Structural Equation Models with analysis Bayesian for Quality of life
Mauricio Hernández Carrillo
April 5rd, 2022
Paquetes requeridos
library(future)
future::plan("multisession") # Windows
library(lavaan)## This is lavaan 0.6-10
## lavaan is FREE software! Please report any bugs.library(blavaan)## Loading required package: Rcpp## This is blavaan 0.4-1## On multicore systems, we suggest use of future::plan("multicore") or
## future::plan("multisession") for faster post-MCMC computations.library(semPlot)## Found more than one class "family" in cache; using the first, from namespace 'MatrixModels'## Also defined by 'lme4'## Found more than one class "family" in cache; using the first, from namespace 'MatrixModels'## Also defined by 'lme4'## Found more than one class "family" in cache; using the first, from namespace 'MatrixModels'## Also defined by 'lme4'library(bayestestR)## Warning: package 'bayestestR' was built under R version 4.1.3library(sjPlot)## Warning: package 'sjPlot' was built under R version 4.1.3library(knitr)
#leer la base de datos
datos <- readRDS("data/datos.RDS")
#comparacion de modelos
#MODELO DE REFERENCIA
model_bayesianoref <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad
# residual correlations
'
fitref <- bsem(
model = model_bayesianoref,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 26.22 seconds (Warm-up)
## Chain 1: 45.471 seconds (Sampling)
## Chain 1: 71.691 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0.001 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 29.231 seconds (Warm-up)
## Chain 2: 42.445 seconds (Sampling)
## Chain 2: 71.676 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 24.959 seconds (Warm-up)
## Chain 3: 36.155 seconds (Sampling)
## Chain 3: 61.114 seconds (Total)
## Chain 3:## Warning: Tail Effective Samples Size (ESS) is too low, indicating posterior variances and tail quantiles may be unreliable.
## Running the chains for more iterations may help. See
## https://mc-stan.org/misc/warnings.html#tail-ess## Computing posterior predictives...summary(fitref,standardized = TRUE)## blavaan (0.4-1) results of 1000 samples after 500 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -519.174 0.209
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.541 0.813
## F_c30 1.438 0.157 1.177 1.780 0.778 0.939
## sintomas =~
## S_br23 1.000 0.331 0.588
## S_c30 2.378 0.656 1.655 3.726 0.787 0.932
## Rhat Prior
##
##
## 1.000 normal(0,15)
##
##
## 1.009 normal(0,15)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) -1.618 0.443 -2.581 -1.075 -0.989 -0.989
## CV_Gral ~
## Salud (c) 0.750 0.085 0.563 0.902 0.750 0.765
## sintomas (e) -0.607 7.318 -16.903 13.688 -0.201 -0.110
## funcionldd (d) 0.341 4.662 -9.169 9.575 0.185 0.101
## Salud ~
## sintomas -5.149 8.452 -22.773 10.897 -1.704 -0.916
## funcionldd (b) -0.593 5.442 -12.004 9.669 -0.321 -0.173
## Rhat Prior
##
## 1.006 normal(0,10)
##
## 1.001 normal(0,10)
## 1.001 normal(0,10)
## 1.001 normal(0,10)
##
## 1.001 normal(-10,10)
## 1.002 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.339 0.071 2.199 2.479 2.339 3.512
## .F_c30 2.432 0.086 2.261 2.603 2.432 2.933
## .S_br23 1.767 0.062 1.646 1.887 1.767 3.144
## .S_c30 2.169 0.089 1.993 2.340 2.169 2.570
## .CV_Gral 0.846 0.379 0.152 1.667 0.846 0.464
## .Salud 4.328 0.202 3.944 4.729 4.328 2.328
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 1.001 normal(0,32)
## 1.001 normal(0,32)
## 1.000 normal(0,32)
## 1.002 normal(0,32)
## 1.001 normal(0,10)
## 1.000 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.150 0.030 0.100 0.219 0.150 0.339
## .F_c30 0.082 0.028 0.031 0.141 0.082 0.119
## .S_br23 0.207 0.036 0.148 0.286 0.207 0.654
## .S_c30 0.093 0.035 0.012 0.161 0.093 0.131
## .CV_Gral 0.433 0.107 0.190 0.640 0.433 0.131
## .Salud 1.534 0.333 0.862 2.226 1.534 0.444
## .funcionalidad 0.007 0.010 0.000 0.038 0.022 0.022
## sintomas 0.109 0.042 0.038 0.205 1.000 1.000
## Rhat Prior
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.005 gamma(1,.5)[sd]
## 1.003 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.007 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]plot(fitref)
#SEM Bayesiano final utilizando variables moderadoras
#Modelo 1.0 interaccion Edad
model_bayesiano1.0 <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad + Edad
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad
# residual correlations
'
fitedad1.0 <- bsem(
model = model_bayesiano1.0,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 46.761 seconds (Warm-up)
## Chain 1: 81.978 seconds (Sampling)
## Chain 1: 128.739 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 46.935 seconds (Warm-up)
## Chain 2: 61.924 seconds (Sampling)
## Chain 2: 108.859 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 47.249 seconds (Warm-up)
## Chain 3: 77.817 seconds (Sampling)
## Chain 3: 125.066 seconds (Total)
## Chain 3:
## Computing posterior predictives...summary(fitedad1.0,standardized = TRUE)## blavaan (0.4-1) results of 1000 samples after 500 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -526.876 0.030
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.537 0.810
## F_c30 1.435 0.157 1.171 1.779 0.770 0.938
## sintomas =~
## S_br23 1.000 0.330 0.588
## S_c30 2.352 0.477 1.669 3.551 0.777 0.930
## Rhat Prior
##
##
## 1.000 normal(0,15)
##
##
## 1.001 normal(0,15)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) -1.606 0.344 -2.406 -1.097 -0.988 -0.988
## CV_Gral ~
## Salud (c) 0.742 0.086 0.573 0.905 0.742 0.752
## sintomas (e) -1.593 7.331 -16.493 13.581 -0.526 -0.287
## funcionldd (d) -0.210 4.646 -9.875 9.293 -0.113 -0.061
## Edad -0.005 0.007 -0.019 0.009 -0.005 -0.033
## Salud ~
## sintomas -5.530 8.053 -22.505 8.945 -1.827 -0.983
## funcionldd (b) -0.842 5.077 -11.808 8.190 -0.452 -0.243
## Rhat Prior
##
## 1.001 normal(0,10)
##
## 1.001 normal(0,10)
## 1.002 normal(0,10)
## 1.002 normal(0,10)
## 1.000 normal(0,10)
##
## 1.004 normal(-10,10)
## 1.004 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.340 0.072 2.198 2.481 2.340 3.534
## .F_c30 2.435 0.087 2.268 2.610 2.435 2.967
## .S_br23 1.767 0.064 1.643 1.894 1.767 3.145
## .S_c30 2.166 0.089 1.992 2.338 2.166 2.593
## .CV_Gral 1.146 0.576 0.038 2.252 1.146 0.625
## .Salud 4.331 0.205 3.929 4.736 4.331 2.331
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 1.001 normal(0,32)
## 1.001 normal(0,32)
## 1.000 normal(0,32)
## 1.001 normal(0,32)
## 1.001 normal(0,10)
## 1.000 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.150 0.029 0.102 0.216 0.150 0.343
## .F_c30 0.081 0.027 0.031 0.136 0.081 0.120
## .S_br23 0.207 0.036 0.149 0.287 0.207 0.654
## .S_c30 0.094 0.034 0.018 0.162 0.094 0.134
## .CV_Gral 0.433 0.112 0.186 0.642 0.433 0.129
## .Salud 1.544 0.306 0.972 2.180 1.544 0.447
## .funcionalidad 0.007 0.010 0.000 0.037 0.023 0.023
## sintomas 0.109 0.042 0.041 0.203 1.000 1.000
## Rhat Prior
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.004 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.006 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]#COMPARACION MODREF Vs MOD1.0
blavCompare(fitref, fitedad1.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are too high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.
## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.927
## object2: 916.356
##
## WAIC difference & SE:
## -1.214 1.055
##
## LOO estimates:
## object1: 914.083
## object2: 917.082
##
## LOO difference & SE:
## -1.500 1.117
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 7.702#Gana el mod ref 7.185
#confimacion COMPARACION MODREF Vs MOD1.0
blavCompare(fitedad1.0, fitref)## Warning: Some Pareto k diagnostic values are too high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.
## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 916.356
## object2: 913.927
##
## WAIC difference & SE:
## -1.214 1.055
##
## LOO estimates:
## object1: 917.082
## object2: 914.083
##
## LOO difference & SE:
## -1.500 1.117
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): -7.702#Gana el mod ref -7.185
#Modelo 2.0 interaccion compañero permanente
model_bayesiano2.0 <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad + Con_compañero_permanente
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad
# residual correlations
'
fit2.0 <- bsem(
model = model_bayesiano2.0,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 22.275 seconds (Warm-up)
## Chain 1: 19.466 seconds (Sampling)
## Chain 1: 41.741 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0.001 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 44.229 seconds (Warm-up)
## Chain 2: 88.344 seconds (Sampling)
## Chain 2: 132.573 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0.001 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 40.689 seconds (Warm-up)
## Chain 3: 79.195 seconds (Sampling)
## Chain 3: 119.884 seconds (Total)
## Chain 3:## Warning: There were 2 divergent transitions after warmup. See
## https://mc-stan.org/misc/warnings.html#divergent-transitions-after-warmup
## to find out why this is a problem and how to eliminate them.## Warning: Examine the pairs() plot to diagnose sampling problems## Warning: The largest R-hat is 1.66, indicating chains have not mixed.
## Running the chains for more iterations may help. See
## https://mc-stan.org/misc/warnings.html#r-hat## Warning: Bulk Effective Samples Size (ESS) is too low, indicating posterior means and medians may be unreliable.
## Running the chains for more iterations may help. See
## https://mc-stan.org/misc/warnings.html#bulk-ess## Warning: Tail Effective Samples Size (ESS) is too low, indicating posterior variances and tail quantiles may be unreliable.
## Running the chains for more iterations may help. See
## https://mc-stan.org/misc/warnings.html#tail-ess## Warning: blavaan WARNING: at least one parameter has a psrf > 1.2.## Computing posterior predictives...## Warning: blavaan WARNING: Small effective sample sizes (< 100) for some
## parameters.summary(fit2.0,standardized = TRUE)## ** WARNING ** blavaan (0.4-1) did NOT converge after 500 adapt+burnin iterations
## ** WARNING ** Proceed with caution
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -661.617 0.158
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.932 0.922
## F_c30 1.458 0.164 1.183 1.817 1.359 0.980
## sintomas =~
## S_br23 1.000 0.268 0.468
## S_c30 -5.597 11.799 -30.173 3.510 -1.502 -0.981
## Rhat Prior
##
##
## 1.029 normal(0,15)
##
##
## 3.725 normal(0,15)## Warning in abbreviate(NAMES, minlength = (W - MAX.L), strict = TRUE):
## abreviatura utilizada con caracteres no ASCII##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) 3.452 7.526 -2.374 19.045 0.994 0.994
## CV_Gral ~
## Salud (c) 0.754 0.075 0.605 0.901 0.754 1.051
## sintomas (e) 0.236 7.863 -15.692 16.694 0.063 0.051
## funcionldd (d) 0.416 3.665 -7.840 8.942 0.387 0.310
## Cn_cmpñr_p -0.001 0.158 -0.319 0.307 -0.001 -0.000
## Salud ~
## sintomas -6.568 8.881 -24.461 9.787 -1.763 -1.011
## funcionldd (b) 0.589 4.688 -10.666 7.553 0.549 0.315
## Rhat Prior
##
## 3.684 normal(0,10)
##
## 1.001 normal(0,10)
## 1.017 normal(0,10)
## 1.003 normal(0,10)
## 1.000 normal(0,10)
##
## 1.018 normal(-10,10)
## 1.121 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.343 0.073 2.203 2.491 2.343 2.319
## .F_c30 2.439 0.089 2.268 2.612 2.439 1.759
## .S_br23 1.765 0.062 1.646 1.882 1.765 3.080
## .S_c30 2.162 0.091 1.986 2.335 2.162 1.412
## .CV_Gral 0.834 0.400 0.036 1.617 0.834 0.667
## .Salud 4.335 0.208 3.921 4.752 4.335 2.486
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 1.000 normal(0,32)
## 1.001 normal(0,32)
## 0.999 normal(0,32)
## 1.000 normal(0,32)
## 0.999 normal(0,10)
## 1.001 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.152 0.030 0.102 0.218 0.152 0.149
## .F_c30 0.076 0.027 0.026 0.133 0.076 0.040
## .S_br23 0.256 0.084 0.152 0.451 0.256 0.781
## .S_c30 0.087 0.038 0.006 0.161 0.087 0.037
## .CV_Gral 0.453 0.096 0.247 0.644 0.453 0.290
## .Salud 1.555 0.313 0.978 2.237 1.555 0.511
## .funcionalidad 0.010 0.013 0.000 0.047 0.011 0.011
## sintomas 0.072 0.060 0.001 0.189 1.000 1.000
## Rhat Prior
## 1.014 gamma(1,.5)[sd]
## 1.038 gamma(1,.5)[sd]
## 1.955 gamma(1,.5)[sd]
## 1.038 gamma(1,.5)[sd]
## 1.016 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.115 gamma(1,.5)[sd]
## 1.890 gamma(1,.5)[sd]#COMPARACION MODREF Vs MOD2.0
blavCompare(fitref, fit2.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.## Warning:
## 20 (25.0%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.927
## object2: 936.231
##
## WAIC difference & SE:
## -11.152 1.910
##
## LOO estimates:
## object1: 914.083
## object2: 935.829
##
## LOO difference & SE:
## -10.873 1.930
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 142.443#Gana MODREF
#COMPARACION MOD1.0 Vs MOD2.0
blavCompare(fitedad1.0, fit2.0)## Warning: Some Pareto k diagnostic values are too high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.## Warning:
## 20 (25.0%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 916.356
## object2: 936.231
##
## WAIC difference & SE:
## -9.937 2.144
##
## LOO estimates:
## object1: 917.082
## object2: 935.829
##
## LOO difference & SE:
## -9.373 2.181
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 134.741#Gana MOD2.0 -2.782
#MODELO COMPUESTO 1.0 + 2.0 (Edad + compañero permanente)
model_bayesiano1.0_2.0 <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad + Edad + Con_compañero_permanente
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad
# residual correlations
'
fit1.0_2.0 <- bsem(
model = model_bayesiano1.0_2.0,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 53.121 seconds (Warm-up)
## Chain 1: 62.527 seconds (Sampling)
## Chain 1: 115.648 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0.001 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 58.515 seconds (Warm-up)
## Chain 2: 83.624 seconds (Sampling)
## Chain 2: 142.139 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 55.425 seconds (Warm-up)
## Chain 3: 103.268 seconds (Sampling)
## Chain 3: 158.693 seconds (Total)
## Chain 3:## Warning: Tail Effective Samples Size (ESS) is too low, indicating posterior variances and tail quantiles may be unreliable.
