)/sum(eigen_val.c^2), output$n2)
output$nInf.c = max(eigen_sum.c/max(eigen_val.c), output$nInf)
output$nC.c = max(K - ((K^2)/(eigen_sum.c^2))*eigen_var.c, output$nC) }
if (print.summary == TRUE) {
description = "ED estimated from the"
if (cov.mat == TRUE) {description = paste(description, "covariance matrix;")}
else {description = paste(description, "correlation matrix;")}
if (is.null(rel.values) == FALSE) {description = paste(description, "disattenuated;")}
else {description = paste(description, "no disattenuation;")}
if ( (small.sample.c == TRUE) & (is.null(eigen_val.c) == FALSE) ) {
if (is.data.frame(x) == TRUE) {description = paste(description, "corrected for small-sample bias (Ledoit & Wolf 2015).")}
else {description = paste(description, "corrected for small-sample bias (Mestre 2008).")}}
else {description = paste(description, "no small-sample correction.")}
if (indefinite.matrix == TRUE) {description = paste(description, "Warning: an indefinite matrix was detected and replaced with the nearest positive definite matrix.")}
print(description, quote = FALSE)
cat("\n")}
return(lapply(output,round,round.digits))}
FITM <- c("chisq", "df", "nPar", "cfi", "rmsea", "rmsea.ci.lower", "rmsea.ci.upper", "aic", "bic", "srmr")Rationale
TBD. I will not be sharing data unless Richard OKs it. The data is from the survey described here https://richardhanania.substack.com/p/survey-results-i-basic-demographics and here https://richardhanania.substack.com/p/survey-results-ii-likes-and-dislikes.
Analysis
Imputation
MICE or IRMI, it does basically the same thing. The problem with this is that imputation does mess up some clusters using some methods, like unpruned, unregularized EGA. The reason is that the data is MNAR: if people did not know a person in the survey, or they answered before some questions were added, their responses are missing. I have imputed with this code before, but I will not run it now because of the NMAR problem.
MicePiece <- mice(data, m = 1)
data <- complete(MicePiece)Exploratory Dimensionality
fa.parallel(data)## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in sqrt(1/diag(V)): NaNs produced## Warning in cov2cor(t(w) %*% r %*% w): diag(.) had 0 or NA entries; non-finite
## result is doubtful## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## In smc, smcs < 0 were set to .0## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully
## Parallel analysis suggests that the number of factors = 28 and the number of components = 21HananiaFA <- fa(data, nfactors = 27)## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Loading required namespace: GPArotation## Warning in GPFoblq(L, Tmat = Tmat, normalize = normalize, eps = eps, maxit =
## maxit, : convergence not obtained in GPFoblq. 1000 iterations used.## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefullynfactors(data); KGA(HananiaFA); MAPA(HananiaFA); PTV(HananiaFA); estimate.ED(data); EGA(data, plot.ega = T)## Warning in sqrt(e$values): NaNs produced## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined.
## Chi square is based upon observed residuals.
## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done
## Warning in cor.smooth(R): Matrix was not positive definite, smoothing was done## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done## The determinant of the smoothed correlation was zero.
