SEM_BAYES_CMAMA
Mauricio Hernandez Carrillo
17/5/2022
Paquetes utilizados
Se hará uso de la base de datos recolectada la cual consta de 80 observaciones y 105 variables de mujeres con cáncer de mama en la ciudad de Cali, concretando algunos parámetros para las simulaciones y el MCMC para obtener la convergencia de los parámetros esperados. Donde se parametrizara el numero de muestras de calentamiento (BURNIN1), el número de iteraciones(SAMPLE1) y el numero de cadenas (NCHAINS1).
options(mc.cores = parallel::detectCores())
datos2 <- readRDS("data/datos2.RDS")
datos <- datos2
set.seed(535535)
BURNIN1 = 8000 #3000
SAMPLE1 = 16000 #6500
NCHAINS1 = 10 #6
BURNIN = 3000 # 2500
SAMPLE = 7000 # 6500
CHAINS = 6 # 6MODELOS PLANTEADOS
A partir del analisis de los modelos propuestos por Wilson & Cleary se tienen en cuenta para el planteamento de un modelo base y los modelos mas completos donde final se obtiene el modelo final.
Se establece después de las prueba de modelos frecuentistas y sus efectos indirectos, finalmente con la investigación en la literatura, el modelo bayesiano con sus variables latentes.
Modelo base: primer modelo planteado. Modelo base bio: modelo base mas la variable latente biologica. Modelo base bio ind: modelo base mas la variable latente biologica y sus respectivas variables moderadoras. model_base_bio_ind_econ: modelo base mas la variable latente biologica,con sus respectivas variables moderadoras y variable latente ecnomica. MODELO DE REFENCIA: modelo final planteado a partir de los resultados que se observaron. Modelo indic: Modelo final con efectos indirectos
model_base <- '
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
cv_gral ~ salud
salud ~ funcionalidad
funcionalidad ~ sintomas
# residual correlations
'
model_base_bio <- '
# 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
biologicas =~ her2_pos + edad + comorb + estadio_avz
# regressions
cv_gral ~ salud
salud ~ funcionalidad
funcionalidad ~ sintomas
sintomas ~ biologicas
# residual correlations
'
model_base_bio_ind <- '
# 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
biologicas =~ her2_pos + edad + comorb + estadio_avz
# regressions
cv_gral ~ salud + sintomas + funcionalidad
salud ~ funcionalidad
funcionalidad ~ sintomas
sintomas ~ biologicas
# residual correlations
'
model_base_bio_ind_econ <- '
# 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
biologicas =~ her2_pos + edad + comorb + estadio_avz
socioeconom =~ estr_bajo + rs_subsid + hasta_sec + trabaja
# regressions
cv_gral ~ salud + sintomas + funcionalidad + companero
salud ~ funcionalidad
funcionalidad ~ sintomas
sintomas ~ biologicas
# residual correlations
'
model_ref_bio_ind_sinedad <- '
# 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
biologicas =~ her2_pos + comorb + estadio_avz
# regressions
cv_gral ~ salud + sintomas + funcionalidad
salud ~ funcionalidad
funcionalidad ~ sintomas
sintomas ~ biologicas
# residual correlations
'
model_ref_bio_ind_sinedad_indi <- '
# 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
biologicas =~ her2_pos + comorb + estadio_avz
# regressions
cv_gral ~ d*salud + e*sintomas + c*funcionalidad
salud ~ funcionalidad
funcionalidad ~ b*sintomas
sintomas ~ a*biologicas
# indirect effect
ab:= a*b
abc:= a*b*c
abcd:=a*b*c*d
bc:= b*c
# total effect
indtot := ab + abc + abcd
tot := indtot + e
'Exploracion de funcion bsem
De el paquete Blavaan que ayuda a ejecutar la estimacion de los modelos bayesianos para ecuaciones de modelos estructurales, por medio Markov Chain Monte Carlo (MCMC) el cual es un metodo de simulacion para generar muestras de las distribuciones a posteriori y estimar cantidades de interes a posteriori.
#codigo para funcion sem
set.seed(535535)
fitbase <- bsem(
model = model_base,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE,
save.lvs = TRUE,
inits = "prior",
sample = BURNIN1,
burnin = SAMPLE1,
n.chains = NCHAINS1)## Computing posterior predictives...set.seed(535535)
fitbase_bio <- bsem(
model = model_base_bio,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE,
save.lvs = TRUE,
inits = "prior",
sample = BURNIN1,
burnin = SAMPLE1,
n.chains = NCHAINS1) #estable en el otro## Computing posterior predictives...set.seed(535535)
fitbase_bio_ind <- bsem(
model = model_base_bio_ind,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE,
save.lvs = TRUE,
inits = "prior",
sample = BURNIN1,
burnin = SAMPLE1,
n.chains = NCHAINS1)## Computing posterior predictives...#save(fitbase_bio_ind, file = "data/fitbase_bio_ind.Rdata") #Modelo que esta estable
#load("data/fitbase_bio_ind.Rdata")# para cargar
set.seed(535535)
fitbase_bio_ind_econ <- bsem(
model = model_base_bio_ind_econ,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE,
save.lvs = TRUE,
inits = "prior",
sample = BURNIN1,
burnin = SAMPLE1,
n.chains = NCHAINS1)## Computing posterior predictives...set.seed(535535)
fitref_bio_ind_sinedad <- bsem(
model = model_ref_bio_ind_sinedad,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE,
save.lvs = TRUE,
inits = "prior",
sample = BURNIN1,
burnin = SAMPLE1,
n.chains = NCHAINS1)## Computing posterior predictives...set.seed(535535)
fit_ref_bio_ind_sinedad_indi <- bsem(
model = model_ref_bio_ind_sinedad_indi,
data = datos,
auto.var = TRUE,
auto.fix.first = TRUE,
auto.cov.lv.x = TRUE,
save.lvs = TRUE,