## Running the chains for more iterations may help. See
## https://mc-stan.org/misc/warnings.html#tail-ess## Computing posterior predictives...summary(fit1.0_2.0,standardized = TRUE)## blavaan (0.4-1) results of 1000 samples after 500 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -531.206 0.050
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.536 0.810
## F_c30 1.442 0.157 1.173 1.800 0.772 0.939
## sintomas =~
## S_br23 1.000 0.330 0.587
## S_c30 2.357 0.467 1.647 3.429 0.779 0.933
## Rhat Prior
##
##
## 1.001 normal(0,15)
##
##
## 1.002 normal(0,15)## Warning in abbreviate(NAMES, minlength = (W - MAX.L), strict = TRUE):
## abreviatura utilizada con caracteres no ASCII##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) -1.599 0.340 -2.427 -1.071 -0.986 -0.986
## CV_Gral ~
## Salud (c) 0.741 0.084 0.575 0.906 0.741 0.752
## sintomas (e) -1.125 6.622 -14.628 12.822 -0.372 -0.204
## funcionldd (d) 0.069 4.178 -8.828 9.195 0.037 0.020
## Edad -0.005 0.007 -0.018 0.009 -0.005 -0.033
## Cn_cmpñr_p -0.011 0.161 -0.332 0.308 -0.011 -0.003
## Salud ~
## sintomas -5.107 8.092 -21.858 8.931 -1.687 -0.913
## funcionldd (b) -0.599 5.170 -11.708 8.516 -0.321 -0.174
## Rhat Prior
##
## 1.002 normal(0,10)
##
## 1.000 normal(0,10)
## 1.000 normal(0,10)
## 1.000 normal(0,10)
## 1.001 normal(0,10)
## 1.000 normal(0,10)
##
## 1.003 normal(-10,10)
## 1.003 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.341 0.073 2.196 2.482 2.341 3.541
## .F_c30 2.436 0.089 2.263 2.607 2.436 2.963
## .S_br23 1.767 0.063 1.647 1.895 1.767 3.141
## .S_c30 2.167 0.091 1.986 2.339 2.167 2.595
## .CV_Gral 1.166 0.640 -0.046 2.497 1.166 0.639
## .Salud 4.332 0.205 3.935 4.732 4.332 2.343
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 1.000 normal(0,32)
## 1.000 normal(0,32)
## 1.000 normal(0,32)
## 1.000 normal(0,32)
## 1.000 normal(0,10)
## 1.000 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.150 0.028 0.102 0.213 0.150 0.343
## .F_c30 0.079 0.029 0.022 0.141 0.079 0.117
## .S_br23 0.207 0.036 0.148 0.290 0.207 0.655
## .S_c30 0.091 0.035 0.006 0.156 0.091 0.130
## .CV_Gral 0.447 0.100 0.231 0.655 0.447 0.134
## .Salud 1.537 0.305 0.976 2.175 1.537 0.450
## .funcionalidad 0.008 0.012 0.000 0.046 0.028 0.028
## sintomas 0.109 0.042 0.044 0.205 1.000 1.000
## Rhat Prior
## 1.001 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.012 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.007 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]#COMPARACION MODREF Vs MODCOMPUESTO 1.0 + 2.0
blavCompare(fitref, fit1.0_2.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are too high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.
## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.927
## object2: 917.917
##
## WAIC difference & SE:
## -1.995 1.072
##
## LOO estimates:
## object1: 914.083
## object2: 918.339
##
## LOO difference & SE:
## -2.128 1.102
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 12.032#Gana MODREF 11.216
#COMPATACION MODCOMPUESTO VS MOD1.0
blavCompare(fit1.0_2.0, fitedad1.0)## Warning: Some Pareto k diagnostic values are too high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are too high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.
## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 917.917
## object2: 916.356
##
## WAIC difference & SE:
## -0.781 0.272
##
## LOO estimates:
## object1: 918.339
## object2: 917.082
##
## LOO difference & SE:
## -0.629 0.382
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): -4.330#Gana MOD1.0 -4.378
#COMPATACION MODCOMPUESTO VS MOD2.0
blavCompare(fit1.0_2.0, fit2.0)## Warning: Some Pareto k diagnostic values are too high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.## Warning:
## 20 (25.0%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 917.917
## object2: 936.231
##
## WAIC difference & SE:
## -9.157 2.140
##
## LOO estimates:
## object1: 918.339
## object2: 935.829
##
## LOO difference & SE:
## -8.745 2.177
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 130.411#Gana MOD2.0 -7.160 #Modelo 3.0 interaccion + estrato
model_bayesiano3.0 <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas + Estrato
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad
# residual correlations
'
fit3.0 <- bsem(
model = model_bayesiano3.0,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 22.113 seconds (Warm-up)
## Chain 1: 44.058 seconds (Sampling)
## Chain 1: 66.171 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 27.731 seconds (Warm-up)
## Chain 2: 45.567 seconds (Sampling)
## Chain 2: 73.298 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 24.879 seconds (Warm-up)
## Chain 3: 45.489 seconds (Sampling)
## Chain 3: 70.368 seconds (Total)
## Chain 3:
## Computing posterior predictives...summary(fit3.0,standardized = TRUE)## blavaan (0.4-1) results of 1000 samples after 500 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -524.179 0.294
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.545 0.815
## F_c30 1.432 0.151 1.170 1.761 0.781 0.943
## sintomas =~
## S_br23 1.000 0.326 0.582
## S_c30 2.421 0.534 1.717 3.768 0.790 0.937
## Rhat Prior
##
##
## 1.000 normal(0,15)
##
##
## 1.003 normal(0,15)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) -1.639 0.382 -2.582 -1.106 -0.981 -0.981
## Estrato 0.082 0.061 -0.019 0.210 0.151 0.075
## CV_Gral ~
## Salud (c) 0.757 0.070 0.617 0.894 0.757 0.767
## sintomas (e) -1.446 4.001 -10.507 7.513 -0.472 -0.254
## funcionldd (d) -0.159 2.433 -5.409 5.069 -0.087 -0.047
## Salud ~
## sintomas -3.390 5.438 -16.612 6.421 -1.106 -0.587
## funcionldd (b) 0.542 3.378 -7.774 6.714 0.295 0.157
## Rhat Prior
##
## 1.001 normal(0,10)
## 1.002 normal(0,10)
##
## 1.000 normal(0,10)
## 1.002 normal(0,10)
## 1.002 normal(0,10)
##
## 1.005 normal(-10,10)
## 1.006 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.226 0.113 1.995 2.427 2.226 3.329
## .F_c30 2.272 0.150 1.958 2.547 2.272 2.743
## .S_br23 1.763 0.063 1.637 1.886 1.763 3.147
## .S_c30 2.162 0.090 1.982 2.336 2.162 2.566
## .CV_Gral 0.848 0.358 0.157 1.588 0.848 0.456
## .Salud 4.224 0.389 3.372 4.961 4.224 2.242
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 1.001 normal(0,32)
## 1.001 normal(0,32)
## 1.001 normal(0,32)
## 1.001 normal(0,32)
## 1.000 normal(0,10)
## 1.002 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.150 0.029 0.103 0.215 0.150 0.335
## .F_c30 0.077 0.026 0.028 0.132 0.077 0.112
## .S_br23 0.207 0.036 0.148 0.289 0.207 0.661
## .S_c30 0.086 0.033 0.013 0.151 0.086 0.121
## .CV_Gral 0.458 0.085 0.309 0.638 0.458 0.133
## .Salud 1.599 0.301 1.082 2.265 1.599 0.451
## .funcionalidad 0.010 0.013 0.000 0.047 0.033 0.033
## sintomas 0.106 0.042 0.038 0.198 1.000 1.000
## Rhat Prior
## 0.999 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.003 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.004 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]#COMPARACION MODREF Vs MOD3.0
blavCompare(fitref, fit3.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are too high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.## Warning:
## 15 (18.8%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.927
## object2: 913.483
##
## WAIC difference & SE:
## -0.222 1.370
##
## LOO estimates:
## object1: 914.083
## object2: 913.8
##
## LOO difference & SE:
## -0.142 1.375
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 5.005#Gana MODREF 4.229
#Modelo 4.0 interaccion nivel educativo
model_bayesiano4.0 <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad + Nivel_educativo
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad
# residual correlations
'
fit4.0 <- bsem(
model = model_bayesiano4.0,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0.001 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 34.811 seconds (Warm-up)
## Chain 1: 47.36 seconds (Sampling)
## Chain 1: 82.171 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 41.449 seconds (Warm-up)
## Chain 2: 68.258 seconds (Sampling)
## Chain 2: 109.707 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0.001 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 38.219 seconds (Warm-up)
## Chain 3: 81.969 seconds (Sampling)
## Chain 3: 120.188 seconds (Total)
## Chain 3:## Warning: Tail Effective Samples Size (ESS) is too low, indicating posterior variances and tail quantiles may be unreliable.