## This means the objective function is not defined for the null model either.
## The Chi square is thus based upon observed correlations.## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
##
## Number of factors
## Call: vss(x = x, n = n, rotate = rotate, diagonal = diagonal, fm = fm,
## n.obs = n.obs, plot = FALSE, title = title, use = use, cor = cor)
## VSS complexity 1 achieves a maximimum of 0.66 with 1 factors
## VSS complexity 2 achieves a maximimum of 0.83 with 2 factors
## The Velicer MAP achieves a minimum of 0.01 with 14 factors
## Empirical BIC achieves a minimum of -123809.7 with 20 factors
## Sample Size adjusted BIC achieves a minimum of 16830.96 with 18 factors
##
## Statistics by number of factors
## vss1 vss2 map dof chisq prob sqresid fit RMSEA BIC SABIC
## 1 0.66 0.00 0.0244 29889 1411283 0 1185 0.66 0.190 1197556 1292498
## 2 0.63 0.83 0.0157 29644 721772 0 607 0.83 0.135 509797 603961
## 3 0.48 0.82 0.0115 29400 481179 0 405 0.88 0.110 270948 364337
## 4 0.42 0.74 0.0090 29157 354423 0 298 0.92 0.094 145930 238547
## 5 0.40 0.71 0.0078 28915 288787 0 243 0.93 0.084 82025 173873
## 6 0.39 0.67 0.0066 28674 238612 0 201 0.94 0.076 33573 124655
## 7 0.38 0.67 0.0060 28434 210066 0 177 0.95 0.071 6743 97063
## 8 0.38 0.67 0.0058 28195 193964 0 164 0.95 0.068 -7650 81911
## 9 0.38 0.68 0.0056 27957 180436 0 152 0.96 0.065 -19476 69329
## 10 0.38 0.66 0.0055 27720 169439 0 143 0.96 0.063 -28778 59274
## 11 0.37 0.66 0.0054 27484 159437 0 135 0.96 0.061 -37092 50210
## 12 0.38 0.66 0.0054 27249 151274 0 128 0.96 0.060 -43575 42981
## 13 0.38 0.66 0.0053 27015 144473 0 122 0.97 0.058 -48703 37110
## 14 0.38 0.66 0.0053 26782 138620 0 117 0.97 0.057 -52890 32183
## 15 0.37 0.66 0.0054 26550 133355 0 113 0.97 0.056 -56496 27839
## 16 0.37 0.66 0.0054 26319 128155 0 109 0.97 0.055 -60045 23557
## 17 0.37 0.66 0.0054 26089 123834 0 105 0.97 0.054 -62721 20150
## 18 0.37 0.65 0.0055 25860 119604 0 101 0.97 0.053 -65313 16831
## 19 0.33 0.61 0.0056 25632 888728 0 98 0.97 0.163 705442 786861
## 20 0.32 0.61 0.0057 25405 886396 0 95 0.97 0.163 704733 785431
## complex eChisq SRMR eCRMS eBIC
## 1 1.0 1299201 0.130 0.131 1085474
## 2 1.3 608234 0.089 0.090 396259
## 3 1.7 374960 0.070 0.071 164730
## 4 2.0 255463 0.058 0.059 46970
## 5 2.3 196325 0.051 0.052 -10438
## 6 2.5 151698 0.044 0.046 -53342
## 7 2.7 127606 0.041 0.042 -75717
## 8 2.8 114946 0.039 0.040 -86668
## 9 2.9 104673 0.037 0.038 -95239
## 10 3.1 96605 0.035 0.037 -101613
## 11 3.2 89270 0.034 0.036 -107260
## 12 3.2 83636 0.033 0.035 -111213
## 13 3.3 78847 0.032 0.034 -114329
## 14 3.4 74913 0.031 0.033 -116597
## 15 3.4 71508 0.031 0.032 -118344
## 16 3.5 68201 0.030 0.032 -119998
## 17 3.6 65466 0.029 0.031 -121088
## 18 3.6 62787 0.029 0.031 -122130
## 19 3.8 60159 0.028 0.030 -123128
## 20 3.8 57854 0.027 0.030 -123810## [1] 49## The smallest factor had an eigenvalue of 1.505 with a confidence interval of 1.389 to 1.622 so the factor should be retained.