inits = "prior",
sample = BURNIN1,
burnin = SAMPLE1,
n.chains = NCHAINS1)## Computing posterior predictives...El resumen del modelo el cual nos indica diferentes resultados de interes
summary(fitbase,standardized = TRUE, rsquare=TRUE)## ** WARNING ** blavaan (0.4-1) did NOT converge after 16000 adapt+burnin iterations
## ** WARNING ** Proceed with caution
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -1011.635 0.064
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## f_br23 1.000 0.169 0.393
## f_c30 1.478 0.163 1.201 1.840 0.250 0.709
## sintomas =~
## s_br23 1.000 0.322 0.565
## s_c30 -0.005 7.417 -25.352 3.435 -0.002 -0.007
## Rhat Prior
##
##
## 1.007 normal(0,15)
##
##
## 3.644 normal(0,15)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## cv_gral ~
## salud 0.899 0.046 0.809 0.988 0.899 0.857
## salud ~
## funcionalidad 2.612 0.392 1.909 3.446 0.442 0.328
## funcionalidad ~
## sintomas -0.008 4.599 -2.198 15.700 -0.015 -0.015
## Rhat Prior
##
## 1.000 normal(0,10)
##
## 1.002 normal(0,10)
##
## 3.554 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .f_br23 2.342 0.072 2.200 2.485 2.342 5.436
## .f_c30 2.437 0.088 2.263 2.609 2.437 6.914
## .s_br23 1.765 0.064 1.639 1.892 1.765 3.096
## .s_c30 2.164 0.090 1.989 2.342 2.164 9.343
## .cv_gral 0.200 0.214 -0.217 0.625 0.200 0.142
## .salud 4.336 0.206 3.930 4.741 4.336 3.220
## .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 0.157 0.029 0.108 0.222 0.157 0.846
## .f_c30 0.062 0.028 0.009 0.120 0.062 0.497
## .s_br23 0.221 0.059 0.149 0.390 0.221 0.681
## .s_c30 0.054 0.041 0.000 0.141 0.054 1.000
## .cv_gral 0.530 0.087 0.386 0.726 0.530 0.266
## .salud 1.617 0.283 1.147 2.250 1.617 0.892
## .funcionalidad 0.029 0.020 0.000 0.070 1.000 1.000
## sintomas 0.104 0.053 0.001 0.209 1.000 1.000
## Rhat Prior
## 1.002 gamma(1,.5)[sd]
## 1.009 gamma(1,.5)[sd]
## 1.547 gamma(1,.5)[sd]
## 1.008 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.327 gamma(1,.5)[sd]
##
## R-Square:
## Estimate
## f_br23 0.154
## f_c30 0.503
## s_br23 0.319
## s_c30 0.000
## cv_gral 0.734
## salud 0.108
## funcionalidad 0.000summary(fitbase_bio,standardized = TRUE, rsquare=TRUE)## ** WARNING ** blavaan (0.4-1) did NOT converge after 16000 adapt+burnin iterations
## ** WARNING ** Proceed with caution
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -1597.464 0.000
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## f_br23 1.000 0.177 0.406
## f_c30 1.482 0.164 1.205 1.847 0.262 0.730
## sintomas =~
## s_br23 1.000 0.280 0.510
## s_c30 0.127 6.997 -23.834 3.394 0.036 0.159
## biologicas =~
## her2_pos 1.000 0.039 0.076
## edad -0.355 10.487 -20.744 20.314 -0.014 -0.001
## comorb 0.067 6.077 -13.299 13.541 0.003 0.005
## estadio_avz -1.051 9.638 -19.433 18.196 -0.041 -0.092
## Rhat Prior
##
##
## 1.004 normal(0,15)
##
##
## 3.620 normal(0,15)
##
##
## 1.001 normal(0,10)
## 1.000 normal(0,10)
## 1.001 normal(0,10)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## cv_gral ~
## salud 0.899 0.046 0.810 0.989 0.899 0.858
## salud ~
## funcionalidad 2.614 0.395 1.902 3.453 0.462 0.341
## funcionalidad ~
## sintomas -0.081 4.315 -2.147 14.665 -0.128 -0.128
## sintomas ~
## biologicas 0.600 8.589 -17.028 17.528 0.083 0.083
## Rhat Prior
##
## 1.001 normal(0,10)
##
## 1.001 normal(0,10)
##
## 3.546 normal(0,10)
##
## 1.001 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .f_br23 2.342 0.073 2.199 2.483 2.342 5.378
## .f_c30 2.436 0.088 2.263 2.609 2.436 6.790
## .s_br23 1.765 0.064 1.640 1.891 1.765 3.218
## .s_c30 2.165 0.091 1.988 2.344 2.165 9.668
## .her2_pos 0.439 0.057 0.328 0.550 0.439 0.861
## .edad 53.711 1.341 51.073 56.341 53.711 4.479
## .comorb 0.337 0.055 0.227 0.445 0.337 0.707
## .estadio_avz 0.337 0.054 0.229 0.443 0.337 0.759
## .cv_gral 0.203 0.216 -0.218 0.637 0.203 0.143
## .salud 4.334 0.204 3.931 4.733 4.334 3.202
## .funcionalidad 0.000 0.000 0.000
## .sintomas 0.000 0.000 0.000
## biologicas 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(0,32)
## 1.000 normal(0,32)
## 1.001 normal(0,32)
## 1.000 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 0.158 0.030 0.109 0.225 0.158 0.835
## .f_c30 0.060 0.028 0.007 0.119 0.060 0.467
## .s_br23 0.222 0.059 0.149 0.393 0.222 0.739
## .s_c30 0.049 0.040 0.000 0.138 0.049 0.975
## .her2_pos 0.258 0.043 0.188 0.354 0.258 0.994
## .edad 143.820 22.332 106.365 193.318 143.820 1.000
## .comorb 0.228 0.046 0.144 0.318 0.228 1.000
## .estadio_avz 0.195 0.063 0.027 0.300 0.195 0.992
## .cv_gral 0.530 0.088 0.384 0.726 0.530 0.264
## .salud 1.619 0.285 1.147 2.247 1.619 0.884
## .funcionalidad 0.031 0.020 0.000 0.071 0.984 0.984
## .sintomas 0.078 0.053 0.000 0.187 0.993 0.993
## biologicas 0.002 0.004 0.000 0.011 1.000 1.000
## Rhat Prior
## 1.003 gamma(1,.5)[sd]
## 1.008 gamma(1,.5)[sd]
## 1.561 gamma(1,.5)[sd]
## 1.009 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.006 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.003 gamma(1,.5)[sd]
## 1.152 gamma(1,.5)[sd]
## 1.026 gamma(1,.5)[sd]
##
## R-Square:
## Estimate
## f_br23 0.165
## f_c30 0.533
## s_br23 0.261
## s_c30 0.025
## her2_pos 0.006
## edad 0.000
## comorb 0.000
## estadio_avz 0.008
## cv_gral 0.736
## salud 0.116
## funcionalidad 0.016
## sintomas 0.007summary(fitbase_bio_ind,standardized = TRUE, rsquare=TRUE)## blavaan (0.4-1) results of 8000 samples after 16000 adapt/burnin iterations
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -1105.048 0.001
