In what follows, please find the results of additional analyses. These include models, results without covariates, results with all participants (hence, including those removed due to speeding).
Load packages.
# define packages
packages <- c("cowplot", "devtools", "faoutlier", "GGally", "kableExtra", "knitr", "lavaan", "magrittr", "MVN", "psych",
"pwr", "quanteda", "semTools", "td", "tidyverse")
# load packages
lapply(packages, library, character.only = TRUE, quietly = TRUE)Load data.
# load workspace
load("data/workspace.rdata")In what follows, you can find estimations of variance inflation factors, which help gauge multicollinearity. Generally, values above 5 or even 10 are considered problematic. However, these are only rules of thumb, and multicollinearity can occur with lower values. Indeed, although the values reported below are not above 5, they are increased, suggesting that multicollinearity might be at play here, which the preregistered analyses also confirm.
# Self-Efficacy
model <- "
pri_con =~ PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07
grats_gen =~ GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05
pri_delib =~ PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05
self_eff =~ SE01_01 + SE01_02 + SE01_03 + SE01_04
SE01_01 ~~ a*SE01_02
SE01_03 ~~ a*SE01_04
trust_community =~ TR01_01 + TR01_02 + TR01_03
trust_provider =~ TR01_04 + TR01_05 + TR01_06 + TR01_07 + TR01_08 + TR01_09
trust_spec =~ trust_community + trust_provider
self_eff ~ pri_con + grats_gen + pri_delib + trust_spec
# Covariates
GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05 + PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07 + TR01_01 + TR01_02 + TR01_03 + TR01_04 + TR01_05 + TR01_06 + TR01_07 + TR01_08 + TR01_09 + PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05 + SE01_01 + SE01_02 + SE01_03 + SE01_04 ~ male + age + edu
"
fit <- sem(model, data = d, estimator = "MLR", missing = "ML")
r_self_eff <- inspect(fit, what = "rsquare")["self_eff"] # extract rsquare
vif_self_eff <- 1 / (1 - r_self_eff) # compute vif
# Privacy Deliberation
model <- "
pri_con =~ PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07
grats_gen =~ GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05
pri_delib =~ PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05
self_eff =~ SE01_01 + SE01_02 + SE01_03 + SE01_04
SE01_01 ~~ a*SE01_02
SE01_03 ~~ a*SE01_04
trust_community =~ TR01_01 + TR01_02 + TR01_03
trust_provider =~ TR01_04 + TR01_05 + TR01_06 + TR01_07 + TR01_08 + TR01_09
trust_spec =~ trust_community + trust_provider
pri_delib ~ self_eff + pri_con + grats_gen + trust_spec
# Covariates
GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05 + PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07 + TR01_01 + TR01_02 + TR01_03 + TR01_04 + TR01_05 + TR01_06 + TR01_07 + TR01_08 + TR01_09 + PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05 + SE01_01 + SE01_02 + SE01_03 + SE01_04 ~ male + age + edu
"
fit <- sem(model, data = d, estimator = "MLR", missing = "ML")
r_pri_delib <- inspect(fit, what = "rsquare")["pri_delib"]
vif_pri_delib <- 1 / (1 - r_pri_delib)
## Privacy Concerns
model <- "
pri_con =~ PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07
grats_gen =~ GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05
pri_delib =~ PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05
self_eff =~ SE01_01 + SE01_02 + SE01_03 + SE01_04
SE01_01 ~~ a*SE01_02
SE01_03 ~~ a*SE01_04
trust_community =~ TR01_01 + TR01_02 + TR01_03
trust_provider =~ TR01_04 + TR01_05 + TR01_06 + TR01_07 + TR01_08 + TR01_09
trust_spec =~ trust_community + trust_provider
pri_con ~ self_eff + pri_delib + grats_gen + trust_spec
# Covariates
GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05 + PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07 + TR01_01 + TR01_02 + TR01_03 + TR01_04 + TR01_05 + TR01_06 + TR01_07 + TR01_08 + TR01_09 + PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05 + SE01_01 + SE01_02 + SE01_03 + SE01_04 ~ male + age + edu
"
fit <- sem(model, data = d, estimator = "MLR", missing = "ML")
r_pri_con <- inspect(fit, what = "rsquare")["pri_con"]
vif_pri_con <- 1 / (1 - r_pri_con)
# Gratifications
model <- "
pri_con =~ PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07
grats_gen =~ GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05
pri_delib =~ PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05
self_eff =~ SE01_01 + SE01_02 + SE01_03 + SE01_04
SE01_01 ~~ a*SE01_02
SE01_03 ~~ a*SE01_04
trust_community =~ TR01_01 + TR01_02 + TR01_03
trust_provider =~ TR01_04 + TR01_05 + TR01_06 + TR01_07 + TR01_08 + TR01_09
trust_spec =~ trust_community + trust_provider
grats_gen ~ self_eff + pri_con + pri_delib + trust_spec
# Covariates
GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05 + PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07 + TR01_01 + TR01_02 + TR01_03 + TR01_04 + TR01_05 + TR01_06 + TR01_07 + TR01_08 + TR01_09 + PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05 + SE01_01 + SE01_02 + SE01_03 + SE01_04 ~ male + age + edu
"
fit <- sem(model, data = d, estimator = "MLR", missing = "ML")
r_grats_gen <- inspect(fit, what = "rsquare")["grats_gen"]
vif_grats_gen <- 1 / (1 - r_grats_gen)
# Trust
model <- "
pri_con =~ PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07
grats_gen =~ GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05
pri_delib =~ PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05
self_eff =~ SE01_01 + SE01_02 + SE01_03 + SE01_04
SE01_01 ~~ a*SE01_02
SE01_03 ~~ a*SE01_04
trust_community =~ TR01_01 + TR01_02 + TR01_03
trust_provider =~ TR01_04 + TR01_05 + TR01_06
trust_system =~ TR01_07 + TR01_08 + TR01_09
trust_spec =~ trust_community + trust_provider + trust_system
trust_spec ~ self_eff + pri_con + grats_gen + pri_delib
# Covariates
GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05 + PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07 + TR01_01 + TR01_02 + TR01_03 + TR01_04 + TR01_05 + TR01_06 + TR01_07 + TR01_08 + TR01_09 + PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05 + SE01_01 + SE01_02 + SE01_03 + SE01_04 ~ male + age + edu
"
fit <- sem(model, data = d, estimator = "MLR", missing = "ML")
r_trust_spec <- inspect(fit, what = "rsquare")["trust_spec"]
vif_trust_spec <- 1 / (1 - r_trust_spec)# Table
tibble("Gratifications" = vif_grats_gen, "Trust Specific" = vif_trust_spec, "Privacy Concerns" = vif_pri_con, "Privacy Deliberation" = vif_pri_delib, "Self-Efficacy" = vif_self_eff) %>%
kable() %>%
kable_styling("striped")| Gratifications | Trust Specific | Privacy Concerns | Privacy Deliberation | Self-Efficacy |
|---|---|---|---|---|
| 2.73 | 3.14 | 1.61 | 1.51 | 1.51 |
I first analyze the model how it was initially preregistered.