## [1] 1.962679e-01 9.783610e-02 5.781771e-02 4.198637e-02 3.023769e-02
## [6] 2.645307e-02 1.997532e-02 1.503643e-02 1.381314e-02 1.246861e-02
## [11] 1.189448e-02 1.078343e-02 9.810195e-03 9.123258e-03 8.692041e-03
## [16] 8.605910e-03 7.880885e-03 7.816940e-03 7.607366e-03 7.289442e-03
## [21] 7.113159e-03 6.830572e-03 6.680527e-03 6.447033e-03 6.421975e-03
## [26] 6.296742e-03 6.119479e-03 6.081363e-03 5.923075e-03 5.740887e-03
## [31] 5.637679e-03 5.565700e-03 5.425699e-03 5.368589e-03 5.251272e-03
## [36] 5.167557e-03 5.020854e-03 4.968219e-03 4.855343e-03 4.711299e-03
## [41] 4.655803e-03 4.596300e-03 4.507306e-03 4.433090e-03 4.342006e-03
## [46] 4.331266e-03 4.208267e-03 4.186397e-03 4.081962e-03 4.050528e-03
## [51] 4.032120e-03 3.962045e-03 3.905327e-03 3.867459e-03 3.746251e-03
## [56] 3.722739e-03 3.665565e-03 3.604995e-03 3.537422e-03 3.506350e-03
## [61] 3.474312e-03 3.442560e-03 3.361637e-03 3.356114e-03 3.319836e-03
## [66] 3.222761e-03 3.175470e-03 3.131324e-03 3.111547e-03 3.042808e-03
## [71] 3.022852e-03 2.955289e-03 2.937486e-03 2.898044e-03 2.850015e-03
## [76] 2.825767e-03 2.803270e-03 2.780997e-03 2.767219e-03 2.727701e-03
## [81] 2.682063e-03 2.627966e-03 2.619374e-03 2.583529e-03 2.556922e-03
## [86] 2.509093e-03 2.500866e-03 2.464873e-03 2.430053e-03 2.414936e-03
## [91] 2.405801e-03 2.392864e-03 2.353802e-03 2.305450e-03 2.265596e-03
## [96] 2.237925e-03 2.202727e-03 2.166586e-03 2.153949e-03 2.094455e-03
## [101] 2.068953e-03 2.052370e-03 2.029566e-03 2.023925e-03 2.003125e-03
## [106] 1.965690e-03 1.960539e-03 1.917343e-03 1.883647e-03 1.863325e-03
## [111] 1.851809e-03 1.825493e-03 1.799429e-03 1.788438e-03 1.751547e-03
## [116] 1.721880e-03 1.714025e-03 1.706131e-03 1.688573e-03 1.670057e-03
## [121] 1.628606e-03 1.615598e-03 1.606356e-03 1.577554e-03 1.536357e-03
## [126] 1.535009e-03 1.525024e-03 1.501358e-03 1.464177e-03 1.447021e-03
## [131] 1.437731e-03 1.423148e-03 1.409653e-03 1.395353e-03 1.387685e-03
## [136] 1.375339e-03 1.350476e-03 1.318988e-03 1.301232e-03 1.278504e-03
## [141] 1.275782e-03 1.264969e-03 1.252469e-03 1.220810e-03 1.201763e-03
## [146] 1.162620e-03 1.148986e-03 1.137938e-03 1.117284e-03 1.105164e-03
## [151] 1.096773e-03 1.072022e-03 1.066185e-03 1.045233e-03 1.038600e-03
## [156] 1.029107e-03 1.008210e-03 1.000988e-03 9.841519e-04 9.695810e-04
## [161] 9.520808e-04 9.278417e-04 9.093640e-04 8.807553e-04 8.692024e-04
## [166] 8.656519e-04 8.393290e-04 8.295772e-04 8.171738e-04 7.967967e-04
## [171] 7.784265e-04 7.657310e-04 7.468374e-04 7.290109e-04 7.060642e-04
## [176] 6.966075e-04 6.920103e-04 6.768750e-04 6.604178e-04 6.435443e-04
## [181] 6.305510e-04 6.235409e-04 6.048339e-04 5.905986e-04 5.844893e-04
## [186] 5.676079e-04 5.528722e-04 5.415745e-04 5.140748e-04 4.916938e-04
## [191] 4.690709e-04 4.527213e-04 4.405674e-04 4.273570e-04 3.964353e-04
## [196] 3.820476e-04 3.776786e-04 3.596414e-04 3.345997e-04 3.233837e-04
## [201] 3.155798e-04 2.899350e-04 2.598409e-04 2.441498e-04 2.263635e-04
## [206] 2.039787e-04 1.773535e-04 1.613031e-04 1.452867e-04 1.281803e-04
## [211] 8.040039e-05 6.589345e-05 4.230593e-05 1.246090e-05 -1.521563e-06
## [216] -1.738952e-05 -4.856929e-05 -7.390202e-05 -1.441135e-04 -1.894202e-04
## [221] -2.115392e-04 -2.321199e-04 -2.730877e-04 -3.181124e-04 -3.264182e-04
## [226] -3.797286e-04 -4.447010e-04 -4.648030e-04 -4.713911e-04 -5.412177e-04
## [231] -5.493254e-04 -6.211420e-04 -6.638965e-04 -6.800829e-04 -8.825406e-04
## [236] -9.187484e-04 -9.562684e-04 -9.925296e-04 -1.103512e-03 -1.215443e-03
## [241] -1.343955e-03 -1.536083e-03 -1.555714e-03 -1.861107e-03 -1.983172e-03
## [246] -2.542125e-03## [1] ED estimated from the correlation matrix; no disattenuation; no small-sample correction. Warning: an indefinite matrix was detected and replaced with the nearest positive definite matrix.