## Running the chains for more iterations may help. See
## https://mc-stan.org/misc/warnings.html#tail-ess## Computing posterior predictives...summary(fit4.0,standardized = TRUE)## blavaan (0.4-1) results of 1000 samples after 500 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -523.796 0.079
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.538 0.811
## F_c30 1.432 0.158 1.155 1.786 0.771 0.938
## sintomas =~
## S_br23 1.000 0.331 0.588
## S_c30 2.354 0.504 1.665 3.449 0.778 0.931
## Rhat Prior
##
##
## 0.999 normal(0,15)
##
##
## 1.003 normal(0,15)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) -1.608 0.345 -2.379 -1.097 -0.988 -0.988
## CV_Gral ~
## Salud (c) 0.746 0.083 0.568 0.900 0.746 0.744
## sintomas (e) -1.068 7.286 -16.054 14.213 -0.353 -0.191
## funcionldd (d) 0.162 4.649 -9.703 10.068 0.087 0.047
## Nivel_dctv 0.115 0.174 -0.223 0.443 0.115 0.030
## Salud ~
## sintomas -5.638 8.340 -22.695 9.547 -1.864 -1.011
## funcionldd (b) -0.942 5.317 -12.104 8.678 -0.507 -0.275
## Rhat Prior
##
## 1.001 normal(0,10)
##
## 1.000 normal(0,10)
## 1.004 normal(0,10)
## 1.005 normal(0,10)
## 1.000 normal(0,10)
##
## 1.002 normal(-10,10)
## 1.002 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.342 0.071 2.200 2.480 2.342 3.530
## .F_c30 2.436 0.084 2.270 2.599 2.436 2.966
## .S_br23 1.765 0.063 1.645 1.894 1.765 3.139
## .S_c30 2.165 0.085 1.998 2.333 2.165 2.591
## .CV_Gral 0.708 0.449 -0.113 1.642 0.708 0.383
## .Salud 4.336 0.202 3.946 4.744 4.336 2.351
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 0.999 normal(0,32)
## 1.000 normal(0,32)
## 0.999 normal(0,32)
## 1.000 normal(0,32)
## 1.000 normal(0,10)
## 1.000 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.151 0.028 0.104 0.213 0.151 0.342
## .F_c30 0.081 0.028 0.031 0.140 0.081 0.120
## .S_br23 0.207 0.037 0.148 0.291 0.207 0.654
## .S_c30 0.093 0.034 0.018 0.160 0.093 0.133
## .CV_Gral 0.440 0.097 0.239 0.626 0.440 0.129
## .Salud 1.538 0.321 0.937 2.213 1.538 0.452
## .funcionalidad 0.007 0.011 0.000 0.040 0.023 0.023
## sintomas 0.109 0.042 0.043 0.202 1.000 1.000
## Rhat Prior
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 0.999 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.006 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]#COMPARACION MODREF Vs MOD3.0
blavCompare(fitref, fit4.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.## Warning:
## 15 (18.8%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.927
## object2: 915.128
##
## WAIC difference & SE:
## -0.600 0.733
##
## LOO estimates:
## object1: 914.083
## object2: 915.333
##
## LOO difference & SE:
## -0.625 0.738
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 4.622#Gana MODREF 4.092
#COMPARACION MOD3.0 Vs MOD4.0
blavCompare(fit3.0, fit4.0)## Warning: Some Pareto k diagnostic values are too high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 15 (18.8%) p_waic estimates greater than 0.4. We recommend trying loo instead.