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## f_br23 1.000 0.472 0.770
## f_c30 1.450 0.159 1.179 1.803 0.684 0.927
## sintomas =~
## s_br23 1.000 0.296 0.546
## s_c30 2.352 0.482 1.670 3.506 0.695 0.931
## biologicas =~
## her2_pos 1.000 0.038 0.075
## edad -0.429 10.589 -21.351 20.336 -0.016 -0.001
## comorb 0.032 6.246 -13.823 13.933 0.001 0.003
## estadio_avz -0.995 9.439 -19.044 18.068 -0.038 -0.085
## Rhat Prior
##
##
## 1.000 normal(0,15)
##
##
## 1.001 normal(0,15)
##
##
## 1.000 normal(0,10)
## 1.000 normal(0,10)
## 1.001 normal(0,10)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## cv_gral ~
## salud 0.758 0.067 0.625 0.889 0.758 0.778
## sintomas -0.521 5.646 -13.383 12.266 -0.154 -0.089
## funcionalidad 0.385 3.709 -8.026 8.780 0.181 0.105
## salud ~
## funcionalidad 2.603 0.391 1.901 3.441 1.228 0.695
## funcionalidad ~
## sintomas -1.540 0.336 -2.335 -1.041 -0.965 -0.965
## sintomas ~
## biologicas 0.462 8.827 -17.665 17.872 0.059 0.059
## Rhat Prior
##
## 1.000 normal(0,10)
## 1.000 normal(0,10)
## 1.000 normal(0,10)
##
## 1.000 normal(0,10)
##
## 1.001 normal(0,10)
##
## 1.001 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .f_br23 2.343 0.072 2.203 2.486 2.343 3.828
## .f_c30 2.438 0.088 2.265 2.611 2.438 3.305
## .s_br23 1.765 0.062 1.641 1.887 1.765 3.258
## .s_c30 2.163 0.090 1.986 2.340 2.163 2.899
## .her2_pos 0.438 0.057 0.327 0.549 0.438 0.860
## .edad 53.716 1.340 51.091 56.337 53.716 4.483
## .comorb 0.338 0.055 0.231 0.445 0.338 0.712
## .estadio_avz 0.338 0.054 0.231 0.444 0.338 0.759
## .cv_gral 0.811 0.305 0.218 1.418 0.811 0.472
## .salud 4.338 0.205 3.934 4.742 4.338 2.456
## .funcionalidad 0.000 0.000 0.000
## .sintomas 0.000 0.000 0.000
## biologicas 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(0,32)
## 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 0.152 0.029 0.104 0.217 0.152 0.406
## .f_c30 0.077 0.028 0.026 0.135 0.077 0.141
## .s_br23 0.206 0.036 0.147 0.286 0.206 0.702
## .s_c30 0.074 0.040 0.001 0.149 0.074 0.133
## .her2_pos 0.258 0.043 0.188 0.355 0.258 0.994
## .edad 143.585 22.424 105.817 193.123 143.585 1.000
## .comorb 0.225 0.050 0.110 0.318 0.225 1.000
## .estadio_avz 0.196 0.064 0.020 0.302 0.196 0.993
## .cv_gral 0.443 0.103 0.212 0.639 0.443 0.150
## .salud 1.613 0.286 1.138 2.258 1.613 0.517
## .funcionalidad 0.015 0.017 0.000 0.058 0.069 0.069
## .sintomas 0.087 0.048 0.002 0.189 0.996 0.996
## biologicas 0.001 0.004 0.000 0.010 1.000 1.000
## Rhat Prior
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
##
## R-Square:
## Estimate
## f_br23 0.594
## f_c30 0.859
## s_br23 0.298
## s_c30 0.867
## her2_pos 0.006
## edad 0.000
## comorb 0.000
## estadio_avz 0.007
## cv_gral 0.850
## salud 0.483
## funcionalidad 0.931
## sintomas 0.004summary(fitbase_bio_ind_econ,standardized = TRUE, rsquare=TRUE)## ** WARNING ** blavaan (0.4-1) did NOT converge after 16000 adapt+burnin iterations
## ** WARNING ** Proceed with caution
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -1783.898 0.004
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## f_br23 1.000 0.134 0.323
## f_c30 1.462 0.163 1.187 1.824 0.196 0.584
## sintomas =~
## s_br23 1.000 0.281 0.513
## s_c30 0.071 7.153 -24.257 3.467 0.020 0.075
## biologicas =~
## her2_pos 1.000 0.060 0.118
## edad -3.215 11.447 -25.686 18.838 -0.193 -0.016
## comorb -0.681 5.113 -11.480 10.678 -0.041 -0.085
## estadio_avz -1.651 8.680 -17.697 16.794 -0.099 -0.214
## socioeconom =~
## estr_bajo 1.000 0.132 0.263
## rs_subsid 3.248 2.512 0.928 10.219 0.427 0.719
## hasta_sec 5.326 3.727 1.710 15.794 0.701 0.964
## trabaja 0.423 0.966 -1.268 2.681 0.056 0.110
## Rhat Prior
##
##
## 1.008 normal(0,15)
##
##
## 3.561 normal(0,15)
##
##
## 1.008 normal(0,10)
## 1.010 normal(0,10)
## 1.024 normal(0,10)
##
##
## 1.001 normal(0,10)
## 1.000 normal(0,10)
## 1.000 normal(0,10)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## cv_gral ~
## salud 0.759 0.068 0.624 0.893 0.759 0.816
## sintomas -0.111 5.777 -12.967 13.191 -0.031 -0.025
## funcionalidad 0.503 3.388 -7.272 8.427 0.067 0.055
## companero -0.001 0.162 -0.320 0.318 -0.001 -0.000
## salud ~
## funcionalidad 2.617 0.395 1.915 3.463 0.351 0.266
## funcionalidad ~
## sintomas -0.116 4.437 -2.290 14.993 -0.243 -0.243
## sintomas ~
## biologicas 1.162 8.348 -16.631 16.796 0.249 0.249
## Rhat Prior
##
## 1.000 normal(0,10)
## 1.008 normal(0,10)
## 1.000 normal(0,10)
## 1.000 normal(0,10)
##
## 1.002 normal(0,10)
##
## 3.543 normal(0,10)
##
## 1.030 normal(0,10)
##
## Covariances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## biologicas ~~
## socioeconom -0.002 0.005 -0.016 0.003 -0.262 -0.262
## Rhat Prior
##
## 1.015 beta(1,1)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .f_br23 2.343 0.072 2.201 2.486 2.343 5.647
## .f_c30 2.438 0.088 2.264 2.612 2.438 7.264
## .s_br23 1.765 0.064 1.641 1.890 1.765 3.225
## .s_c30 2.163 0.091 1.986 2.342 2.163 8.090
## .her2_pos 0.437 0.057 0.325 0.549 0.437 0.859
## .edad 53.717 1.341 51.072 56.339 53.717 4.505
## .comorb 0.338 0.055 0.230 0.446 0.338 0.703
## .estadio_avz 0.338 0.054 0.231 0.445 0.338 0.729
## .estr_bajo 