## $n1
## [1] 58.41
##
## $n2
## [1] 17.3
##
## $nInf
## [1] 5.1
##
## $nC
## [1] 232.78## Warning in EGA(data, plot.ega = T): Previous versions of EGAnet (<= 0.9.8)
## checked unidimensionality using [4;muni.method = "expand"[0m as the default## [1;m[4;m
## Exploratory Graph Analysis
## [0m[0m## • model = glasso
## • algorithm = walktrap
## • correlation = cor_auto
## • unidimensional check = leading eigenvalue## Variables detected as ordinal: capitalism; onlyfans; washington; sowell; adamsmith; lincoln; betteroff; tyler; jefferson; scottalexander; hanania; razib; hk; raceiq; tabarrok; friedman; hanson; suffrage; yang; natalism; lee; lemoine; climatechange; mlk; caplan; vaccines; henderson; elon; hananiatwitter; andreessen; democracy; rogan; crtban; deboer; clarence; pinker; greenwald; abe; weiss; hitchens; ea; yimby; thiel; graham; peterson; lesswrong; rationalist; sailer; genderroles; bullying; rufo; desantis; libsoftiktok; mcardle; eliezer; kaufmann; emil; usleadership; yglesias; taleb; ronpaul; wsj; sullivan; terfs; rittenhouse; claire; drugs; reagan; cummings; equal; fedoc; masters; geoffreymiller; gabbard; rothbard; sibarium; tracey; barro; nationalism; bezos; yarvin; saagar; womb; claremont; embryo; improvegenetics; unz; inherentiq; corporations; aella; americansnationalism; beattie; abortiondis; goldberg; labmeat; utilitarianism; taylor; transadult; vance; incarcerate; antiaging; eweinstein; schlafly; heartiste; lind; cra; hochman; bap; karlin; factoryfarm; noahsmith; krystal; young; thirdworld; nr; guns; zelensky; yoram; buchanan; ai; israel; nowrasteh; deng; gates; zionism; tucker; ahmari; replacement; vegetarianism; shapiro; plastic; organs; orban; dinosaurs; defendtaiwan; death; god; paytax; cernovich; shoot; profiling; singer; polis; atlantic; vermeule; iran; koch; miller; safetynet; womenbreasts; romney; trust; robertelee; klein; ukraineaid; french; socialdemocracy; pence; nixon; rbg; transhuman; nader; macron; bulwark; theology; naacp; obama; banabortion; promiscuity; boris; merkel; tariffs; clinton; breitbart; feminism; bannon; prejudicewomen; fat; trump; polyamory; republicans; porn; zuckerberg; fox; lbj; bernie; openborders; climate; pinochet; nineeleven; tnr; incest; fuentes; chapo; cia; jeffersondavis; adl; oann; bush; krugman; bugs; fauci; jones; nyt; wp; vox; incels; lgbt; biden; overpopulated; stole; aclu; assad; putin; pressure; libshonest; marx; democrats; cnn; aoc; aliens; masks; pelosi; newsom; fewerchildren; xi; wn; omar; hillary; msnbc; transwomen; kamala; blm; iraq; ccp; transminors; castro; taliban; crt; hweinstein; mao; epstein; kim; hitler; stalin; isis## Warning in qgraph::cor_auto(data, forcePD = TRUE): Correlation matrix is not
## positive definite. Finding nearest positive definite matrix## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2
## EGA Results:
##
## Number of Dimensions:
## [1] 11
##
## Items per Dimension:
## items dimension
## ea ea 1
## drugs drugs 1
## womb womb 1
## embryo embryo 1
## improvegenetics improvegenetics 1
## abortiondis abortiondis 1
## labmeat labmeat 1
## utilitarianism utilitarianism 1
## transadult transadult 1
## antiaging antiaging 1
## factoryfarm factoryfarm 1
## vegetarianism vegetarianism 1
## god god 1
## singer singer 1
## transhuman transhuman 1
## theology theology 1
## banabortion banabortion 1
## polyamory polyamory 1
## porn porn 1
## incest incest 1
## bugs bugs 1
## onlyfans onlyfans 2
## hanania hanania 2
## hananiatwitter hananiatwitter 