## Warning:
## 15 (18.8%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.483
## object2: 915.128
##
## WAIC difference & SE:
## -0.822 1.564
##
## LOO estimates:
## object1: 913.8
## object2: 915.333
##
## LOO difference & SE:
## -0.767 1.565
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): -0.383#Gana MOD4.0 -0.137 #GANADOR A MOD REF
#MODELO COMPUESTO 3.0 + 4.0 (Estrato + nivel educativo)
model_bayesiano3.0_4.0 <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas + Estrato
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad + Nivel_educativo
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad
# residual correlations
'
fit3.0_4.0 <- bsem(
model = model_bayesiano3.0_4.0,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 34.49 seconds (Warm-up)
## Chain 1: 42.387 seconds (Sampling)
## Chain 1: 76.877 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 34.316 seconds (Warm-up)
## Chain 2: 72.863 seconds (Sampling)
## Chain 2: 107.179 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0.001 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 31.713 seconds (Warm-up)
## Chain 3: 45.783 seconds (Sampling)
## Chain 3: 77.496 seconds (Total)
## Chain 3:
## Computing posterior predictives...summary(fit3.0_4.0,standardized = TRUE)## blavaan (0.4-1) results of 1000 samples after 500 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -527.810 0.129
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.546 0.816
## F_c30 1.431 0.149 1.171 1.761 0.781 0.943
## sintomas =~
## S_br23 1.000 0.323 0.579
## S_c30 2.443 0.562 1.708 3.876 0.789 0.937
## Rhat Prior
##
##
## 1.002 normal(0,15)
##
##
## 1.006 normal(0,15)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) -1.658 0.407 -2.674 -1.103 -0.981 -0.981
## Estrato 0.088 0.060 -0.019 0.214 0.161 0.080
## CV_Gral ~
## Salud (c) 0.757 0.070 0.619 0.891 0.757 0.759
## sintomas (e) -2.194 3.947 -11.707 5.917 -0.708 -0.375
## funcionldd (d) -0.555 2.396 -5.946 4.402 -0.303 -0.161
## Nivel_dctv 0.147 0.186 -0.215 0.508 0.147 0.037
## Salud ~
## sintomas -3.394 5.260 -15.586 5.610 -1.095 -0.578
## funcionldd (b) 0.587 3.200 -6.712 6.343 0.321 0.169
## Rhat Prior
##
## 1.004 normal(0,10)
## 1.004 normal(0,10)
##
## 1.002 normal(0,10)
## 1.004 normal(0,10)
## 1.003 normal(0,10)
## 1.000 normal(0,10)
##
## 1.004 normal(-10,10)
## 1.004 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.216 0.110 1.995 2.427 2.216 3.314
## .F_c30 2.260 0.148 1.956 2.533 2.260 2.729
## .S_br23 1.764 0.061 1.646 1.883 1.764 3.163
## .S_c30 2.164 0.088 1.995 2.335 2.164 2.570
## .CV_Gral 0.691 0.416 -0.138 1.545 0.691 0.366
## .Salud 4.215 0.395 3.388 4.977 4.215 2.224
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 1.004 normal(0,32)
## 1.003 normal(0,32)
## 0.999 normal(0,32)
## 1.000 normal(0,32)
## 1.001 normal(0,10)
## 1.003 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.149 0.029 0.101 0.214 0.149 0.334
## .F_c30 0.076 0.028 0.022 0.132 0.076 0.110
## .S_br23 0.207 0.036 0.146 0.291 0.207 0.665
## .S_c30 0.087 0.036 0.007 0.154 0.087 0.123
## .CV_Gral 0.461 0.087 0.304 0.647 0.461 0.129
## .Salud 1.599 0.294 1.095 2.256 1.599 0.445
## .funcionalidad 0.009 0.013 0.000 0.048 0.032 0.032
## sintomas 0.104 0.041 0.035 0.196 1.000 1.000
## Rhat Prior
## 1.003 gamma(1,.5)[sd]
## 1.004 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.003 gamma(1,.5)[sd]
## 1.004 gamma(1,.5)[sd]#COMPARACION MODREF Vs MODCOMPUESTO 3.0 + 4.0
blavCompare(fitref, fit3.0_4.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.## Warning:
## 15 (18.8%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.927
## object2: 914.226
##
## WAIC difference & SE:
## -0.150 1.697
##
## LOO estimates:
## object1: 914.083
## object2: 914.475
##
## LOO difference & SE:
## -0.196 1.694
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 8.636#Gana MODREF #MODELO 5.0 Situracion laboral
model_bayesiano5.0 <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas + Situacion_laboral
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad
# residual correlations
'
fit5.0 <- bsem(
model = model_bayesiano5.0,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 36.747 seconds (Warm-up)
## Chain 1: 60.525 seconds (Sampling)
## Chain 1: 97.272 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 38.904 seconds (Warm-up)
## Chain 2: 63.617 seconds (Sampling)
## Chain 2: 102.521 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 39.444 seconds (Warm-up)
## Chain 3: 59.411 seconds (Sampling)
## Chain 3: 98.855 seconds (Total)
## Chain 3:
## Computing posterior predictives...summary(fit5.0,standardized = TRUE)## blavaan (0.4-1) results of 1000 samples after 500 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -524.753 0.194
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.538 0.813
## F_c30 1.423 0.152 1.162 1.760 0.766 0.936
## sintomas =~
## S_br23 1.000 0.333 0.591
## S_c30 2.336 0.484 1.666 3.489 0.777 0.931
## Rhat Prior
##
##
## 1.000 normal(0,15)
##
##
## 1.006 normal(0,15)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) -1.597 0.347 -2.428 -1.089 -0.987 -0.987
## Sitcn_lbrl -0.019 0.050 -0.124 0.080 -0.036 -0.018
## CV_Gral ~
## Salud (c) 0.765 0.079 0.609 0.919 0.765 0.774
## sintomas (e) 0.736 6.023 -12.074 13.353 0.245 0.132
## funcionldd (d) 1.159 3.813 -6.770 9.183 0.624 0.338
## Salud ~
## sintomas -4.873 7.308 -20.324 8.656 -1.621 -0.867
## funcionldd (b) -0.428 4.601 -10.492 8.101 -0.230 -0.123
## Rhat Prior
##
## 1.004 normal(0,10)
## 1.005 normal(0,10)
##
## 1.000 normal(0,10)
## 1.002 normal(0,10)
## 1.003 normal(0,10)
##
## 1.000 normal(-10,10)
## 1.001 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.374 0.107 2.169 2.584 2.374 3.587
## .F_c30 2.481 0.141 2.205 2.751 2.481 3.031
## .S_br23 1.765 0.064 1.642 1.887 1.765 3.136
## .S_c30 2.163 0.090 1.984 2.342 2.163 2.592
## .CV_Gral 0.908 0.386 0.189 1.683 0.908 0.491
## .Salud 4.252 0.355 3.456 4.940 4.252 2.275
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 1.004 normal(0,32)
## 1.003 normal(0,32)
## 1.002 normal(0,32)
## 1.001 normal(0,32)
## 1.001 normal(0,10)
## 1.000 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.148 0.029 0.100 0.215 0.148 0.339
## .F_c30 0.083 0.027 0.033 0.139 0.083 0.123
## .S_br23 0.206 0.037 0.144 0.291 0.206 0.651
## .S_c30 0.092 0.035 0.020 0.161 0.092 0.133
## .CV_Gral 0.440 0.099 0.225 0.627 0.440 0.129
## .Salud 1.552 0.327 0.936 2.244 1.552 0.444
## .funcionalidad 0.008 0.011 0.000 0.042 0.026 0.026
## sintomas 0.111 0.042 0.043 0.205 1.000 1.000
## Rhat Prior
## 1.000 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.003 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.005 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.003 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]#COMPARACION MODREF Vs MOD5.0
blavCompare(fitref, fit5.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.
## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.## Warning:
## 15 (18.8%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.927
## object2: 915.641
##
## WAIC difference & SE:
## -0.857 0.681
##
## LOO estimates:
## object1: 914.083
## object2: 916.026
##
## LOO difference & SE:
## -0.972 0.713
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 5.579#Gana MOD5.0 5.366 #### GANADOR A MOD REF
#MODELO 6.0 Regimen de salud
model_bayesiano6.0 <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad +Regimen_salud
# residual correlations
'
fit6.0 <- bsem(
model = model_bayesiano6.0,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 40.988 seconds (Warm-up)
## Chain 1: 74.163 seconds (Sampling)
## Chain 1: 115.151 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 47.772 seconds (Warm-up)
## Chain 2: 90.093 seconds (Sampling)
## Chain 2: 137.865 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 46.061 seconds (Warm-up)
## Chain 3: 94.596 seconds (Sampling)
## Chain 3: 140.657 seconds (Total)
## Chain 3:## Warning: Tail Effective Samples Size (ESS) is too low, indicating posterior variances and tail quantiles may be unreliable.