0.562 0.056 0.453 0.671 0.562 1.126
## .rs_subsid 0.363 0.056 0.254 0.471 0.363 0.610
## .hasta_sec 0.650 0.055 0.542 0.759 0.650 0.894
## .trabaja 0.600 0.057 0.489 0.712 0.600 1.185
## .cv_gral 0.809 0.311 0.202 1.423 0.809 0.660
## .salud 4.337 0.206 3.934 4.745 4.337 3.291
## .funcionalidad 0.000 0.000 0.000
## .sintomas 0.000 0.000 0.000
## biologicas 0.000 0.000 0.000
## socioeconom 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(0,32)
## 1.000 normal(0,32)
## 1.000 normal(0,32)
## 1.000 normal(0,32)
## 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 0.154 0.029 0.106 0.220 0.154 0.896
## .f_c30 0.074 0.028 0.021 0.133 0.074 0.659
## .s_br23 0.221 0.059 0.147 0.390 0.221 0.737
## .s_c30 0.071 0.040 0.001 0.147 0.071 0.994
## .her2_pos 0.256 0.043 0.185 0.352 0.256 0.986
## .edad 142.133 22.795 103.315 192.056 142.133 1.000
## .comorb 0.229 0.039 0.164 0.316 0.229 0.993
## .estadio_avz 0.205 0.043 0.126 0.293 0.205 0.954
## .estr_bajo 0.232 0.039 0.167 0.320 0.232 0.931
## .rs_subsid 0.171 0.037 0.099 0.244 0.171 0.483
## .hasta_sec 0.038 0.040 0.000 0.141 0.038 0.071
## .trabaja 0.253 0.042 0.185 0.347 0.253 0.988
## .cv_gral 0.455 0.100 0.245 0.652 0.455 0.303
## .salud 1.614 0.285 1.139 2.254 1.614 0.929
## .funcionalidad 0.017 0.018 0.000 0.060 0.941 0.941
## .sintomas 0.074 0.045 0.000 0.167 0.938 0.938
## biologicas 0.004 0.009 0.000 0.033 1.000 1.000
## socioeconom 0.017 0.017 0.001 0.062 1.000 1.000
## Rhat Prior
## 1.003 gamma(1,.5)[sd]
## 1.014 gamma(1,.5)[sd]
## 1.555 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.004 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.007 gamma(1,.5)[sd]
## 1.200 gamma(1,.5)[sd]
## 1.008 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
##
## R-Square:
## Estimate
## f_br23 0.104
## f_c30 0.341
## s_br23 0.263
## s_c30 0.006
## her2_pos 0.014
## edad 0.000
## comorb 0.007
## estadio_avz 0.046
## estr_bajo 0.069
## rs_subsid 0.517
## hasta_sec 0.929
## trabaja 0.012
## cv_gral 0.697
## salud 0.071
## funcionalidad 0.059
## sintomas 0.062summary(fitref_bio_ind_sinedad,standardized = TRUE, rsquare=TRUE)## ** WARNING ** blavaan (0.4-1) did NOT converge after 16000 adapt+burnin iterations
## ** WARNING ** Proceed with caution
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -1000.025 0.061
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## f_br23 1.000 0.419 0.698
## f_c30 -0.029 4.582 -15.522 1.793 -0.012 -0.044
## sintomas =~
## s_br23 1.000 0.294 0.543
## s_c30 2.368 0.481 1.681 3.513 0.696 0.935
## biologicas =~
## her2_pos 1.000 0.033 0.066
## comorb 0.058 6.131 -13.571 13.574 0.002 0.004
## estadio_avz -1.196 9.650 -19.334 18.397 -0.040 -0.091
## Rhat Prior
##
##
## 4.142 normal(0,15)
##
##
## 1.006 normal(0,15)
##
##
## 1.000 normal(0,10)
## 1.000 normal(0,10)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## cv_gral ~
## salud 0.760 0.068 0.625 0.890 0.760 0.788
## sintomas -0.546 5.340 -12.663 11.900 -0.160 -0.131
## funcionalidad 0.354 4.098 -8.697 9.466 0.148 0.121
## salud ~
## funcionalidad 0.173 7.502 -25.186 3.413 0.073 0.057
## funcionalidad ~
## sintomas -1.367 0.604 -2.286 0.210 -0.960 -0.960
## sintomas ~
## biologicas 0.656 8.916 -17.613 17.937 0.075 0.075
## Rhat Prior
##
## 1.005 normal(0,10)
## 1.002 normal(0,10)
## 1.002 normal(0,10)
##
## 4.392 normal(0,10)
##
## 1.955 normal(0,10)
##
## 1.001 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .f_br23 2.343 0.073 2.200 2.485 2.343 3.902
## .f_c30 2.438 0.088 2.265 2.610 2.438 8.832
## .s_br23 1.765 0.063 1.641 1.889 1.765 3.261
## .s_c30 2.164 0.090 1.988 2.340 2.164 2.906
## .her2_pos 0.438 0.057 0.326 0.549 0.438 0.860
## .comorb 0.337 0.055 0.231 0.446 0.337 0.704
## .estadio_avz 0.338 0.055 0.231 0.445 0.338 0.765
## .cv_gral 0.806 0.306 0.214 1.420 0.806 0.656
## .salud 4.337 0.204 3.937 4.740 4.337 3.408
## .funcionalidad 0.000 0.000 0.000
## .sintomas 0.000 0.000 0.000
## biologicas 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(0,32)
## 1.000 normal(0,32)
## 1.000 normal(0,32)
## 1.005 normal(0,10)
## 1.000 normal(0,10)
##
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .f_br23 0.185 0.105 0.106 0.526 0.185 0.513
## .f_c30 0.076 0.030 0.018 0.138 0.076 0.998
## .s_br23 0.207 0.036 0.147 0.288 0.207 0.705
## .s_c30 0.070 0.040 0.001 0.147 0.070 0.126
## .her2_pos 0.258 0.042 0.188 0.353 0.258 0.996
## .comorb 0.230 0.042 0.157 0.319 0.230 1.000
## .estadio_avz 0.193 0.065 0.016 0.300 0.193 0.992
## .cv_gral 0.445 0.103 0.220 0.639 0.445 0.296
## .salud 1.615 0.286 1.140 2.255 1.615 0.997
## .funcionalidad 0.014 0.017 0.000 0.057 0.079 0.079
## .sintomas 0.086 0.047 0.002 0.186 0.994 0.994
## biologicas 0.001 0.003 0.000 0.007 1.000 1.000
## Rhat Prior
## 2.858 gamma(1,.5)[sd]
## 1.004 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.041 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.007 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.040 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
##
## R-Square:
## Estimate
## f_br23 0.487
## f_c30 0.002
## s_br23 0.295
## s_c30 0.874
## her2_pos 0.004
## comorb 0.000
## estadio_avz 0.008
## cv_gral 0.704
## salud 0.003
## funcionalidad 0.921
## sintomas 0.006summary(fit_ref_bio_ind_sinedad_indi,standardized = TRUE, rsquare=TRUE)## ** WARNING ** blavaan (0.4-1) did NOT converge after 16000 adapt+burnin iterations
## ** WARNING ** Proceed with caution
##
## Number of observations 80
##
## Number of missing patterns 1
##
## Statistic MargLogLik PPP
## Value -1000.025 0.061
##
## Latent Variables:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## funcionalidad =~
## f_br23 1.000 0.419 0.698
## f_c30 -0.029 4.582 -15.522 1.793 -0.012 -0.044
## sintomas =~
## s_br23 1.000 0.294 0.543
## s_c30 2.368 0.481 1.681 3.513 0.696 0.935
## biologicas =~
## her2_pos 1.000 0.033 0.066
## comorb 0.058 6.131 -13.571 13.574 0.002 0.004
## estadio_avz -1.196 9.650 -19.334 18.397 -0.040 -0.091
## Rhat Prior
##
##
## 4.142 normal(0,15)
##
##
## 1.006 normal(0,15)
##
##
## 1.000 normal(0,10)
## 1.000 normal(0,10)
##
## Regressions:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## cv_gral ~
## salud (d) 0.760 0.068 0.625 0.890 0.760 0.788
## sintomas (e) -0.546 5.340 -12.663 11.900 -0.160 -0.131
## funcionldd (c) 0.354 4.098 -8.697 9.466 0.148 0.121
## salud ~
## funcionldd 0.173 7.502 -25.186 3.413 0.073 0.057
## funcionalidad ~
## sintomas (b) -1.367 0.604 -2.286 0.210 -0.960 -0.960
## sintomas ~
## biologicas (a) 0.656 8.916 -17.613 17.937 0.075 0.075
## Rhat Prior
##
## 1.005 normal(0,10)
## 1.002 normal(0,10)
## 1.002 normal(0,10)
##
## 4.392 normal(0,10)
##
## 1.955 normal(0,10)
##
## 1.001 normal(0,10)
##
## Intercepts:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .f_br23 2.343 0.073 2.200 2.485 2.343 3.902
## .f_c30 2.438 0.088 2.265 2.610 2.438 8.832
## .s_br23 1.765 0.063 1.641 1.889 1.765 3.261
## .s_c30 2.164 0.090 1.988 2.340 2.164 2.906
## .her2_pos 0.438 0.057 0.326 0.549 0.438 0.860
## .comorb 0.337 0.055 0.231 0.446 0.337 0.704
## .estadio_avz 0.338 0.055 0.231 0.445 0.338 0.765
## .cv_gral 0.806 0.306 0.214 1.420 0.806 0.656
## .salud 4.337 0.204 3.937 4.740 4.337 3.408
## .funcionalidad 0.000 0.000 0.000
## .sintomas 0.000 0.000 0.000
## biologicas 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(0,32)
## 1.000 normal(0,32)
## 1.000 normal(0,32)
## 1.005 normal(0,10)
## 1.000 normal(0,10)
##
##
##
##
## Variances:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## .f_br23 0.185 0.105 0.106 0.526 0.185 0.513
## .f_c30 0.076 0.030 0.018 0.138 0.076 0.998
## .s_br23 0.207 0.036 0.147 0.288 0.207 0.705
## .s_c30 0.070 0.040 0.001 0.147 0.070 0.126
## .her2_pos 0.258 0.042 0.188 0.353 0.258 0.996
## .comorb 0.230 0.042 0.157 0.319 0.230 1.000
## .estadio_avz 0.193 0.065 0.016 0.300 0.193 0.992
## .cv_gral 0.445 0.103 0.220 0.639 0.445 0.296
## .salud 1.615 0.286 1.140 2.255 1.615 0.997
## .funcionalidad 0.014 0.017 0.000 0.057 0.079 0.079
## .sintomas 0.086 0.047 0.002 0.186 0.994 0.994
## biologicas 0.001 0.003 0.000 0.007 1.000 1.000
## Rhat Prior
## 2.858 gamma(1,.5)[sd]
## 1.004 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.041 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.007 gamma(1,.5)[sd]
## 1.002 gamma(1,.5)[sd]
## 1.040 gamma(1,.5)[sd]
## 1.001 gamma(1,.5)[sd]
## 1.000 gamma(1,.5)[sd]
##
## R-Square:
## Estimate
## f_br23 0.487
## f_c30 0.002
## s_br23 0.295
## s_c30 0.874
## her2_pos 0.004
## comorb 0.000
## estadio_avz 0.008
## cv_gral 0.704
## salud 0.003
## funcionalidad 0.921
## sintomas 0.006
##
## Defined Parameters:
## Estimate Post.SD pi.lower pi.upper Std.lv Std.all
## ab -0.897 13.235 -26.837 25.043 -0.072 -0.072
## abc -0.317 47.722 -93.850 93.216 -0.011 -0.009
## abcd -0.241 36.039 -70.876 70.394 -0.008 -0.007
## bc -0.483 5.346 -10.961 9.994 -0.142 -0.116
## indtot -1.455 86.058 -170.125 167.215 -0.090 -0.087
## tot -2.001 86.055 -170.666 166.664 -0.251 -0.218
## Rhat Prior
##
##
##
##
##
## Informacion del BRMSEA
blavFitIndices(fitbase)## Posterior mean (EAP) of devm-based fit indices:
##
## BRMSEA BGammaHat adjBGammaHat BMc
## 0.196 0.927 0.659 0.888blavFitIndices(fitbase_bio)## Posterior mean (EAP) of devm-based fit indices:
##
## BRMSEA BGammaHat adjBGammaHat BMc
## 0.144 0.870 0.764 0.689blavFitIndices(fitbase_bio_ind) #Estable## Posterior mean (EAP) of devm-based fit indices:
##
## BRMSEA BGammaHat adjBGammaHat BMc
## 0.129 0.890 0.808 0.735blavFitIndices(fitbase_bio_ind_econ)## Posterior mean (EAP) of devm-based fit indices:
##
## BRMSEA BGammaHat adjBGammaHat BMc
## 0.095 0.898 0.852 0.656blavFitIndices(fitref_bio_ind_sinedad)## Posterior mean (EAP) of devm-based fit indices:
##
## BRMSEA BGammaHat adjBGammaHat BMc
## 0.123 0.925 0.819 0.834blavFitIndices(fit_ref_bio_ind_sinedad_indi)## Posterior mean (EAP) of devm-based fit indices:
##
## BRMSEA BGammaHat adjBGammaHat BMc
## 0.123 0.925 0.819 0.834Informacion de R hat modelo de referencia
blavInspect(fitref_bio_ind_sinedad, 'rhat')## funcionalidad=~f_c30 sintomas=~s_c30
## 4.1416945 1.0057563
## biologicas=~comorb biologicas=~estadio_avz
## 1.0003526 1.0004456
## cv_gral~salud cv_gral~sintomas
## 1.0050586 1.0017878
## cv_gral~funcionalidad salud~funcionalidad
## 1.0019100 4.3917103
## funcionalidad~sintomas sintomas~biologicas
## 1.9549747 1.0007313
## f_br23~~f_br23 f_c30~~f_c30
## 2.8578249 1.0035277
## s_br23~~s_br23 s_c30~~s_c30
## 1.0010867 1.0408338
## her2_pos~~her2_pos comorb~~comorb
## 0.9999434 1.0001239
## estadio_avz~~estadio_avz cv_gral~~cv_gral
## 1.0012542 1.0070653
## salud~~salud funcionalidad~~funcionalidad
## 1.0015160 1.0397867
## sintomas~~sintomas biologicas~~biologicas
## 1.0014242 1.0003310
## f_br23~1 f_c30~1
## 1.0001414 1.0002870
## s_br23~1 s_c30~1
## 1.0001496 1.0003307
## her2_pos~1 comorb~1
## 0.9999232 0.9999847
## estadio_avz~1 cv_gral~1
## 1.0000231 1.0046053
## salud~1
## 1.0001564Informacion del neff modelo de referencia
blavInspect(fitref_bio_ind_sinedad, 'neff')## funcionalidad=~f_c30 sintomas=~s_c30