2
## crtban crtban 2
## bullying bullying 2
## terfs terfs 2
## rbg rbg 2
## naacp naacp 2
## feminism feminism 2
## prejudicewomen prejudicewomen 2
## lgbt lgbt 2
## transwomen transwomen 2
## blm blm 2
## transminors transminors 2
## crt crt 2
## plastic plastic 3
## womenbreasts womenbreasts 3
## hk hk 4
## usleadership usleadership 4
## zelensky zelensky 4
## deng deng 4
## defendtaiwan defendtaiwan 4
## ukraineaid ukraineaid 4
## assad assad 4
## putin putin 4
## marx marx 4
## xi xi 4
## ccp ccp 4
## castro castro 4
## taliban taliban 4
## mao mao 4
## kim kim 4
## stalin stalin 4
## isis isis 4
## tyler tyler 5
## razib razib 5
## tabarrok tabarrok 5
## hanson hanson 5
## yang yang 5
## lee lee 5
## lemoine lemoine 5
## caplan caplan 5
## henderson henderson 5
## elon elon 5
## andreessen andreessen 5
## rogan rogan 5
## deboer deboer 5
## pinker pinker 5
## greenwald greenwald 5
## weiss weiss 5
## hitchens hitchens 5
## thiel thiel 5
## graham graham 5
## peterson peterson 5
## mcardle mcardle 5
## kaufmann kaufmann 5
## emil emil 5
## yglesias yglesias 5
## taleb taleb 5
## sullivan sullivan 5
## claire claire 5
## cummings cummings 5
## geoffreymiller geoffreymiller 5
## gabbard gabbard 5
## sibarium sibarium 5
## tracey tracey 5
## barro barro 5
## bezos bezos 5
## saagar saagar 5
## unz unz 5
## aella aella 5
## goldberg goldberg 5
## taylor taylor 5
## eweinstein eweinstein 5
## schlafly schlafly 5
## heartiste heartiste 5
## lind lind 5
## hochman hochman 5
## bap bap 5
## karlin karlin 5
## noahsmith noahsmith 5
## young young 5
## yoram yoram 5
## ahmari ahmari 5
## shapiro shapiro 5
## dinosaurs dinosaurs 5
## polis polis 5
## vermeule vermeule 5
## robertelee robertelee 5
## french french 5
## bulwark bulwark 5
## fuentes fuentes 5
## jeffersondavis jeffersondavis 5
## washington washington 6
## lincoln lincoln 6
## jefferson jefferson 6
## raceiq raceiq 6
## suffrage suffrage 6
## mlk mlk 6
## democracy democracy 6
## abe abe 6
## sailer sailer 6
## genderroles genderroles 6
## equal equal 6
## nationalism nationalism 6
## inherentiq inherentiq 6
## americansnationalism americansnationalism 6
## incarcerate incarcerate 6
## cra cra 6
## thirdworld thirdworld 6
## israel israel 6
## zionism zionism 6
## replacement replacement 6
## death death 6
## shoot shoot 6
## profiling profiling 6
## nixon nixon 6
## promiscuity promiscuity 6
## fat fat 6
## pinochet pinochet 6
## incels incels 6
## pressure pressure 6
## wn wn 6
## hweinstein hweinstein 6
## epstein epstein 6
## hitler hitler 6
## clarence clarence 7
## rufo rufo 7
## desantis desantis 7
## libsoftiktok libsoftiktok 7
## wsj wsj 7
## rittenhouse rittenhouse 7
## reagan reagan 7
## fedoc fedoc 7
## masters masters 7
## yarvin yarvin 7
## claremont claremont 7
## beattie beattie 7
## vance vance 7
## nr nr 7
## buchanan buchanan 7
## tucker tucker 7
## orban orban 7
## cernovich cernovich 7
## iran iran 7
## koch koch 7
## miller miller 7
## romney romney 7
## pence pence 7
## boris boris 7
## breitbart breitbart 7
## bannon bannon 7
## trump trump 7
## republicans republicans 7
## fox fox 7
## nineeleven nineeleven 7
## cia cia 7
## oann oann 7
## bush bush 7
## jones jones 7
## stole stole 7
## iraq iraq 7
## nyt nyt 8
## wp wp 8
## biden biden 8
## democrats democrats 8
## cnn cnn 8
## pelosi pelosi 8
## newsom newsom 8
## hillary hillary 8
## msnbc msnbc 8
## kamala kamala 8
## capitalism capitalism 