model <- "
pri_con =~ PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07
grats_gen =~ GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05
pri_delib =~ PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05
self_eff =~ SE01_01 + SE01_02 + SE01_03 + SE01_04
SE01_01 ~~ x*SE01_02
SE01_03 ~~ x*SE01_04
trust_community =~ TR02_01 + TR01_01 + TR01_02 + TR01_03
trust_provider =~ TR02_02 + TR01_04 + TR01_05 + TR01_06
trust_system =~ TR02_03 + TR01_07 + TR01_08 + TR01_09
trust =~ trust_community + trust_provider + trust_system
self_dis_log ~ a1*pri_con + b1*grats_gen + c1*pri_delib + d1*self_eff + e1*trust
# Covariates
self_dis_log + GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05 + PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07 + TR02_01 + TR02_02 + TR02_03 + TR01_01 + TR01_02 + TR01_03 + TR01_04 + TR01_05 + TR01_06 + TR01_07 + TR01_08 + TR01_09 + PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05 + SE01_01 + SE01_02 + SE01_03 + SE01_04 ~ male + age + edu
"
fit_prereg <- sem(model, data = d, estimator = "MLR", missing = "ML")
summary(fit_prereg, fit = TRUE, std = TRUE)lavaan 0.6.16.1845 ended normally after 371 iterations
Estimator ML
Optimization method NLMINB
Number of model parameters 217
Number of equality constraints 1
Used Total
Number of observations 558 559
Number of missing patterns 3
Model Test User Model:
Standard Scaled
Test Statistic 1586.064 1215.351
Degrees of freedom 477 477
P-value (Chi-square) 0.000 0.000
Scaling correction factor 1.305
Yuan-Bentler correction (Mplus variant)
Model Test Baseline Model:
Test statistic 15518.638 11639.461
Degrees of freedom 627 627
P-value 0.000 0.000
Scaling correction factor 1.333
User Model versus Baseline Model:
Comparative Fit Index (CFI) 0.926 0.933
Tucker-Lewis Index (TLI) 0.902 0.912
Robust Comparative Fit Index (CFI) 0.935
Robust Tucker-Lewis Index (TLI) 0.915
Loglikelihood and Information Criteria:
Loglikelihood user model (H0) -25561.311 -25561.311
Scaling correction factor 1.272
for the MLR correction
Loglikelihood unrestricted model (H1) -24768.279 -24768.279
Scaling correction factor 1.296
for the MLR correction
Akaike (AIC) 51554.622 51554.622
Bayesian (BIC) 52488.684 52488.684
Sample-size adjusted Bayesian (SABIC) 51802.997 51802.997
Root Mean Square Error of Approximation:
RMSEA 0.065 0.053
90 Percent confidence interval - lower 0.061 0.049
90 Percent confidence interval - upper 0.068 0.056
P-value H_0: RMSEA <= 0.050 0.000 0.085
P-value H_0: RMSEA >= 0.080 0.000 0.000
Robust RMSEA 0.060
90 Percent confidence interval - lower 0.056
90 Percent confidence interval - upper 0.064
P-value H_0: Robust RMSEA <= 0.050 0.000
P-value H_0: Robust RMSEA >= 0.080 0.000
Standardized Root Mean Square Residual:
SRMR 0.055 0.055
Parameter Estimates:
Standard errors Sandwich
Information bread Observed
Observed information based on Hessian
Latent Variables:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
pri_con =~
PC01_01 1.000 1.595 0.926
PC01_02 0.990 0.027 36.261 0.000 1.579 0.894
PC01_04 0.972 0.027 35.770 0.000 1.550 0.884
PC01_05 1.002 0.024 42.507 0.000 1.599 0.907
PC01_06 0.855 0.038 22.715 0.000 1.363 0.795
PC01_07 0.995 0.023 43.874 0.000 1.587 0.921
grats_gen =~
GR02_01 1.000 1.131 0.842
GR02_02 1.121 0.033 33.552 0.000 1.267 0.894
GR02_03 1.022 0.048 21.487 0.000 1.155 0.863
GR02_04 0.987 0.048 20.426 0.000 1.116 0.849
GR02_05 1.075 0.040 27.159 0.000 1.215 0.848
pri_delib =~
PD01_01 1.000 1.477 0.856
PD01_02 0.669 0.048 13.865 0.000 0.988 0.643
PD01_03 0.704 0.055 12.844 0.000 1.040 0.668
PD01_04 0.839 0.047 17.744 0.000 1.239 0.726
PD01_05 0.714 0.050 14.199 0.000 1.054 0.636
self_eff =~
SE01_01 1.000 1.117 0.809
SE01_02 0.813 0.057 14.200 0.000 0.907 0.672
SE01_03 0.928 0.045 20.405 0.000 1.036 0.774
SE01_04 0.951 0.043 22.273 0.000 1.062 0.788
trust_community =~
TR02_01 1.000 0.995 0.863
TR01_01 0.997 0.050 19.980 0.000 0.992 0.782
TR01_02 0.860 0.041 20.893 0.000 0.855 0.778
TR01_03 0.959 0.042 22.816 0.000 0.953 0.827
trust_provider =~
TR02_02 1.000 0.978 0.850
TR01_04 1.060 0.046 23.034 0.000 1.036 0.863
TR01_05 0.911 0.047 19.287 0.000 0.891 0.770
TR01_06 0.923 0.035 26.574 0.000 0.903 0.816
trust_system =~
TR02_03 1.000 1.034 0.857
TR01_07 0.802 0.044 18.371 0.000 0.829 0.705
TR01_08 0.820 0.057 14.411 0.000 0.848 0.654
TR01_09 1.073 0.043 24.682 0.000 1.110 0.826
trust =~
trust_communty 1.000 0.815 0.815
trust_provider 1.176 0.064 18.418 0.000 0.975 0.975
trust_system 1.322 0.077 17.165 0.000 1.036 1.036
Regressions:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
self_dis_log ~
pri_con (a1) -0.058 0.079 -0.729 0.466 -0.092 -0.040
grats_gen (b1) 0.068 0.130 0.521 0.602 0.077 0.034
pri_delib (c1) -0.169 0.092 -1.840 0.066 -0.249 -0.109