## 5.310336e+00 8.986759e+03
## biologicas=~comorb biologicas=~estadio_avz
## 3.703932e+04 1.516862e+04
## cv_gral~salud cv_gral~sintomas
## 1.100330e+04 8.925498e+03
## cv_gral~funcionalidad salud~funcionalidad
## 1.069878e+04 5.271663e+00
## funcionalidad~sintomas sintomas~biologicas
## 6.725866e+00 1.720989e+04
## f_br23~~f_br23 f_c30~~f_c30
## 5.674639e+00 1.574809e+04
## s_br23~~s_br23 s_c30~~s_c30
## 7.836849e+04 7.781605e+01
## her2_pos~~her2_pos comorb~~comorb
## 9.652116e+04 3.892976e+04
## estadio_avz~~estadio_avz cv_gral~~cv_gral
## 1.348066e+04 3.996257e+03
## salud~~salud funcionalidad~~funcionalidad
## 7.760741e+04 8.548301e+01
## sintomas~~sintomas biologicas~~biologicas
## 2.966903e+04 3.775208e+04
## f_br23~1 f_c30~1
## 3.770940e+04 3.139352e+04
## s_br23~1 s_c30~1
## 4.904776e+04 3.152051e+04
## her2_pos~1 comorb~1
## 1.030892e+05 1.024333e+05
## estadio_avz~1 cv_gral~1
## 9.705563e+04 2.165530e+04
## salud~1
## 4.087441e+04Graficos de modelos sem bayesiano con la funcion semplot
semPaths(
fitbase,
intercepts = FALSE,
residuals = TRUE,
edge.label.cex = 1.5,
intStyle = "multi",
optimizeLatRes = TRUE,
title.color = "black",
groups = "lat",
pastel = TRUE,
exoVar = FALSE,
sizeInt = 5,
edge.color = "black",
esize = 6,
label.prop = 2,
sizeLat = 6,
"std"
)
semPaths(
fitbase_bio,
intercepts = FALSE,
residuals = TRUE,
edge.label.cex = 1.5,
intStyle = "multi",
optimizeLatRes = TRUE,
title.color = "black",
groups = "lat",
pastel = TRUE,
exoVar = FALSE,
sizeInt = 5,
edge.color = "black",
esize = 6,
label.prop = 2,
sizeLat = 6,
"std"
)
semPaths(
fitbase_bio_ind,
intercepts = FALSE,
residuals = TRUE,
edge.label.cex = 1.5,
intStyle = "multi",
optimizeLatRes = TRUE,
title.color = "black",
groups = "lat",
pastel = TRUE,
exoVar = FALSE,
sizeInt = 5,
edge.color = "black",
esize = 6,
label.prop = 2,
sizeLat = 6,
"std"
)
semPaths(
fitbase_bio_ind_econ,
intercepts = FALSE,
residuals = TRUE,
edge.label.cex = 1.5,
intStyle = "multi",
optimizeLatRes = TRUE,
title.color = "black",
groups = "lat",
pastel = TRUE,
exoVar = FALSE,
sizeInt = 5,
edge.color = "black",
esize = 6,
label.prop = 2,
sizeLat = 6,
"std"
)
semPaths(
fitref_bio_ind_sinedad,
intercepts = FALSE,
residuals = TRUE,
edge.label.cex = 1.5,
intStyle = "multi",
optimizeLatRes = TRUE,
title.color = "black",
groups = "lat",
pastel = TRUE,
exoVar = FALSE,
sizeInt = 5,
edge.color = "black",
esize = 6,
label.prop = 2,
sizeLat = 6,
"std"
)
graficos de mcmc
plot(fitbase, par = 1:12, facet_args = list(ncol = 4))
plot(fitbase_bio, par = 1:12, facet_args = list(ncol = 4))
plot(fitbase_bio_ind, par = 1:12, facet_args = list(ncol = 4))
plot(fitbase_bio_ind_econ, par = 1:12, facet_args = list(ncol = 4))
plot(fitref_bio_ind_sinedad, par = 1:12, facet_args = list(ncol = 4))
continuacion de graficos mcmc modelos ref
plot(fitbase, facet_args = list(ncol = 4))
plot(fitbase_bio, facet_args = list(ncol = 4))
plot(fitbase_bio_ind, facet_args = list(ncol = 4))
plot(fitbase_bio_ind_econ, facet_args = list(ncol = 4))
plot(fitref_bio_ind_sinedad, facet_args = list(ncol = 4))
Grafico de intervalos todo modelos ref
plot(fitbase, plot.type = "intervals")
plot(fitbase_bio, plot.type = "intervals")
plot(fitbase_bio_ind, plot.type = "intervals")
plot(fitbase_bio_ind_econ, plot.type = "intervals")
plot(fitref_bio_ind_sinedad, plot.type = "intervals")
Gráfico de coordenas paralelas de todos modelos ref
plot(fitbase, plot.type = "parcoord")
plot(fitbase_bio, plot.type = "parcoord")
plot(fitbase_bio_ind, plot.type = "parcoord")
plot(fitbase_bio_ind_econ, plot.type = "parcoord")
plot(fitref_bio_ind_sinedad, plot.type = "parcoord")
Tabla de indices relevantes para describir el SEM
describe_posterior(fitref_bio_ind_sinedad)## Summary of Posterior Distribution
##
## Parameter | Component | Median | 95% CI | pd | ROPE | % in ROPE | Rhat | ESS
## ------------------------------------------------------------------------------------------------------------------------------
## funcionalidad=~f_c30 | latent | 1.42 | [-13.08, 2.10] | 90.00% | [-0.10, 0.10] | 0% | 4.142 | 5.00
## sintomas=~s_c30 | latent | 2.29 | [ 1.57, 3.29] | 100% | [-0.10, 0.10] | 0% | 1.006 | 8987.00
## biologicas=~comorb | latent | 0.09 | [-13.79, 13.32] | 51.15% | [-0.10, 0.10] | 2.60% | 1.000 | 37039.00
## biologicas=~estadio_avz | latent | -2.13 | [-19.56, 18.12] | 57.39% | [-0.10, 0.10] | 0.54% | 1.000 | 15169.00
## cv_gral~salud | regression | 0.76 | [ 0.63, 0.89] | 100% | [-0.10, 0.10] | 0% | 1.005 | 11003.00
## cv_gral~sintomas | regression | -0.60 | [-12.76, 11.77] | 61.33% | [-0.10, 0.10] | 3.54% | 1.002 | 8925.00
## cv_gral~funcionalidad | regression | 0.37 | [ -8.88, 9.25] | 58.80% | [-0.10, 0.10] | 4.83% | 1.002 | 10699.00
## salud~funcionalidad | regression | 2.53 | [-21.40, 4.04] | 90.00% | [-0.10, 0.10] | 0% | 4.392 | 5.00
## funcionalidad~sintomas | regression | -1.45 | [ -2.15, 0.27] | 90.00% | [-0.10, 