9
## sowell sowell 9
## adamsmith adamsmith 9
## betteroff betteroff 9
## friedman friedman 9
## natalism natalism 9
## climatechange climatechange 9
## vaccines vaccines 9
## yimby yimby 9
## ronpaul ronpaul 9
## rothbard rothbard 9
## corporations corporations 9
## krystal krystal 9
## guns guns 9
## ai ai 9
## nowrasteh nowrasteh 9
## gates gates 9
## organs organs 9
## paytax paytax 9
## safetynet safetynet 9
## socialdemocracy socialdemocracy 9
## nader nader 9
## macron macron 9
## tariffs tariffs 9
## zuckerberg zuckerberg 9
## lbj lbj 9
## bernie bernie 9
## openborders openborders 9
## climate climate 9
## chapo chapo 9
## adl adl 9
## overpopulated overpopulated 9
## aliens aliens 9
## fewerchildren fewerchildren 9
## atlantic atlantic 10
## trust trust 10
## klein klein 10
## obama obama 10
## merkel merkel 10
## clinton clinton 10
## tnr tnr 10
## krugman krugman 10
## fauci fauci 10
## vox vox 10
## aclu aclu 10
## libshonest libshonest 10
## aoc aoc 10
## masks masks 10
## omar omar 10
## scottalexander scottalexander 11
## lesswrong lesswrong 11
## rationalist rationalist 11
## eliezer eliezer 11Triangulated Maximally Filtered Graph
Because a partial, regularized network model would take me 14 hours to fit with psychonetrics, I am not going to do that. I will just fit a triangulated maximally filtered graph, or TMFG, and then make it so people can interact with it. The TMFG is good enough as a data description, and it looks very interesting to boot. Here’s how it works: the TMFG structurally constraints the number of bivariate correlations in a network model as 3k - 6, where k is the total number of variables to be modeled. The algorithm is fitted to the data by scouring it for the four variables who have the highest sum of correlations with every other variable, and then every other variable is added in order of the highest sum of correlations with three other variables that have already been modeled until, finally, every variable has been added. This can be turned into a graphical Gaussian model with relative ease.
EGA(data, plot.ega = T, model = "TMFG")## Warning in EGA(data, plot.ega = T, model = "TMFG"): Previous versions of EGAnet
## (<= 0.9.8) checked unidimensionality using [4;muni.method = "expand"[0m as the
## default## [1;m[4;m
## Exploratory Graph Analysis
## [0m[0m## • model = TMFG
## • algorithm = walktrap
## • correlation = cor_auto
## • unidimensional check = leading eigenvalue## Variables detected as ordinal: capitalism; onlyfans; washington; sowell; adamsmith; lincoln; betteroff; tyler; jefferson; scottalexander; hanania; razib; hk; raceiq; tabarrok; friedman; hanson; suffrage; yang; natalism; lee; lemoine; climatechange; mlk; caplan; vaccines; henderson; elon; hananiatwitter; andreessen; democracy; rogan; crtban; deboer; clarence; pinker; greenwald; abe; weiss; hitchens; ea; yimby; thiel; graham; peterson; lesswrong; rationalist; sailer; genderroles; bullying; rufo; desantis; libsoftiktok; mcardle; eliezer; kaufmann; emil; usleadership; yglesias; taleb; ronpaul; wsj; sullivan; terfs; rittenhouse; claire; drugs; reagan; cummings; equal; fedoc; masters; geoffreymiller; gabbard; rothbard; sibarium; tracey; barro; nationalism; bezos; yarvin; saagar; womb; claremont; embryo; improvegenetics; unz; inherentiq; corporations; aella; americansnationalism; beattie; abortiondis; goldberg; labmeat; utilitarianism; taylor; transadult; vance; incarcerate; antiaging