## Running the chains for more iterations may help. See
## https://mc-stan.org/misc/warnings.html#tail-ess## Computing posterior predictives...summary(fit6.0,standardized = TRUE)## blavaan (0.4-1) results of 1000 samples after 500 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -522.831 0.123
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.536 0.810
## F_c30 1.437 0.152 1.177 1.763 0.770 0.939
## sintomas =~
## S_br23 1.000 0.330 0.587
## S_c30 2.354 0.477 1.673 3.503 0.778 0.931
## Rhat Prior
##
##
## 0.999 normal(0,15)
##
##
## 1.000 normal(0,15)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) -1.602 0.339 -2.375 -1.103 -0.988 -0.988
## CV_Gral ~
## Salud (c) 0.763 0.091 0.601 0.939 0.763 0.778
## sintomas (e) -0.393 6.938 -14.810 14.189 -0.130 -0.070
## funcionldd (d) 0.440 4.384 -8.943 9.354 0.236 0.128
## Salud ~
## sintomas -5.258 8.354 -22.794 10.060 -1.738 -0.924
## funcionldd (b) -0.620 5.336 -11.814 9.545 -0.332 -0.177
## Regimn_sld 0.283 0.316 -0.354 0.915 0.283 0.072
## Rhat Prior
##
## 1.000 normal(0,10)
##
## 1.006 normal(0,10)
## 1.004 normal(0,10)
## 1.004 normal(0,10)
##
## 1.002 normal(-10,10)
## 1.002 normal(0,10)
## 0.999 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.342 0.074 2.197 2.486 2.342 3.540
## .F_c30 2.439 0.090 2.257 2.620 2.439 2.973
## .S_br23 1.764 0.064 1.641 1.894 1.764 3.135
## .S_c30 2.163 0.093 1.973 2.346 2.163 2.589
## .CV_Gral 0.792 0.405 0.039 1.542 0.792 0.430
## .Salud 3.878 0.560 2.747 4.947 3.878 2.062
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 1.001 normal(0,32)
## 1.000 normal(0,32)
## 1.000 normal(0,32)
## 1.000 normal(0,32)
## 1.006 normal(0,10)
## 1.000 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.151 0.029 0.104 0.215 0.151 0.344
## .F_c30 0.079 0.026 0.033 0.135 0.079 0.118
## .S_br23 0.208 0.037 0.145 0.290 0.208 0.655
## .S_c30 0.092 0.035 0.014 0.163 0.092 0.133
## .CV_Gral 0.435 0.100 0.211 0.627 0.435 0.128
## .Salud 1.530 0.330 0.843 2.195 1.530 0.432
## .funcionalidad 0.007 0.011 0.000 0.039 0.025 0.025
## sintomas 0.109 0.042 0.043 0.204 1.000 1.000
## Rhat Prior
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.006 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.010 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]#COMPARACION MODREF Vs MOD6.0
blavCompare(fitref, fit6.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.## Warning:
## 15 (18.8%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.927
## object2: 915.09
##
## WAIC difference & SE:
## -0.581 0.948
##
## LOO estimates:
## object1: 914.083
## object2: 915.447
##
## LOO difference & SE:
## -0.682 0.962
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 3.657#Gana MODREF 3.451 ####
#COMPARACION MOD5.0 VS MOD6.0
blavCompare(fit5.0, fit6.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 15 (18.8%) p_waic estimates greater than 0.4. We recommend trying loo instead.
## Warning:
## 15 (18.8%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 915.641
## object2: 915.09
##
## WAIC difference & SE:
## -0.275 1.156
##
## LOO estimates:
## object1: 916.026
## object2: 915.447
##
## LOO difference & SE:
## -0.289 1.153
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): -1.921#Gana MOD6.0 -1.916 ####
#MODELO COMPUESTO 5.0 + 6.0 (Situracion laboral + Regimen de salud)
model_bayesiano5.0_6.0 <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas + Situacion_laboral
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad + Regimen_salud
# residual correlations
'
fit5.0_6.0 <- bsem(
model = model_bayesiano5.0_6.0,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0.001 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 50.725 seconds (Warm-up)
## Chain 1: 78.489 seconds (Sampling)
## Chain 1: 129.214 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 40.133 seconds (Warm-up)
## Chain 2: 59.135 seconds (Sampling)
## Chain 2: 99.268 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 41.795 seconds (Warm-up)
## Chain 3: 107.303 seconds (Sampling)
## Chain 3: 149.098 seconds (Total)
## Chain 3:
## Computing posterior predictives...summary(fit5.0_6.0,standardized = TRUE)## blavaan (0.4-1) results of 1000 samples after 500 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -527.929 0.122
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.542 0.815
## F_c30 1.423 0.151 1.160 1.761 0.771 0.939
## sintomas =~
## S_br23 1.000 0.330 0.587
## S_c30 2.366 0.526 1.672 3.615 0.780 0.931
## Rhat Prior
##
##
## 1.000 normal(0,15)
##
##
## 1.007 normal(0,15)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) -1.622 0.376 -2.529 -1.091 -0.987 -0.987
## Sitcn_lbrl -0.018 0.053 -0.127 0.092 -0.034 -0.017
## CV_Gral ~
## Salud (c) 0.767 0.083 0.609 0.935 0.767 0.775
## sintomas (e) 0.380 6.069 -12.551 12.617 0.125 0.067
## funcionldd (d) 0.943 3.777 -7.217 8.695 0.511 0.272
## Salud ~
## sintomas -5.094 7.417 -20.897 8.984 -1.680 -0.887
## funcionldd (b) -0.490 4.667 -10.517 8.569 -0.265 -0.140
## Regimn_sld 0.300 0.317 -0.318 0.898 0.300 0.076
## Rhat Prior
##
## 1.005 normal(0,10)
## 1.003 normal(0,10)
##
## 1.001 normal(0,10)
## 1.004 normal(0,10)
## 1.004 normal(0,10)
##
## 1.001 normal(-10,10)
## 1.001 normal(0,10)
## 1.001 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.369 0.111 2.143 2.583 2.369 3.562
## .F_c30 2.475 0.148 2.168 2.759 2.475 3.013
## .S_br23 1.766 0.063 1.639 1.886 1.766 3.146
## .S_c30 2.166 0.089 1.987 2.341 2.166 2.583
## .CV_Gral 0.898 0.394 0.120 1.673 0.898 0.479
## .Salud 3.747 0.647 2.439 5.030 3.747 1.979
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 1.002 normal(0,32)
## 1.002 normal(0,32)
## 0.999 normal(0,32)
## 1.000 normal(0,32)
## 1.002 normal(0,10)
## 1.002 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.149 0.028 0.101 0.209 0.149 0.336
## .F_c30 0.080 0.027 0.030 0.137 0.080 0.119
## .S_br23 0.206 0.036 0.147 0.287 0.206 0.655
## .S_c30 0.094 0.034 0.018 0.162 0.094 0.134
## .CV_Gral 0.438 0.103 0.218 0.641 0.438 0.125
## .Salud 1.551 0.316 0.974 2.239 1.551 0.433
## .funcionalidad 0.008 0.011 0.000 0.042 0.026 0.026
## sintomas 0.109 0.042 0.040 0.205 1.000 1.000
## Rhat Prior
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.003 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.004 gamma(1,.5)[sd]
## 1.004 gamma(1,.5)[sd]#COMPARACION MODREF Vs MODCOMPUESTO 5.0 + 6.0
blavCompare(fitref, fit5.0_6.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.## Warning:
## 16 (20.0%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.927
## object2: 917.345
##
## WAIC difference & SE:
## -1.709 1.198
##
## LOO estimates:
## object1: 914.083
## object2: 917.494
##
## LOO difference & SE:
## -1.705 1.197
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 8.755#Gana #MODELO 7.0 Comorbilidad
model_bayesiano7.0 <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas + Comorbilidad
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad
# residual correlations
'
fit7.0 <- bsem(
model = model_bayesiano7.0,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 28.307 seconds (Warm-up)
## Chain 1: 74.787 seconds (Sampling)
## Chain 1: 103.094 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0.001 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 42.101 seconds (Warm-up)
## Chain 2: 81.058 seconds (Sampling)
## Chain 2: 123.159 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 38.138 seconds (Warm-up)
## Chain 3: 80.093 seconds (Sampling)
## Chain 3: 118.231 seconds (Total)
## Chain 3:## Warning: There were 2 divergent transitions after warmup. See
## https://mc-stan.org/misc/warnings.html#divergent-transitions-after-warmup
## to find out why this is a problem and how to eliminate them.## Warning: There were 3 transitions after warmup that exceeded the maximum treedepth. Increase max_treedepth above 10. See
## https://mc-stan.org/misc/warnings.html#maximum-treedepth-exceeded## Warning: Examine the pairs() plot to diagnose sampling problems## Warning: Bulk Effective Samples Size (ESS) is too low, indicating posterior means and medians may be unreliable.