self_eff (d1) 0.758 0.139 5.447 0.000 0.846 0.370
trust (e1) -0.213 0.230 -0.923 0.356 -0.172 -0.075
male -0.021 0.197 -0.109 0.913 -0.021 -0.005
age 0.003 0.006 0.570 0.569 0.003 0.024
edu 0.213 0.116 1.836 0.066 0.213 0.078
GR02_01 ~
male -0.127 0.116 -1.096 0.273 -0.127 -0.047
age 0.000 0.004 0.091 0.927 0.000 0.004
edu 0.005 0.068 0.073 0.941 0.005 0.003
GR02_02 ~
male -0.067 0.120 -0.559 0.576 -0.067 -0.024
age 0.006 0.004 1.542 0.123 0.006 0.068
edu -0.080 0.071 -1.127 0.260 -0.080 -0.047
GR02_03 ~
male -0.025 0.116 -0.220 0.826 -0.025 -0.009
age 0.001 0.004 0.310 0.756 0.001 0.014
edu -0.083 0.067 -1.237 0.216 -0.083 -0.052
GR02_04 ~
male 0.028 0.113 0.250 0.802 0.028 0.011
age 0.005 0.004 1.304 0.192 0.005 0.057
edu -0.072 0.067 -1.072 0.284 -0.072 -0.046
GR02_05 ~
male -0.140 0.124 -1.136 0.256 -0.140 -0.049
age -0.004 0.004 -0.874 0.382 -0.004 -0.039
edu 0.013 0.073 0.173 0.862 0.013 0.007
PC01_01 ~
male -0.182 0.151 -1.206 0.228 -0.182 -0.053
age -0.004 0.005 -0.820 0.412 -0.004 -0.036
edu 0.110 0.087 1.255 0.209 0.110 0.054
PC01_02 ~
male -0.302 0.154 -1.966 0.049 -0.302 -0.085
age -0.008 0.005 -1.663 0.096 -0.008 -0.072
edu 0.047 0.089 0.522 0.601 0.047 0.022
PC01_04 ~
male -0.225 0.152 -1.475 0.140 -0.225 -0.064
age -0.010 0.005 -1.980 0.048 -0.010 -0.085
edu 0.113 0.089 1.269 0.204 0.113 0.054
PC01_05 ~
male -0.098 0.154 -0.636 0.525 -0.098 -0.028
age -0.006 0.005 -1.164 0.244 -0.006 -0.051
edu 0.090 0.090 0.996 0.319 0.090 0.043
PC01_06 ~
male -0.108 0.150 -0.722 0.470 -0.108 -0.032
age -0.005 0.005 -1.055 0.291 -0.005 -0.046
edu 0.043 0.087 0.491 0.623 0.043 0.021
PC01_07 ~
male -0.174 0.150 -1.160 0.246 -0.174 -0.050
age -0.006 0.005 -1.337 0.181 -0.006 -0.058
edu 0.081 0.087 0.934 0.350 0.081 0.040
TR02_01 ~
male -0.156 0.099 -1.570 0.116 -0.156 -0.067
age -0.003 0.003 -0.813 0.416 -0.003 -0.038
edu 0.026 0.060 0.433 0.665 0.026 0.019
TR02_02 ~
male 0.076 0.100 0.762 0.446 0.076 0.033
age -0.004 0.003 -1.216 0.224 -0.004 -0.053
edu 0.088 0.059 1.490 0.136 0.088 0.064
TR02_03 ~
male 0.064 0.104 0.619 0.536 0.064 0.027
age -0.007 0.004 -1.939 0.053 -0.007 -0.088
edu -0.018 0.060 -0.295 0.768 -0.018 -0.012
TR01_01 ~
male -0.297 0.108 -2.744 0.006 -0.297 -0.117
age -0.004 0.004 -1.103 0.270 -0.004 -0.049
edu 0.005 0.062 0.086 0.931 0.005 0.004
TR01_02 ~
male -0.140 0.095 -1.480 0.139 -0.140 -0.064
age -0.002 0.003 -0.566 0.571 -0.002 -0.025
edu 0.023 0.053 0.434 0.664 0.023 0.018
TR01_03 ~
male -0.134 0.099 -1.361 0.173 -0.134 -0.058
age -0.004 0.003 -1.211 0.226 -0.004 -0.055
edu -0.003 0.060 -0.046 0.964 -0.003 -0.002
TR01_04 ~
male -0.086 0.104 -0.831 0.406 -0.086 -0.036
age 0.000 0.003 0.110 0.912 0.000 0.005
edu -0.051 0.058 -0.880 0.379 -0.051 -0.036
TR01_05 ~
male -0.045 0.099 -0.450 0.653 -0.045 -0.019
age 0.001 0.003 0.344 0.731 0.001 0.015
edu 0.018 0.058 0.309 0.757 0.018 0.013
TR01_06 ~
male 0.046 0.095 0.480 0.631 0.046 0.021
age -0.004 0.003 -1.250 0.211 -0.004 -0.053
edu 0.025 0.056 0.445 0.656 0.025 0.019
TR01_07 ~
male 0.092 0.100 0.915 0.360 0.092 0.039
age -0.004 0.003 -1.176 0.240 -0.004 -0.050
edu -0.055 0.058 -0.948 0.343 -0.055 -0.040
TR01_08 ~
male 0.027 0.112 0.245 0.806 0.027 0.011
age 0.003 0.004 0.824 0.410 0.003 0.035
edu -0.093 0.065 -1.435 0.151 -0.093 -0.061
TR01_09 ~
male -0.121 0.115 -1.044 0.296 -0.121 -0.045
age -0.002 0.004 -0.405 0.685 -0.002 -0.018
edu -0.146 0.068 -2.156 0.031 -0.146 -0.091
PD01_01 ~
male -0.177 0.148 -1.197 0.231 -0.177 -0.051
age -0.015 0.005 -3.275 0.001 -0.015 -0.137
edu -0.026 0.085 -0.310 0.756 -0.026 -0.013
PD01_02 ~
male -0.119 0.131 -0.906 0.365 -0.119 -0.039
age -0.014 0.004 -3.443 0.001 -0.014 -0.142
edu 0.031 0.077 0.405 0.686 0.031 0.017
PD01_03 ~
male -0.321 0.132 -2.425 0.015 -0.321 -0.103
age -0.004 0.004 -1.024 0.306 -0.004 -0.044
edu 0.065 0.080 0.807 0.419 0.065 0.035
PD01_04 ~
male -0.412 0.145 -2.847 0.004 -0.412 -0.121
age -0.009 0.005 -1.904 0.057 -0.009 -0.082
edu 0.103 0.085 1.207 0.227 0.103 0.051
PD01_05 ~
male -0.205 0.142 -1.439 0.150 -0.205 -0.062
age -0.012 0.004 -2.696 0.007 -0.012 -0.111
edu -0.002 0.084 -0.025 0.980 -0.002 -0.001
SE01_01 ~
male 0.119 0.118 1.009 0.313 0.119 0.043
age 0.000 0.004 0.005 0.996 0.000 0.000
edu 0.211 0.068 3.110 0.002 0.211 0.129
SE01_02 ~
male 0.059 0.112 0.525 0.599 0.059 0.022
age -0.013 0.004 -3.600 0.000 -0.013 -0.151
edu 0.198 0.066 2.996 0.003 0.198 0.123
SE01_03 ~
male 0.194 0.114 1.696 0.090 0.194 0.072
age 0.001 0.004 0.244 0.807 0.001 0.011
edu 0.142 0.067 2.130 0.033 0.142 0.090
SE01_04 ~
male 0.053 0.115 0.460 0.646 0.053 0.020
age 0.007 0.004 2.045 0.041 0.007 0.085
edu 0.126 0.066 1.904 0.057 0.126 0.079
Covariances:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
.SE01_01 ~~
.SE01_02 (x) 0.107 0.044 2.444 0.015 0.107 0.142