; eweinstein; schlafly; heartiste; lind; cra; hochman; bap; karlin; factoryfarm; noahsmith; krystal; young; thirdworld; nr; guns; zelensky; yoram; buchanan; ai; israel; nowrasteh; deng; gates; zionism; tucker; ahmari; replacement; vegetarianism; shapiro; plastic; organs; orban; dinosaurs; defendtaiwan; death; god; paytax; cernovich; shoot; profiling; singer; polis; atlantic; vermeule; iran; koch; miller; safetynet; womenbreasts; romney; trust; robertelee; klein; ukraineaid; french; socialdemocracy; pence; nixon; rbg; transhuman; nader; macron; bulwark; theology; naacp; obama; banabortion; promiscuity; boris; merkel; tariffs; clinton; breitbart; feminism; bannon; prejudicewomen; fat; trump; polyamory; republicans; porn; zuckerberg; fox; lbj; bernie; openborders; climate; pinochet; nineeleven; tnr; incest; fuentes; chapo; cia; jeffersondavis; adl; oann; bush; krugman; bugs; fauci; jones; nyt; wp; vox; incels; lgbt; biden; overpopulated; stole; aclu; assad; putin; pressure; libshonest; marx; democrats; cnn; aoc; aliens; masks; pelosi; newsom; fewerchildren; xi; wn; omar; hillary; msnbc; transwomen; kamala; blm; iraq; ccp; transminors; castro; taliban; crt; hweinstein; mao; epstein; kim; hitler; stalin; isis## Warning in qgraph::cor_auto(data, forcePD = TRUE): Correlation matrix is not
## positive definite. Finding nearest positive definite matrix
## EGA Results:
##
## Number of Dimensions:
## [1] 16
##
## Items per Dimension:
## items dimension
## raceiq raceiq 1
## yimby yimby 1
## sailer sailer 1
## emil emil 1
## nationalism nationalism 1
## unz unz 1
## inherentiq inherentiq 1
## americansnationalism americansnationalism 1
## taylor taylor 1
## incarcerate incarcerate 1
## heartiste heartiste 1
## thirdworld thirdworld 1
## buchanan buchanan 1
## nowrasteh nowrasteh 1
## replacement replacement 1
## orban orban 1
## death death 1
## shoot shoot 1
## profiling profiling 1
## robertelee robertelee 1
## nixon nixon 1
## tariffs tariffs 1
## openborders openborders 1
## pinochet pinochet 1
## jeffersondavis jeffersondavis 1
## lgbt lgbt 1
## overpopulated overpopulated 1
## assad assad 1
## pressure pressure 1
## wn wn 1
## hitler hitler 1
## greenwald greenwald 2
## ronpaul ronpaul 2
## rittenhouse rittenhouse 2
## masters masters 2
## gabbard gabbard 2
## rothbard rothbard 2
## tracey tracey 2
## yarvin yarvin 2
## beattie beattie 2
## vance vance 2
## schlafly schlafly 2
## bap bap 2
## karlin karlin 2
## tucker tucker 2
## ahmari ahmari 2
## cernovich cernovich 2
## vermeule vermeule 2
## miller miller 2
## breitbart breitbart 2
## bannon bannon 2
## trump trump 2
## republicans republicans 2
## fox fox 2
## fuentes fuentes 2
## oann oann 2
## jones jones 2
## noahsmith noahsmith 3
## guns guns 3
## polis polis 3
## atlantic atlantic 3
## trust trust 3
## klein klein 3
## macron macron 3
## bulwark bulwark 3
## obama obama 3
## clinton clinton 3
## lbj lbj 3
## climate climate 3
## tnr tnr 3
## krugman krugman 3
## fauci fauci 3
## nyt nyt 3
## wp wp 3
## vox vox 3
## biden biden 3
## aclu aclu 3
## libshonest libshonest 3
## democrats democrats 3
## cnn cnn 3
## masks masks 3
## pelosi pelosi 3
## newsom newsom 3
## hillary hillary 3
## msnbc msnbc 3
## kamala kamala 3
## vaccines vaccines 4
## usleadership usleadership 4
## wsj wsj 4
## nr nr 4
## zelensky zelensky 4
## defendtaiwan defendtaiwan 4
## romney romney 4
## ukraineaid ukraineaid 4
## french french 4
## pence pence 