0.10] | 0.49% | 1.955 | 7.00
## sintomas~biologicas | regression | 1.41 | [-17.01, 18.50] | 56.93% | [-0.10, 0.10] | 0.77% | 1.001 | 17210.00
## f_br23~~f_br23 | residual | 0.15 | [ 0.09, 0.47] | 100% | [-0.10, 0.10] | 0.99% | 2.858 | 6.00
## f_c30~~f_c30 | residual | 0.08 | [ 0.02, 0.14] | 100% | [-0.10, 0.10] | 82.20% | 1.004 | 15748.00
## s_br23~~s_br23 | residual | 0.20 | [ 0.14, 0.28] | 100% | [-0.10, 0.10] | 0% | 1.001 | 78368.00
## s_c30~~s_c30 | residual | 0.07 | [ 0.00, 0.13] | 100% | [-0.10, 0.10] | 80.10% | 1.041 | 78.00
## her2_pos~~her2_pos | residual | 0.25 | [ 0.18, 0.34] | 100% | [-0.10, 0.10] | 0% | 1.000 | 96521.00
## comorb~~comorb | residual | 0.23 | [ 0.16, 0.32] | 100% | [-0.10, 0.10] | 0% | 1.000 | 38930.00
## estadio_avz~~estadio_avz | residual | 0.20 | [ 0.00, 0.28] | 100% | [-0.10, 0.10] | 9.88% | 1.001 | 13481.00
## cv_gral~~cv_gral | residual | 0.45 | [ 0.26, 0.66] | 100% | [-0.10, 0.10] | 0% | 1.007 | 3996.00
## salud~~salud | residual | 1.59 | [ 1.10, 2.19] | 100% | [-0.10, 0.10] | 0% | 1.002 | 77607.00
## funcionalidad~~funcionalidad | residual | 6.22e-03 | [ 0.00, 0.05] | 100% | [-0.10, 0.10] | 100% | 1.040 | 85.00
## sintomas~~sintomas | residual | 0.08 | [ 0.00, 0.17] | 100% | [-0.10, 0.10] | 67.01% | 1.001 | 29669.00
## biologicas~~biologicas | residual | 3.99e-04 | [ 0.00, 0.00] | 100% | [-0.10, 0.10] | 100% | 1.000 | 37752.00
## f_br23~1 | intercept | 2.34 | [ 2.20, 2.49] | 100% | [-0.10, 0.10] | 0% | 1.000 | 37709.00
## f_c30~1 | intercept | 2.44 | [ 2.27, 2.61] | 100% | [-0.10, 0.10] | 0% | 1.000 | 31394.00
## s_br23~1 | intercept | 1.77 | [ 1.64, 1.89] | 100% | [-0.10, 0.10] | 0% | 1.000 | 49048.00
## s_c30~1 | intercept | 2.16 | [ 1.99, 2.34] | 100% | [-0.10, 0.10] | 0% | 1.000 | 31521.00
## her2_pos~1 | intercept | 0.44 | [ 0.33, 0.55] | 100% | [-0.10, 0.10] | 0% | 1.000 | 1.03e+05
## comorb~1 | intercept | 0.34 | [ 0.23, 0.44] | 100% | [-0.10, 0.10] | 0% | 1.000 | 1.02e+05
## estadio_avz~1 | intercept | 0.34 | [ 0.23, 0.44] | 100% | [-0.10, 0.10] | 0% | 1.000 | 97056.00
## cv_gral~1 | intercept | 0.80 | [ 0.22, 1.43] | 99.62% | [-0.10, 0.10] | 0% | 1.005 | 21655.00
## salud~1 | intercept | 4.34 | [ 3.94, 4.74] | 100% | [-0.10, 0.10] | 0% | 1.000 | 40874.00sexit(fitref_bio_ind_sinedad)## # Following the Sequential Effect eXistence and sIgnificance Testing (SEXIT) framework, we report the median of the posterior distribution and its 95% CI (Highest Density Interval), along the probability of direction (pd), the probability of significance and the probability of being large. The thresholds beyond which the effect is considered as significant (i.e., non-negligible) and large are |0.05| and |0.30|.
##
## - funcionalidad=~f_c30 (Median = 1.42, 95% CI [-13.08, 2.10]) has a 90.00% probability of being positive (> 0), 90.00% of being significant (> 0.05), and 90.00% of being large (> 0.30)
## - sintomas=~s_c30 (Median = 2.29, 95% CI [1.57, 3.29]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 100.00% of being large (> 0.30)
## - biologicas=~comorb (Median = 0.09, 95% CI [-13.79, 13.32]) has a 51.15% probability of being positive (> 0), 50.50% of being significant (> 0.05), and 47.39% of being large (> 0.30)
## - biologicas=~estadio_avz (Median = -2.13, 95% CI [-19.56, 18.12]) has a 57.39% probability of being negative (< 0), 57.24% of being significant (< -0.05), and 56.59% of being large (< -0.30)
## - cv_gral~salud (Median = 0.76, 95% CI [0.63, 0.89]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 100.00% of being large (> 0.30)
## - cv_gral~sintomas (Median = -0.60, 95% CI [-12.76, 11.77]) has a 61.33% probability of being negative (< 0), 60.48% of being significant (< -0.05), and 55.95% of being large (< -0.30)
## - cv_gral~funcionalidad (Median = 0.37, 95% CI [-8.88, 9.25]) has a 58.80% probability of being positive (> 0), 57.67% of being significant (> 0.05), and 51.54% of being large (> 0.30)
## - salud~funcionalidad (Median = 2.53, 95% CI [-21.40, 4.04]) has a 90.00% probability of being positive (> 0), 90.00% of being significant (> 0.05), and 90.00% of being large (> 0.30)
## - funcionalidad~sintomas (Median = -1.45, 95% CI [-2.15, 0.27]) has a 90.00% probability of being negative (< 0), 90.00% of being significant (< -0.05), and 90.00% of being large (< -0.30)
## - sintomas~biologicas (Median = 1.41, 95% CI [-17.01, 18.50]) has a 56.93% probability of being positive (> 0), 56.75% of being significant (> 0.05), and 55.82% of being large (> 0.30)
## - f_br23~~f_br23 (Median = 0.15, 95% CI [0.09, 0.47]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 10.00% of being large (> 0.30)
## - f_c30~~f_c30 (Median = 0.08, 95% CI [0.02, 0.14]) has a 100.00% probability of being positive (> 0), 82.18% of being significant (> 0.05), and 0.00% of being large (> 0.30)
## - s_br23~~s_br23 (Median = 0.20, 95% CI [0.14, 0.28]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 1.47% of being large (> 0.30)
## - s_c30~~s_c30 (Median = 0.07, 95% CI [5.58e-10, 0.13]) has a 100.00% probability of being positive (> 0), 68.52% of being significant (> 0.05), and 0.00% of being large (> 0.30)
## - her2_pos~~her2_pos (Median = 0.25, 95% CI [0.18, 0.34]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 15.33% of being large (> 0.30)
## - comorb~~comorb (Median = 0.23, 95% CI [0.16, 0.32]) has a 100.00% probability of being positive (> 0), 99.78% of being significant (> 0.05), and 5.38% of being large (> 0.30)
## - estadio_avz~~estadio_avz (Median = 0.20, 95% CI [1.20e-10, 0.28]) has a 100.00% probability of being positive (> 0), 94.98% of being significant (> 0.05), and 2.53% of being large (> 0.30)
## - cv_gral~~cv_gral (Median = 0.45, 95% CI [0.26, 0.66]) has a 100.00% probability of being positive (> 0), 99.16% of being significant (> 0.05), and 94.34% of being large (> 0.30)
## - salud~~salud (Median = 1.59, 95% CI [1.10, 2.19]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 100.00% of being large (> 0.30)
## - funcionalidad~~funcionalidad (Median = 6.22e-03, 95% CI [1.92e-13, 0.05]) has a 100.00% probability of being positive (> 0), 4.66% of being significant (> 0.05), and 0.00% of being large (> 0.30)
## - sintomas~~sintomas (Median = 0.08, 95% CI [2.82e-10, 0.17]) has a 100.00% probability of being positive (> 0), 77.12% of being significant (> 0.05), and 0.03% of being large (> 0.30)
## - biologicas~~biologicas (Median = 3.99e-04, 95% CI [8.84e-13, 4.37e-03]) has a 100.00% probability of being positive (> 0), 0.03% of being significant (> 0.05), and 0.00% of being large (> 0.30)
## - f_br23~1 (Median = 2.34, 95% CI [2.20, 2.49]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 100.00% of being large (> 0.30)
## - f_c30~1 (Median = 2.44, 95% CI [2.27, 2.61]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 100.00% of being large (> 0.30)
## - s_br23~1 (Median = 1.77, 95% CI [1.64, 1.89]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 100.00% of being large (> 0.30)
## - s_c30~1 (Median = 2.16, 95% CI [1.99, 2.34]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 100.00% of being large (> 0.30)
## - her2_pos~1 (Median = 0.44, 95% CI [0.33, 0.55]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 99.19% of being large (> 0.30)
## - comorb~1 (Median = 0.34, 95% CI [0.23, 0.44]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 75.20% of being large (> 0.30)
## - estadio_avz~1 (Median = 0.34, 95% CI [0.23, 0.44]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 75.72% of being large (> 0.30)
## - cv_gral~1 (Median = 0.80, 95% CI [0.22, 1.43]) has a 99.62% probability of being positive (> 0), 99.38% of being significant (> 0.05), and 95.33% of being large (> 0.30)
## - salud~1 (Median = 4.34, 95% CI [3.94, 4.74]) has a 100.00% probability of being positive (> 0), 100.00% of being significant (> 0.05), and 100.00% of being large (> 0.30)
##
## Parameter | Median | 95% CI | Direction | Significance (> |0.05|) | Large (> |0.30|)
## -----------------------------------------------------------------------------------------------------------------------
## funcionalidad=~f_c30 | 1.42 | [-13.08, 2.10] | 0.90 | 0.90 | 0.90
## sintomas=~s_c30 | 2.29 | [1.57, 3.29] | 1.00 | 1.00 | 1.00
## biologicas=~comorb | 0.09 | [-13.79, 13.32] | 0.51 | 0.50 | 0.47
## biologicas=~estadio_avz | -2.13 | [-19.56, 18.12] | 0.57 | 0.57 | 0.57
## cv_gral~salud | 0.76 | [0.63, 0.89] | 1.00 | 1.00 | 1.00
## cv_gral~sintomas | -0.60 | [-12.76, 11.77] | 0.61 | 0.60 | 0.56
## cv_gral~funcionalidad | 0.37 | [-8.88, 9.25] | 0.59 | 0.58 | 0.52
## salud~funcionalidad | 2.53 | [-21.40, 4.04] | 0.90 | 0.90 | 0.90
## funcionalidad~sintomas | -1.45 | [-2.15, 0.27] | 0.90 | 0.90 | 0.90
## sintomas~biologicas | 1.41 | [-17.01, 18.50] | 0.57 | 0.57 | 0.56
## f_br23~~f_br23 | 0.15 | [0.09, 0.47] | 1.00 | 1.00 | 0.10
## f_c30~~f_c30 | 0.08 | [0.02, 0.14] | 1.00 | 0.82 | 0.00
## s_br23~~s_br23 | 0.20 | [0.14, 0.28] | 1.00 | 1.00 | 0.01
## s_c30~~s_c30 | 0.07 | [5.58e-10, 0.13] | 1.00 | 0.69 | 0.00
## her2_pos~~her2_pos | 0.25 | [0.18, 0.34] | 1.00 | 1.00 | 0.15
## comorb~~comorb | 0.23 | [0.16, 0.32] | 1.00 | 1.00 | 0.05
## estadio_avz~~estadio_avz | 0.20 | [1.20e-10, 0.28] | 1.00 | 0.95 | 0.03
## cv_gral~~cv_gral | 0.45 | [0.26, 0.66] | 1.00 | 0.99 | 0.94
## salud~~salud | 1.59 | [1.10, 2.19] | 1.00 | 1.00 | 1.00
## funcionalidad~~funcionalidad | 6.22e-03 | [1.92e-13, 0.05] | 1.00 | 0.05 | 0.00
## sintomas~~sintomas | 0.08 | [2.82e-10, 0.17] | 1.00 | 0.77 | 3.38e-04
## biologicas~~biologicas | 3.99e-04 | [8.84e-13, 4.37e-03] | 1.00 | 2.75e-04 | 0.00
## f_br23~1 | 2.34 | [2.20, 2.49] | 1.00 | 1.00 | 1.00
## f_c30~1 | 2.44 | [2.27, 2.61] | 1.00 | 1.00 | 1.00
## s_br23~1 | 1.77 | [1.64, 1.89] | 1.00 | 1.00 | 1.00
## s_c30~1 | 2.16 | [1.99, 2.34] | 1.00 | 1.00 | 1.00
## her2_pos~1 | 0.44 | [0.33, 0.55] | 1.00 | 1.00 | 0.99
## comorb~1 | 0.34 | [0.23, 0.44] | 1.00 | 1.00 | 0.75
## estadio_avz~1 | 0.34 | [0.23, 0.44] | 1.00 | 1.00 | 0.76
## cv_gral~1 | 0.80 | [0.22, 1.43] | 1.00 | 0.99 | 0.95
## salud~1 | 4.34 | [3.94, 4.74] | 1.00 | 1.00 | 1.00Comparacion de todos los modelos vs modelo de referencia
comparison <- bayesfactor_models(fitbase,fitbase_bio,fitbase_bio_ind,fitbase_bio_ind_econ, denominator = fitref_bio_ind_sinedad)
comparison## Bayes Factors for Model Comparison
##
## Model BF
## [1] fitbase 9.08e-06
## [2] fitbase_bio 3.43e-260
## [3] fitbase_bio_ind 2.45e-46
## [4] fitbase_bio_ind_econ 0.00e+00
##
## * Against Denominator: [5] fitref_bio_ind_sinedad
## * Bayes Factor Type: marginal likelihoods (Laplace approximation)mat_comp <- as.matrix(comparison)
heatmap(mat_comp)