.SE01_03 ~~
.SE01_04 (x) 0.107 0.044 2.444 0.015 0.107 0.158
pri_con ~~
grats_gen -0.282 0.096 -2.953 0.003 -0.157 -0.157
pri_delib 1.328 0.131 10.165 0.000 0.563 0.563
self_eff -0.378 0.091 -4.146 0.000 -0.212 -0.212
trust -0.463 0.066 -7.039 0.000 -0.358 -0.358
grats_gen ~~
pri_delib -0.069 0.103 -0.672 0.502 -0.041 -0.041
self_eff 0.470 0.067 7.039 0.000 0.373 0.373
trust 0.654 0.067 9.731 0.000 0.714 0.714
pri_delib ~~
self_eff -0.327 0.095 -3.456 0.001 -0.198 -0.198
trust -0.220 0.074 -2.956 0.003 -0.183 -0.183
self_eff ~~
trust 0.500 0.055 9.139 0.000 0.553 0.553
Intercepts:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
.PC01_01 3.369 0.292 11.557 0.000 3.369 1.955
.PC01_02 3.769 0.304 12.398 0.000 3.769 2.135
.PC01_04 3.571 0.297 12.020 0.000 3.571 2.035
.PC01_05 3.414 0.304 11.229 0.000 3.414 1.937
.PC01_06 3.215 0.288 11.155 0.000 3.215 1.875
.PC01_07 3.461 0.294 11.780 0.000 3.461 2.008
.GR02_01 4.319 0.224 19.252 0.000 4.319 3.215
.GR02_02 4.492 0.244 18.372 0.000 4.492 3.170
.GR02_03 5.244 0.222 23.667 0.000 5.244 3.917
.GR02_04 4.988 0.221 22.522 0.000 4.988 3.795
.GR02_05 4.905 0.254 19.323 0.000 4.905 3.422
.PD01_01 4.493 0.290 15.507 0.000 4.493 2.602
.PD01_02 3.997 0.248 16.102 0.000 3.997 2.601
.PD01_03 4.432 0.270 16.438 0.000 4.432 2.845
.PD01_04 4.506 0.295 15.283 0.000 4.506 2.640
.PD01_05 5.000 0.276 18.089 0.000 5.000 3.018
.SE01_01 4.824 0.249 19.360 0.000 4.824 3.495
.SE01_02 5.731 0.234 24.466 0.000 5.731 4.247
.SE01_03 4.819 0.226 21.329 0.000 4.819 3.598
.SE01_04 4.533 0.234 19.381 0.000 4.533 3.363
.TR02_01 5.001 0.210 23.817 0.000 5.001 4.339
.TR01_01 5.083 0.219 23.224 0.000 5.083 4.010
.TR01_02 4.951 0.189 26.178 0.000 4.951 4.505
.TR01_03 4.871 0.200 24.361 0.000 4.871 4.223
.TR02_02 5.361 0.200 26.772 0.000 5.361 4.664
.TR01_04 5.521 0.205 26.991 0.000 5.521 4.600
.TR01_05 5.134 0.197 26.024 0.000 5.134 4.440
.TR01_06 5.232 0.188 27.764 0.000 5.232 4.728
.TR02_03 5.704 0.213 26.795 0.000 5.704 4.727
.TR01_07 5.955 0.193 30.911 0.000 5.955 5.060
.TR01_08 4.855 0.218 22.270 0.000 4.855 3.745
.TR01_09 5.581 0.231 24.175 0.000 5.581 4.149
.self_dis_log 1.376 0.375 3.673 0.000 1.376 0.602
pri_con 0.000 0.000 0.000
grats_gen 0.000 0.000 0.000
pri_delib 0.000 0.000 0.000
self_eff 0.000 0.000 0.000
.trust_communty 0.000 0.000 0.000
.trust_provider 0.000 0.000 0.000
.trust_system 0.000 0.000 0.000
trust 0.000 0.000 0.000
Variances:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
.PC01_01 0.403 0.050 8.097 0.000 0.403 0.136
.PC01_02 0.582 0.103 5.658 0.000 0.582 0.187
.PC01_04 0.628 0.077 8.148 0.000 0.628 0.204
.PC01_05 0.533 0.064 8.356 0.000 0.533 0.171
.PC01_06 1.069 0.116 9.245 0.000 1.069 0.364
.PC01_07 0.430 0.065 6.564 0.000 0.430 0.145
.GR02_01 0.522 0.054 9.737 0.000 0.522 0.289
.GR02_02 0.386 0.039 9.864 0.000 0.386 0.192
.GR02_03 0.452 0.074 6.145 0.000 0.452 0.252
.GR02_04 0.473 0.049 9.740 0.000 0.473 0.273
.GR02_05 0.569 0.062 9.128 0.000 0.569 0.277
.PD01_01 0.731 0.110 6.625 0.000 0.731 0.245
.PD01_02 1.330 0.128 10.403 0.000 1.330 0.564
.PD01_03 1.311 0.128 10.223 0.000 1.311 0.540
.PD01_04 1.305 0.147 8.875 0.000 1.305 0.448
.PD01_05 1.585 0.129 12.331 0.000 1.585 0.577
.SE01_01 0.620 0.086 7.205 0.000 0.620 0.326
.SE01_02 0.922 0.120 7.706 0.000 0.922 0.506
.SE01_03 0.693 0.096 7.211 0.000 0.693 0.386
.SE01_04 0.665 0.077 8.616 0.000 0.665 0.366
.TR02_01 0.331 0.035 9.367 0.000 0.331 0.249
.TR01_01 0.596 0.076 7.793 0.000 0.596 0.371
.TR01_02 0.471 0.049 9.541 0.000 0.471 0.390
.TR01_03 0.412 0.044 9.414 0.000 0.412 0.310
.TR02_02 0.354 0.037 9.508 0.000 0.354 0.268
.TR01_04 0.363 0.038 9.456 0.000 0.363 0.252
.TR01_05 0.543 0.054 10.032 0.000 0.543 0.406
.TR01_06 0.405 0.036 11.351 0.000 0.405 0.331
.TR02_03 0.374 0.041 9.150 0.000 0.374 0.257
.TR01_07 0.691 0.054 12.787 0.000 0.691 0.499
.TR01_08 0.953 0.080 11.888 0.000 0.953 0.567
.TR01_09 0.555 0.059 9.412 0.000 0.555 0.307
.self_dis_log 4.375 0.209 20.963 0.000 4.375 0.839
pri_con 2.545 0.144 17.641 0.000 1.000 1.000
grats_gen 1.278 0.114 11.204 0.000 1.000 1.000
pri_delib 2.183 0.158 13.845 0.000 1.000 1.000
self_eff 1.247 0.113 11.065 0.000 1.000 1.000
.trust_communty 0.332 0.041 8.103 0.000 0.336 0.336
.trust_provider 0.048 0.018 2.592 0.010 0.050 0.050
.trust_system -0.078 0.019 -4.083 0.000 -0.073 -0.073
trust 0.657 0.072 9.083 0.000 1.000 1.000rsquare_fit_prereg <- inspect(fit_prereg, what = "rsquare")["self_dis_log"]First, first is not optimal but still okaish, \(\chi^2\)(477) = 1586.06, p < .001, CFI = .93, RMSEA = .06, 90% CI [.06, .07], SRMR = .05. The result show the same problems of multicollinearity, namely that trust reduces online communication (despite a positive and more “plausible” postive bivariate relation).