## Running the chains for more iterations may help. See
## https://mc-stan.org/misc/warnings.html#bulk-ess## Warning: Tail Effective Samples Size (ESS) is too low, indicating posterior variances and tail quantiles may be unreliable.
## Running the chains for more iterations may help. See
## https://mc-stan.org/misc/warnings.html#tail-ess## Computing posterior predictives...## Warning: blavaan WARNING: Small effective sample sizes (< 100) for some
## parameters.summary(fit7.0,standardized = TRUE)## blavaan (0.4-1) results of 1000 samples after 500 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -560.082 0.156
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.541 0.813
## F_c30 1.407 0.146 1.148 1.712 0.761 0.931
## sintomas =~
## S_br23 1.000 0.340 0.600
## S_c30 2.286 0.437 1.638 3.360 0.776 0.930
## Rhat Prior
##
##
## 0.999 normal(0,15)
##
##
## 1.004 normal(0,15)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) -1.580 0.320 -2.351 -1.084 -0.991 -0.991
## Comorbildd 0.027 0.091 -0.127 0.180 0.049 0.023
## CV_Gral ~
## Salud (c) 0.676 0.135 0.340 0.860 0.676 0.687
## sintomas (e) -0.738 7.251 -15.716 11.533 -0.251 -0.139
## funcionldd (d) 0.519 4.628 -8.623 8.892 0.281 0.156
## Salud ~
## sintomas -2.996 11.556 -24.548 14.344 -1.017 -0.555
## funcionldd (b) 0.755 7.465 -13.323 12.007 0.408 0.223
## Rhat Prior
##
## 1.000 normal(0,10)
## 1.046 normal(0,10)
##
## 1.010 normal(0,10)
## 1.039 normal(0,10)
## 1.037 normal(0,10)
##
## 1.039 normal(-10,10)
## 1.035 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.299 0.167 2.003 2.601 2.299 3.456
## .F_c30 2.374 0.228 1.972 2.784 2.374 2.902
## .S_br23 1.765 0.063 1.643 1.887 1.765 3.120
## .S_c30 2.163 0.088 1.987 2.330 2.163 2.591
## .CV_Gral 0.706 0.463 -0.069 1.706 0.706 0.392
## .Salud 3.437 0.592 2.195 4.499 3.437 1.876
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 1.037 normal(0,32)
## 1.038 normal(0,32)
## 1.002 normal(0,32)
## 1.000 normal(0,32)
## 1.008 normal(0,10)
## 1.010 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.150 0.030 0.101 0.217 0.150 0.338
## .F_c30 0.090 0.026 0.044 0.145 0.090 0.134
## .S_br23 0.205 0.037 0.146 0.290 0.205 0.640
## .S_c30 0.094 0.036 0.006 0.164 0.094 0.135
## .CV_Gral 0.412 0.106 0.163 0.605 0.412 0.127
## .Salud 1.332 0.356 0.533 2.002 1.332 0.397
## .funcionalidad 0.005 0.007 0.000 0.025 0.017 0.017
## sintomas 0.115 0.043 0.046 0.213 1.000 1.000
## Rhat Prior
## 1.004 gamma(1,.5)[sd]
## 1.004 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.030 gamma(1,.5)[sd]
## 1.003 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.017 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]#COMPARACION MODREF Vs MOD7.0
blavCompare(fitref, fit7.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.## Warning:
## 17 (21.2%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.927
## object2: 911.13
##
## WAIC difference & SE:
## -1.399 2.247
##
## LOO estimates:
## object1: 914.083
## object2: 911.281
##
## LOO difference & SE:
## -1.401 2.256
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 40.908#Gana
#MODELO 8.0 Estado_del_tumor
model_bayesiano8.0 <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad + Estado_del_tumor
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad
# residual correlations
'
fit8.0 <- bsem(
model = model_bayesiano8.0,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0.001 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 39.266 seconds (Warm-up)
## Chain 1: 62.839 seconds (Sampling)
## Chain 1: 102.105 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 40.059 seconds (Warm-up)
## Chain 2: 98.515 seconds (Sampling)
## Chain 2: 138.574 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 45.273 seconds (Warm-up)
## Chain 3: 83.996 seconds (Sampling)
## Chain 3: 129.269 seconds (Total)
## Chain 3:## Warning: There were 1 transitions after warmup that exceeded the maximum treedepth. Increase max_treedepth above 10. See
## https://mc-stan.org/misc/warnings.html#maximum-treedepth-exceeded## Warning: Examine the pairs() plot to diagnose sampling problems## Computing posterior predictives...summary(fit8.0,standardized = TRUE)## blavaan (0.4-1) results of 1000 samples after 500 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -523.484 0.140
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.535 0.809
## F_c30 1.443 0.164 1.161 1.822 0.772 0.939
## sintomas =~
## S_br23 1.000 0.329 0.586
## S_c30 2.364 0.483 1.692 3.502 0.779 0.931
## Rhat Prior
##
##
## 1.000 normal(0,15)
##
##
## 1.001 normal(0,15)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) -1.605 0.344 -2.390 -1.093 -0.988 -0.988
## CV_Gral ~
## Salud (c) 0.754 0.080 0.596 0.911 0.754 0.757
## sintomas (e) -0.820 7.027 -15.022 13.483 -0.270 -0.146
## funcionldd (d) 0.264 4.402 -8.566 9.549 0.141 0.076
## Estd_dl_tm -0.160 0.167 -0.496 0.163 -0.160 -0.041
## Salud ~
## sintomas -5.204 8.234 -22.638 10.553 -1.714 -0.919
## funcionldd (b) -0.614 5.272 -11.517 9.675 -0.328 -0.176
## Rhat Prior
##
## 1.002 normal(0,10)
##
## 1.000 normal(0,10)
## 1.000 normal(0,10)
## 1.000 normal(0,10)
## 1.000 normal(0,10)
##
## 1.009 normal(-10,10)
## 1.008 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.343 0.072 2.202 2.483 2.343 3.542
## .F_c30 2.438 0.088 2.265 2.610 2.438 2.964
## .S_br23 1.763 0.064 1.638 1.883 1.763 3.138
## .S_c30 2.163 0.092 1.979 2.342 2.163 2.586
## .CV_Gral 1.044 0.422 0.226 1.896 1.044 0.563
## .Salud 4.339 0.207 3.945 4.748 4.339 2.327
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 1.003 normal(0,32)
## 1.003 normal(0,32)
## 1.001 normal(0,32)
## 1.004 normal(0,32)
## 1.000 normal(0,10)
## 1.003 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.151 0.030 0.102 0.219 0.151 0.346
## .F_c30 0.081 0.028 0.027 0.140 0.081 0.119
## .S_br23 0.207 0.036 0.146 0.289 0.207 0.656
## .S_c30 0.093 0.034 0.020 0.158 0.093 0.133
## .CV_Gral 0.437 0.096 0.241 0.620 0.437 0.127
## .Salud 1.542 0.337 0.909 2.240 1.542 0.444
## .funcionalidad 0.007 0.011 0.000 0.040 0.023 0.023
## sintomas 0.108 0.041 0.043 0.202 1.000 1.000
## Rhat Prior
## 1.001 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.005 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.011 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]#COMPARACION MODREF Vs MOD8.0
blavCompare(fitref, fit8.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.
## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.927
## object2: 915.733
##
## WAIC difference & SE:
## -0.903 1.001
##
## LOO estimates:
## object1: 914.083
## object2: 916.152
##
## LOO difference & SE:
## -1.035 1.000
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 4.309#Gana
#MODELO COMPUESTO 7.0 + 8.0 (Comorbilidad + Estado del tumor)
model_bayesiano7.0_8.0 <- '
# measurement model
funcionalidad =~
prior("normal(0,15)")*F_br23 + prior("normal(0,15)")*F_c30
sintomas =~
prior("normal(0,15)")*S_br23 + prior("normal(0,15)")*S_c30
# regressions
funcionalidad ~ a*sintomas + Comorbilidad
CV_Gral ~ c*Salud + e*sintomas + d*prior("normal(0,15)")*funcionalidad + Estado_del_tumor
Salud ~ prior("normal(-10,10)")*sintomas + b*funcionalidad
# residual correlations
'
fit7.0_8.0 <- bsem(
model = model_bayesiano7.0_8.0,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE)##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0.001 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 1: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 1: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 1: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 1: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 1: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 1: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 1: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 41.225 seconds (Warm-up)
## Chain 1: 78.018 seconds (Sampling)
## Chain 1: 119.243 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0.001 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 2: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 2: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 2: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 2: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 2: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 2: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 2: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 46.377 seconds (Warm-up)
## Chain 2: 73.259 seconds (Sampling)
## Chain 2: 119.636 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 1500 [ 0%] (Warmup)
## Chain 3: Iteration: 150 / 1500 [ 10%] (Warmup)
## Chain 3: Iteration: 300 / 1500 [ 20%] (Warmup)
## Chain 3: Iteration: 450 / 1500 [ 30%] (Warmup)
## Chain 3: Iteration: 501 / 1500 [ 33%] (Sampling)
## Chain 3: Iteration: 650 / 1500 [ 43%] (Sampling)
## Chain 3: Iteration: 800 / 1500 [ 53%] (Sampling)
## Chain 3: Iteration: 950 / 1500 [ 63%] (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%] (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%] (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%] (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 44.732 seconds (Warm-up)
## Chain 3: 85.343 seconds (Sampling)
## Chain 3: 130.075 seconds (Total)
## Chain 3:## Warning: The largest R-hat is 1.06, indicating chains have not mixed.
## Running the chains for more iterations may help. See
## https://mc-stan.org/misc/warnings.html#r-hat## Warning: Bulk Effective Samples Size (ESS) is too low, indicating posterior means and medians may be unreliable.
## Running the chains for more iterations may help. See
## https://mc-stan.org/misc/warnings.html#bulk-ess## Computing posterior predictives...## Warning: blavaan WARNING: Small effective sample sizes (< 100) for some
## parameters.summary(fit7.0_8.0,standardized = TRUE)## blavaan (0.4-1) results of 1000 samples after 500 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -558.320 0.108
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## F_br23 1.000 0.542 0.814
## F_c30 1.409 0.157 1.145 1.755 0.763 0.931
## sintomas =~
## S_br23 1.000 0.341 0.603
## S_c30 2.265 0.429 1.629 3.318 0.773 0.930
## Rhat Prior
##
##
## 1.001 normal(0,15)
##
##
## 1.001 normal(0,15)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad ~
## sintomas (a) -1.574 0.321 -2.344 -1.080 -0.992 -0.992
## Comorbildd 0.038 0.089 -0.124 0.184 0.070 0.033
## CV_Gral ~
## Salud (c) 0.678 0.115 0.384 0.854 0.678 0.679
## sintomas (e) 0.392 6.892 -14.293 12.393 0.134 0.072
## funcionldd (d) 1.289 4.464 -7.662 9.680 0.698 0.378
## Estd_dl_tm -0.171 0.173 -0.509 0.174 -0.171 -0.044
## Salud ~
## sintomas -1.310 11.275 -24.413 14.875 -0.447 -0.242
## funcionldd (b) 1.842 7.307 -13.557 12.100 0.998 0.539
## Rhat Prior
##
## 1.002 normal(0,10)
## 1.072 normal(0,10)
##
## 1.001 normal(0,10)
## 1.038 normal(0,10)
## 1.038 normal(0,10)
## 1.000 normal(0,10)
##
## 1.069 normal(-10,10)
## 1.068 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 2.279 0.167 1.993 2.599 2.279 3.424
## .F_c30 2.347 0.225 1.972 2.771 2.347 2.861
## .S_br23 1.766 0.062 1.646 1.883 1.766 3.119
## .S_c30 2.164 0.088 1.988 2.333 2.164 2.602
## .CV_Gral 0.897 0.456 0.075 1.875 0.897 0.485
## .Salud 3.408 0.618 2.155 4.498 3.408 1.841
## .funcionalidad 0.000 0.000 0.000
## sintomas 0.000 0.000 0.000
## Rhat Prior
## 1.059 normal(0,32)
## 1.059 normal(0,32)
## 1.001 normal(0,32)
## 1.001 normal(0,32)
## 1.002 normal(0,10)
## 1.008 normal(0,10)
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .F_br23 0.150 0.029 0.102 0.214 0.150 0.338
## .F_c30 0.090 0.028 0.041 0.151 0.090 0.134
## .S_br23 0.204 0.035 0.147 0.284 0.204 0.637
## .S_c30 0.094 0.032 0.033 0.160 0.094 0.136
## .CV_Gral 0.411 0.107 0.155 0.607 0.411 0.120
## .Salud 1.344 0.340 0.547 1.998 1.344 0.393
## .funcionalidad 0.004 0.007 0.000 0.021 0.015 0.015
## sintomas 0.117 0.042 0.048 0.211 1.000 1.000
## Rhat Prior
## 1.005 gamma(1,.5)[sd]
## 1.003 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.008 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.007 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]#COMPARACION MODREF Vs MODCOMPUESTO 7.0 + 8.0
blavCompare(fitref, fit7.0_8.0)## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.## Warning:
## 14 (17.5%) p_waic estimates greater than 0.4. We recommend trying loo instead.## Warning:
## 17 (21.2%) p_waic estimates greater than 0.4. We recommend trying loo instead.##
## WAIC estimates:
## object1: 913.927
## object2: 912.246
##
## WAIC difference & SE:
## -0.841 2.724
##
## LOO estimates:
## object1: 914.083
## object2: 912.529
##
## LOO difference & SE:
## -0.777 2.738
##
## Laplace approximation to the log-Bayes factor
## (experimental; positive values favor object1): 39.146#Gana