4
## boris boris 4
## nineeleven nineeleven 4
## cia cia 4
## bush bush 4
## stole stole 4
## putin putin 4
## aliens aliens 4
## iraq iraq 4
## washington washington 5
## sowell sowell 5
## jefferson jefferson 5
## hanania hanania 5
## elon elon 5
## hananiatwitter hananiatwitter 5
## andreessen andreessen 5
## rogan rogan 5
## clarence clarence 5
## thiel thiel 5
## peterson peterson 5
## rufo rufo 5
## desantis desantis 5
## libsoftiktok libsoftiktok 5
## reagan reagan 5
## fedoc fedoc 5
## claremont claremont 5
## eweinstein eweinstein 5
## israel israel 5
## zionism zionism 5
## shapiro shapiro 5
## iran iran 5
## razib razib 6
## yang yang 6
## lee lee 6
## lemoine lemoine 6
## henderson henderson 6
## abe abe 6
## graham graham 6
## kaufmann kaufmann 6
## taleb taleb 6
## cummings cummings 6
## geoffreymiller geoffreymiller 6
## sibarium sibarium 6
## saagar saagar 6
## goldberg goldberg 6
## lind lind 6
## hochman hochman 6
## krystal krystal 6
## yoram yoram 6
## lincoln lincoln 7
## suffrage suffrage 7
## natalism natalism 7
## mlk mlk 7
## democracy democracy 7
## genderroles genderroles 7
## equal equal 7
## cra cra 7
## rbg rbg 7
## promiscuity promiscuity 7
## feminism feminism 7
## fat fat 7
## adl adl 7
## fewerchildren fewerchildren 7
## hk hk 8
## deng deng 8
## incels incels 8
## xi xi 8
## ccp ccp 8
## castro castro 8
## taliban taliban 8
## hweinstein hweinstein 8
## mao mao 8
## epstein epstein 8
## kim kim 8
## stalin stalin 8
## isis isis 8
## drugs drugs 9
## abortiondis abortiondis 9
## transadult transadult 9
## plastic plastic 9
## god god 9
## womenbreasts womenbreasts 9
## theology theology 9
## banabortion banabortion 9
## polyamory polyamory 9
## porn porn 9
## incest incest 9
## onlyfans onlyfans 10
## crtban crtban 10
## bullying bullying 10
## terfs terfs 10
## naacp naacp 10
## merkel merkel 10
## prejudicewomen prejudicewomen 10
## chapo chapo 10
## aoc aoc 10
## omar omar 10
## transwomen transwomen 10
## blm blm 10
## transminors transminors 10
## crt crt 10
## capitalism capitalism 11
## adamsmith adamsmith 11
## betteroff betteroff 11
## tyler tyler 11
## tabarrok tabarrok 11
## friedman friedman 11
## hanson hanson 11
## caplan caplan 11
## mcardle mcardle 11
## koch koch 11
## bezos bezos 12
## womb womb 12
## embryo embryo 12
## improvegenetics improvegenetics 12
## corporations corporations 12
## utilitarianism utilitarianism 12
## antiaging antiaging 12
## gates gates 12
## organs organs 12
## dinosaurs dinosaurs 12
## singer singer 12
## transhuman transhuman 12
## zuckerberg zuckerberg 12
## deboer deboer 13
## weiss weiss 13
## hitchens hitchens 13
## yglesias yglesias 13
## sullivan sullivan 13
## claire claire 13
## barro barro 13
## young young 13
## climatechange climatechange 14
## labmeat labmeat 14
## factoryfarm factoryfarm 14
## vegetarianism vegetarianism 14
## bugs bugs 14
## scottalexander scottalexander 15
## pinker pinker 15
## ea ea 15
## lesswrong lesswrong 15
## rationalist rationalist 15
## eliezer eliezer 15
## aella aella 15
## ai ai 15
## paytax paytax 16
## safetynet safetynet 16
## socialdemocracy socialdemocracy 16
## nader nader 16
## bernie bernie 16
## marx marx 16Now, here’s the fun part. Enjoy playing around with this graph!
forceNetwork(Links = TMFGD3$links, Nodes = TMFGD3$nodes,
Source = 'source', Target = 'target',
NodeID = 'name', Group = 'group', opacity = 1, zoom = T) #Zoom out and scroll around!