As stated in our preregistration, we also provide the results without controlling for covariates. Note were here now using the updated preregistered model as reported in the paper.
model <- "
pri_con =~ PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07
grats_gen =~ GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05
pri_delib =~ PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05
self_eff =~ SE01_01 + SE01_02 + SE01_03 + SE01_04
SE01_01 ~~ x*SE01_02
SE01_03 ~~ x*SE01_04
trust_community =~ TR01_01 + TR01_02 + TR01_03
trust_provider =~ TR01_04 + TR01_05 + TR01_06
trust_system =~ TR01_07 + TR01_08 + TR01_09
trust_spec =~ trust_community + trust_provider + trust_system
words_log ~ a1*pri_con + b1*grats_gen + c1*pri_delib + d1*self_eff + e1*trust_spec
"
fit_prereg <- sem(model, data = d, estimator = "MLR", missing = "ML")
summary(fit_prereg, fit = TRUE, std = TRUE)lavaan 0.6.16.1845 ended normally after 124 iterations
Estimator ML
Optimization method NLMINB
Number of model parameters 109
Number of equality constraints 1
Number of observations 559
Number of missing patterns 3
Model Test User Model:
Standard Scaled
Test Statistic 1217.911 931.048
Degrees of freedom 387 387
P-value (Chi-square) 0.000 0.000
Scaling correction factor 1.308
Yuan-Bentler correction (Mplus variant)
Model Test Baseline Model:
Test statistic 13164.929 9384.152
Degrees of freedom 435 435
P-value 0.000 0.000
Scaling correction factor 1.403
User Model versus Baseline Model:
Comparative Fit Index (CFI) 0.935 0.939
Tucker-Lewis Index (TLI) 0.927 0.932
Robust Comparative Fit Index (CFI) 0.944
Robust Tucker-Lewis Index (TLI) 0.937
Loglikelihood and Information Criteria:
Loglikelihood user model (H0) -23976.938 -23976.938
Scaling correction factor 1.472
for the MLR correction
Loglikelihood unrestricted model (H1) -23367.982 -23367.982
Scaling correction factor 1.347
for the MLR correction
Akaike (AIC) 48169.876 48169.876
Bayesian (BIC) 48637.100 48637.100
Sample-size adjusted Bayesian (SABIC) 48294.256 48294.256
Root Mean Square Error of Approximation:
RMSEA 0.062 0.050
90 Percent confidence interval - lower 0.058 0.047
90 Percent confidence interval - upper 0.066 0.054
P-value H_0: RMSEA <= 0.050 0.000 0.467
P-value H_0: RMSEA >= 0.080 0.000 0.000
Robust RMSEA 0.057
90 Percent confidence interval - lower 0.052
90 Percent confidence interval - upper 0.062
P-value H_0: Robust RMSEA <= 0.050 0.009
P-value H_0: Robust RMSEA >= 0.080 0.000
Standardized Root Mean Square Residual:
SRMR 0.054 0.054
Parameter Estimates:
Standard errors Sandwich
Information bread Observed
Observed information based on Hessian
Latent Variables:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
pri_con =~
PC01_01 1.000 1.602 0.929
PC01_02 0.994 0.028 36.133 0.000 1.592 0.901
PC01_04 0.977 0.027 35.564 0.000 1.566 0.892
PC01_05 1.001 0.024 41.964 0.000 1.604 0.910
PC01_06 0.854 0.038 22.418 0.000 1.368 0.798
PC01_07 0.996 0.022 44.916 0.000 1.596 0.925
grats_gen =~
GR02_01 1.000 1.128 0.841
GR02_02 1.123 0.034 33.239 0.000 1.268 0.895
GR02_03 1.029 0.048 21.249 0.000 1.161 0.867
GR02_04 0.991 0.049 20.327 0.000 1.118 0.851
GR02_05 1.073 0.040 26.562 0.000 1.211 0.845
pri_delib =~
PD01_01 1.000 1.491 0.864
PD01_02 0.676 0.047 14.375 0.000 1.008 0.657
PD01_03 0.708 0.053 13.262 0.000 1.055 0.678
PD01_04 0.847 0.047 18.200 0.000 1.264 0.741
PD01_05 0.724 0.049 14.914 0.000 1.079 0.652
self_eff =~
SE01_01 1.000 1.134 0.821
SE01_02 0.808 0.059 13.658 0.000 0.916 0.679
SE01_03 0.928 0.045 20.697 0.000 1.052 0.784
SE01_04 0.939 0.042 22.307 0.000 1.064 0.788
trust_community =~
TR01_01 1.000 1.035 0.817
TR01_02 0.811 0.052 15.509 0.000 0.839 0.763
TR01_03 0.915 0.047 19.410 0.000 0.947 0.821
trust_provider =~
TR01_04 1.000 1.059 0.883
TR01_05 0.854 0.040 21.308 0.000 0.904 0.781
TR01_06 0.829 0.042 19.834 0.000 0.878 0.792
trust_system =~
TR01_07 1.000 0.801 0.680
TR01_08 1.058 0.082 12.937 0.000 0.847 0.654
TR01_09 1.405 0.088 16.009 0.000 1.125 0.837
trust_spec =~
trust_communty 1.000 0.843 0.843
trust_provider 1.159 0.080 14.577 0.000 0.955 0.955
trust_system 0.970 0.079 12.344 0.000 1.057 1.057
Regressions:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
words_log ~
pri_con (a1) -0.033 0.079 -0.415 0.678 -0.053 -0.023
grats_gen (b1) -0.003 0.147 -0.024 0.981 -0.004 -0.002
pri_delib (c1) -0.163 0.092 -1.776 0.076 -0.243 -0.105
self_eff (d1) 0.783 0.139 5.627 0.000 0.888 0.384
trust_spc (e1) -0.108 0.237 -0.456 0.648 -0.095 -0.041
Covariances:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
.SE01_01 ~~
.SE01_02 (x) 0.115 0.046 2.494 0.013 0.115 0.147
.SE01_03 ~~
.SE01_04 (x) 0.115 0.046 2.494 0.013 0.115 0.167
pri_con ~~
grats_gen -0.283 0.096 -2.952 0.003 -0.157 -0.157
pri_delib 1.354 0.132 10.246 0.000 0.566 0.566
self_eff -0.382 0.092 -4.162 0.000 -0.210 -0.210
trust_spec -0.411 0.070 -5.861 0.000 -0.294 -0.294
grats_gen ~~
pri_delib -0.072 0.101 -0.710 0.478 -0.043 -0.043
self_eff 0.462 0.067 6.874 0.000 0.361 0.361
trust_spec 0.749 0.081 9.276 0.000 0.761 0.761
pri_delib ~~
self_eff -0.334 0.093 -3.573 0.000 -0.198 -0.198
trust_spec -0.133 0.079 -1.676 0.094 -0.102 -0.102
self_eff ~~
trust_spec 0.527 0.059 8.856 0.000 0.532 0.532
Intercepts:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
.PC01_01 3.293 0.073 45.160 0.000 3.293 1.910
.PC01_02 3.327 0.075 44.525 0.000 3.327 1.883
.PC01_04 3.222 0.074 43.395 0.000 3.222 1.835
.PC01_05 3.263 0.075 43.748 0.000 3.263 1.850
.PC01_06 3.004 0.073 41.410 0.000 3.004 1.751
.PC01_07 3.224 0.073 44.188 0.000 3.224 1.869
.GR02_01 4.281 0.057 75.413 0.000 4.281 3.190
.GR02_02 4.596 0.060 76.742 0.000 4.596 3.246
.GR02_03 5.131 0.057 90.628 0.000 5.131 3.833
.GR02_04 5.089 0.056 91.559 0.000 5.089 3.873
.GR02_05 4.692 0.061 77.447 0.000 4.692 3.276
.PD01_01 3.658 0.073 50.136 0.000 3.658 2.121
.PD01_02 3.352 0.065 51.628 0.000 3.352 2.184
.PD01_03 4.191 0.066 63.662 0.000 4.191 2.693
.PD01_04 4.081 0.072 56.578 0.000 4.081 2.393
.PD01_05 4.351 0.070 62.149 0.000 4.351 2.629
.SE01_01 5.277 0.059 90.198 0.000 5.277 3.821
.SE01_02 5.523 0.057 96.568 0.000 5.523 4.093
.SE01_03 5.224 0.057 92.085 0.000 5.224 3.895
.SE01_04 5.138 0.057 89.952 0.000 5.138 3.805
.TR01_01 4.764 0.054 88.923 0.000 4.764 3.761
.TR01_02 4.844 0.046 104.195 0.000 4.844 4.407
.TR01_03 4.615 0.049 94.568 0.000 4.615 4.000
.TR01_04 5.403 0.051 106.478 0.000 5.403 4.504
.TR01_05 5.200 0.049 106.180 0.000 5.200 4.491
.TR01_06 5.129 0.047 109.405 0.000 5.129 4.627
.TR01_07 5.725 0.050 114.994 0.000 5.725 4.864
.TR01_08 4.834 0.055 88.152 0.000 4.834 3.728
.TR01_09 5.179 0.057 91.089 0.000 5.179 3.853
.words_log 1.834 0.098 18.765 0.000 1.834 0.794
pri_con 0.000 0.000 0.000
grats_gen 0.000 0.000 0.000
pri_delib 0.000 0.000 0.000
self_eff 0.000 0.000 0.000
.trust_communty 0.000 0.000 0.000
.trust_provider 0.000 0.000 0.000
.trust_system 0.000 0.000 0.000
trust_spec 0.000 0.000 0.000
Variances:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
.PC01_01 0.406 0.050 8.083 0.000 0.406 0.136
.PC01_02 0.587 0.104 5.655 0.000 0.587 0.188
.PC01_04 0.630 0.077 8.203 0.000 0.630 0.205
.PC01_05 0.536 0.065 8.267 0.000 0.536 0.172
.PC01_06 1.069 0.116 9.179 0.000 1.069 0.363
.PC01_07 0.429 0.065 6.568 0.000 0.429 0.144
.GR02_01 0.528 0.055 9.611 0.000 0.528 0.293
.GR02_02 0.398 0.041 9.622 0.000 0.398 0.199
.GR02_03 0.445 0.073 6.105 0.000 0.445 0.248
.GR02_04 0.477 0.048 9.892 0.000 0.477 0.276
.GR02_05 0.585 0.066 8.870 0.000 0.585 0.285
.PD01_01 0.753 0.110 6.829 0.000 0.753 0.253
.PD01_02 1.340 0.130 10.302 0.000 1.340 0.569
.PD01_03 1.310 0.129 10.157 0.000 1.310 0.540
.PD01_04 1.311 0.147 8.901 0.000 1.311 0.451
.PD01_05 1.575 0.129 12.243 0.000 1.575 0.575
.SE01_01 0.621 0.088 7.052 0.000 0.621 0.326
.SE01_02 0.981 0.129 7.630 0.000 0.981 0.539
.SE01_03 0.692 0.095 7.255 0.000 0.692 0.385
.SE01_04 0.690 0.081 8.479 0.000 0.690 0.378
.TR01_01 0.533 0.070 7.621 0.000 0.533 0.333
.TR01_02 0.504 0.057 8.919 0.000 0.504 0.417
.TR01_03 0.435 0.045 9.753 0.000 0.435 0.327
.TR01_04 0.317 0.034 9.382 0.000 0.317 0.220
.TR01_05 0.523 0.054 9.680 0.000 0.523 0.390
.TR01_06 0.458 0.044 10.406 0.000 0.458 0.373
.TR01_07 0.744 0.059 12.699 0.000 0.744 0.537
.TR01_08 0.963 0.079 12.195 0.000 0.963 0.573
.TR01_09 0.542 0.062 8.697 0.000 0.542 0.300
.words_log 4.462 0.216 20.659 0.000 4.462 0.835
pri_con 2.567 0.147 17.512 0.000 1.000 1.000
grats_gen 1.273 0.115 11.095 0.000 1.000 1.000
pri_delib 2.224 0.158 14.113 0.000 1.000 1.000
self_eff 1.286 0.115 11.215 0.000 1.000 1.000
.trust_communty 0.309 0.046 6.756 0.000 0.289 0.289
.trust_provider 0.098 0.032 3.083 0.002 0.088 0.088
.trust_system -0.075 0.020 -3.851 0.000 -0.117 -0.117
trust_spec 0.761 0.096 7.942 0.000 1.000 1.000rsquare_fit_prereg <- inspect(fit_prereg, what = "rsquare")["comm"]The results remain virtually the same (see page analyses).
As stated in the preregistration, we also report the analyses including the deleted participants.
We first need to rerun the baseline model to get new factor scores (output not shown here).
model_baseline <- "
pri_con =~ PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07
grats_gen =~ GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05
grats_inf =~ GR01_01 + GR01_02 + GR01_03
grats_rel =~ GR01_04 + GR01_05 + GR01_06
grats_par =~ GR01_07 + GR01_08 + GR01_09
grats_ide =~ GR01_10 + GR01_11 + GR01_12
grats_ext =~ GR01_13 + GR01_14 + GR01_15
grats_spec =~ grats_inf + grats_rel + grats_par + grats_ide + grats_ext
pri_delib =~ PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05
trust_gen =~ TR02_01 + TR02_02 + TR02_03
trust_community =~ TR01_01 + TR01_02 + TR01_03
trust_provider =~ TR01_04 + TR01_05 + TR01_06
trust_system =~ TR01_07 + TR01_08 + TR01_09
trust_spec =~ trust_community + trust_provider + trust_system
self_eff =~ SE01_01 + SE01_02 + SE01_03 + SE01_04
SE01_01 ~~ x*SE01_02
SE01_03 ~~ x*SE01_04
Words_log =~ words_log
Words_log ~~ a1*pri_con + b1*grats_gen + c1*pri_delib + d1*self_eff + e1*trust_spec + f1*trust_gen + g1*grats_spec
"
fit_baseline <- sem(model_baseline, data = d_all, missing = "ML")
summary(fit_baseline, standardized = TRUE, fit.measures = TRUE)# extract model predicted values for items & calc means
d_fs <- lavPredict(fit_baseline, type = "ov") %>%
as.data.frame() %>%
mutate(version = d_all$version,
grats_gen_fs = rowMeans(select(., starts_with("GR02"))),
grats_spec_fs = rowMeans(select(., starts_with("GR01"))),
pri_con_fs = rowMeans(select(., starts_with("PC01"))),
trust_gen_fs = rowMeans(select(., TR02_01, TR02_02, TR02_03)),
trust_spec_fs = rowMeans(select(., TR01_01: TR01_09)),
pri_del_fs = rowMeans(select(., starts_with("PD01"))),
self_eff_fs = rowMeans(select(., starts_with("SE01")))) %>%
select(version, pri_con_fs, grats_gen_fs, grats_spec_fs, pri_del_fs, self_eff_fs, trust_gen_fs, trust_spec_fs, words_log)
# combine d with d factor scores
d_all %<>% cbind(select(d_fs, -version, -words_log))Let’s now inspect the results of the (updated) preregistered model including removed cases.
model <- "
pri_con =~ PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07
grats_gen =~ GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05
pri_delib =~ PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05
self_eff =~ SE01_01 + SE01_02 + SE01_03 + SE01_04
SE01_01 ~~ x*SE01_02
SE01_03 ~~ x*SE01_04
trust_community =~ TR01_01 + TR01_02 + TR01_03
trust_provider =~ TR01_04 + TR01_05 + TR01_06
trust_system =~ TR01_07 + TR01_08 + TR01_09
trust_spec =~ trust_community + trust_provider + trust_system
words_log ~ a1*pri_con + b1*grats_gen + c1*pri_delib + d1*self_eff + e1*trust_spec
# Covariates
words_log + GR02_01 + GR02_02 + GR02_03 + GR02_04 + GR02_05 + PC01_01 + PC01_02 + PC01_04 + PC01_05 + PC01_06 + PC01_07 + TR01_01 + TR01_02 + TR01_03 + TR01_04 + TR01_05 + TR01_06 + TR01_07 + TR01_08 + TR01_09 + PD01_01 + PD01_02 + PD01_03 + PD01_04 + PD01_05 + SE01_01 + SE01_02 + SE01_03 + SE01_04 ~ male + age + edu
# Covariances
male ~~ age + edu
age ~~ edu
"
fit_prereg <- sem(model, data = d_all, estimator = "MLR", missing = "ML")
summary(fit_prereg, fit = TRUE, std = TRUE)lavaan 0.6.16.1845 ended normally after 343 iterations
Estimator ML
Optimization method NLMINB
Number of model parameters 208
Number of equality constraints 1
Number of observations 590
Number of missing patterns 5
Model Test User Model:
Standard Scaled
Test Statistic 1225.236 920.651
Degrees of freedom 387 387
P-value (Chi-square) 0.000 0.000
Scaling correction factor 1.331
Yuan-Bentler correction (Mplus variant)
Model Test Baseline Model:
Test statistic 14258.264 10500.309
Degrees of freedom 528 528
P-value 0.000 0.000
Scaling correction factor 1.358
User Model versus Baseline Model:
Comparative Fit Index (CFI) 0.939 0.946
Tucker-Lewis Index (TLI) 0.917 0.927
Robust Comparative Fit Index (CFI) 0.948
Robust Tucker-Lewis Index (TLI) 0.930
Loglikelihood and Information Criteria:
Loglikelihood user model (H0) -28885.372 -28885.372
Scaling correction factor 1.261
for the MLR correction
Loglikelihood unrestricted model (H1) -28272.754 -28272.754
Scaling correction factor 1.309
for the MLR correction
Akaike (AIC) 58184.745 58184.745
Bayesian (BIC) 59091.430 59091.430
Sample-size adjusted Bayesian (SABIC) 58434.273 58434.273
Root Mean Square Error of Approximation:
RMSEA 0.061 0.048
90 Percent confidence interval - lower 0.057 0.045
90 Percent confidence interval - upper 0.064 0.052
P-value H_0: RMSEA <= 0.050 0.000 0.779
P-value H_0: RMSEA >= 0.080 0.000 0.000
Robust RMSEA 0.055
90 Percent confidence interval - lower 0.051
90 Percent confidence interval - upper 0.060
P-value H_0: Robust RMSEA <= 0.050 0.029
P-value H_0: Robust RMSEA >= 0.080 0.000
Standardized Root Mean Square Residual:
SRMR 0.049 0.049
Parameter Estimates:
Standard errors Sandwich
Information bread Observed
Observed information based on Hessian
Latent Variables:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
pri_con =~
PC01_01 1.000 1.614 0.921
PC01_02 0.993 0.027 37.250 0.000 1.602 0.897
PC01_04 0.965 0.026 36.598 0.000 1.558 0.882
PC01_05 1.003 0.023 43.336 0.000 1.620 0.908
PC01_06 0.867 0.036 24.417 0.000 1.400 0.803
PC01_07 1.000 0.023 44.394 0.000 1.614 0.922
grats_gen =~
GR02_01 1.000 1.148 0.847
GR02_02 1.117 0.032 35.469 0.000 1.283 0.896
GR02_03 1.009 0.044 22.743 0.000 1.159 0.864
GR02_04 0.980 0.045 21.786 0.000 1.126 0.849
GR02_05 1.069 0.037 28.775 0.000 1.228 0.855
pri_delib =~
PD01_01 1.000 1.466 0.850
PD01_02 0.696 0.046 15.077 0.000 1.021 0.656
PD01_03 0.719 0.053 13.693 0.000 1.055 0.674
PD01_04 0.846 0.045 18.747 0.000 1.241 0.729
PD01_05 0.732 0.048 15.297 0.000 1.073 0.652
self_eff =~
SE01_01 1.000 1.140 0.816
SE01_02 0.841 0.054 15.666 0.000 0.959 0.700
SE01_03 0.927 0.042 22.086 0.000 1.056 0.783
SE01_04 0.930 0.040 22.998 0.000 1.060 0.776
trust_community =~
TR01_01 1.000 1.043 0.816
TR01_02 0.812 0.053 15.263 0.000 0.846 0.755
TR01_03 0.925 0.044 21.134 0.000 0.964 0.823
trust_provider =~
TR01_04 1.000 1.083 0.883
TR01_05 0.884 0.038 23.385 0.000 0.958 0.803
TR01_06 0.859 0.039 22.290 0.000 0.931 0.815
trust_system =~
TR01_07 1.000 0.781 0.658
TR01_08 1.119 0.096 11.602 0.000 0.874 0.674
TR01_09 1.444 0.101 14.345 0.000 1.128 0.838
trust_spec =~
trust_communty 1.000 0.866 0.866
trust_provider 1.126 0.075 14.995 0.000 0.938 0.938
trust_system 0.897 0.084 10.673 0.000 1.036 1.036
Regressions:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
words_log ~
pri_con (a1) -0.055 0.076 -0.722 0.471 -0.089 -0.039
grats_gen (b1) 0.012 0.146 0.085 0.933 0.014 0.006
pri_delib (c1) -0.166 0.092 -1.812 0.070 -0.244 -0.107
self_eff (d1) 0.773 0.137 5.634 0.000 0.881 0.386
trust_spc (e1) -0.169 0.235 -0.718 0.472 -0.152 -0.067
male 0.010 0.191 0.050 0.960 0.010 0.002
age 0.007 0.006 1.213 0.225 0.007 0.049
edu 0.195 0.113 1.728 0.084 0.195 0.072
GR02_01 ~
male -0.124 0.113 -1.101 0.271 -0.124 -0.046
age -0.001 0.004 -0.330 0.741 -0.001 -0.014
edu 0.003 0.067 0.044 0.965 0.003 0.002
GR02_02 ~
male -0.059 0.118 -0.496 0.620 -0.059 -0.020
age 0.004 0.004 1.001 0.317 0.004 0.043
edu -0.080 0.070 -1.147 0.252 -0.080 -0.047
GR02_03 ~
male -0.029 0.112 -0.262 0.793 -0.029 -0.011
age 0.001 0.004 0.189 0.850 0.001 0.008
edu -0.096 0.065 -1.477 0.140 -0.096 -0.060
GR02_04 ~
male 0.011 0.110 0.099 0.921 0.011 0.004
age 0.004 0.004 1.229 0.219 0.004 0.052
edu -0.087 0.066 -1.304 0.192 -0.087 -0.055
GR02_05 ~
male -0.135 0.120 -1.124 0.261 -0.135 -0.047
age -0.005 0.004 -1.196 0.232 -0.005 -0.051
edu 0.002 0.071 0.027 0.979 0.002 0.001
PC01_01 ~
male -0.116 0.148 -0.782 0.434 -0.116 -0.033
age -0.007 0.005 -1.521 0.128 -0.007 -0.065
edu 0.133 0.086 1.539 0.124 0.133 0.064
PC01_02 ~
male -0.257 0.150 -1.708 0.088 -0.257 -0.072
age -0.011 0.005 -2.348 0.019 -0.011 -0.098
edu 0.057 0.088 0.643 0.520 0.057 0.027
PC01_04 ~
male -0.190 0.148 -1.283 0.199 -0.190 -0.054
age -0.012 0.005 -2.452 0.014 -0.012 -0.102
edu 0.132 0.087 1.513 0.130 0.132 0.063
PC01_05 ~
male -0.057 0.150 -0.381 0.703 -0.057 -0.016
age -0.008 0.005 -1.730 0.084 -0.008 -0.073
edu 0.108 0.088 1.225 0.221 0.108 0.051
PC01_06 ~
male -0.100 0.147 -0.676 0.499 -0.100 -0.029
age -0.008 0.005 -1.686 0.092 -0.008 -0.071
edu 0.068 0.086 0.799 0.424 0.068 0.033
PC01_07 ~
male -0.145 0.147 -0.984 0.325 -0.145 -0.041
age -0.009 0.005 -1.922 0.055 -0.009 -0.081
edu 0.100 0.086 1.161 0.246 0.100 0.048
TR01_01 ~
male -0.274 0.106 -2.594 0.009 -0.274 -0.107
age -0.005 0.004 -1.330 0.184 -0.005 -0.057
edu 0.005 0.061 0.076 0.940 0.005 0.003
TR01_02 ~
male -0.151 0.094 -1.607 0.108 -0.151 -0.067
age -0.002 0.003 -0.519 0.604 -0.002 -0.023
edu 0.014 0.053 0.265 0.791 0.014 0.011
TR01_03 ~
male -0.116 0.098 -1.183 0.237 -0.116 -0.049
age -0.005 0.003 -1.431 0.152 -0.005 -0.063
edu -0.000 0.059 -0.000 1.000 -0.000 -0.000
TR01_04 ~
male -0.085 0.102 -0.831 0.406 -0.085 -0.035
age 0.000 0.003 0.101 0.919 0.000 0.004
edu -0.054 0.058 -0.920 0.357 -0.054 -0.037
TR01_05 ~
male -0.032 0.099 -0.319 0.749 -0.032 -0.013
age 0.001 0.003 0.235 0.814 0.001 0.010
edu 0.015 0.058 0.259 0.796 0.015 0.011
TR01_06 ~
male 0.048 0.095 0.501 0.616 0.048 0.021
age -0.004 0.003 -1.272 0.203 -0.004 -0.053
edu 0.013 0.056 0.227 0.820 0.013 0.009
TR01_07 ~
male 0.070 0.098 0.707 0.480 0.070 0.029
age -0.001 0.003 -0.304 0.762 -0.001 -0.013
edu -0.063 0.057 -1.088 0.276 -0.063 -0.044
TR01_08 ~
male 0.036 0.108 0.337 0.736 0.036 0.014
age 0.002 0.003 0.651 0.515 0.002 0.027
edu -0.092 0.064 -1.447 0.148 -0.092 -0.060
TR01_09 ~
male -0.116 0.111 -1.047 0.295 -0.116 -0.043
age -0.001 0.004 -0.346 0.730 -0.001 -0.015
edu -0.153 0.066 -2.302 0.021 -0.153 -0.095
PD01_01 ~
male -0.136 0.143 -0.956 0.339 -0.136 -0.040
age -0.018 0.005 -3.926 0.000 -0.018 -0.159
edu -0.021 0.082 -0.255 0.799 -0.021 -0.010
PD01_02 ~
male -0.102 0.129 -0.792 0.428 -0.102 -0.033
age -0.016 0.004 -4.086 0.000 -0.016 -0.164
edu 0.031 0.076 0.409 0.682 0.031 0.017
PD01_03 ~
male -0.294 0.129 -2.269 0.023 -0.294 -0.094
age -0.005 0.004 -1.278 0.201 -0.005 -0.053
edu 0.095 0.078 1.207 0.228 0.095 0.051
PD01_04 ~
male -0.393 0.139 -2.825 0.005 -0.393 -0.116
age -0.010 0.005 -2.237 0.025 -0.010 -0.094
edu 0.109 0.083 1.318 0.187 0.109 0.054
PD01_05 ~
male -0.184 0.137 -1.344 0.179 -0.184 -0.056
age -0.013 0.004 -3.127 0.002 -0.013 -0.126
edu -0.003 0.082 -0.036 0.971 -0.003 -0.001
SE01_01 ~
male 0.137 0.116 1.185 0.236 0.137 0.049
age 0.001 0.004 0.247 0.805 0.001 0.010
edu 0.207 0.067 3.092 0.002 0.207 0.125
SE01_02 ~
male 0.057 0.111 0.510 0.610 0.057 0.021
age -0.012 0.004 -3.203 0.001 -0.012 -0.131
edu 0.188 0.065 2.868 0.004 0.188 0.115
SE01_03 ~
male 0.211 0.112 1.883 0.060 0.211 0.078
age 0.001 0.004 0.376 0.707 0.001 0.016
edu 0.147 0.066 2.239 0.025 0.147 0.092
SE01_04 ~
male 0.060 0.113 0.534 0.593 0.060 0.022
age 0.006 0.004 1.559 0.119 0.006 0.064
edu 0.103 0.066 1.547 0.122 0.103 0.063
Covariances:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
.SE01_01 ~~
.SE01_02 (x) 0.101 0.043 2.327 0.020 0.101 0.136
.SE01_03 ~~
.SE01_04 (x) 0.101 0.043 2.327 0.020 0.101 0.145
male ~~
age 0.582 0.319 1.821 0.069 0.582 0.075
edu 0.054 0.017 3.149 0.002 0.054 0.129
age ~~
edu -1.173 0.534 -2.197 0.028 -1.173 -0.089
pri_con ~~
grats_gen -0.175 0.097 -1.814 0.070 -0.094 -0.094
pri_delib 1.380 0.128 10.754 0.000 0.583 0.583
self_eff -0.387 0.094 -4.139 0.000 -0.211 -0.211
trust_spec -0.359 0.071 -5.087 0.000 -0.247 -0.247
grats_gen ~~
pri_delib 0.028 0.101 0.279 0.780 0.017 0.017
self_eff 0.477 0.068 7.054 0.000 0.364 0.364
trust_spec 0.791 0.082 9.617 0.000 0.763 0.763
pri_delib ~~
self_eff -0.301 0.095 -3.152 0.002 -0.180 -0.180
trust_spec -0.087 0.080 -1.077 0.281 -0.065 -0.065
self_eff ~~
trust_spec 0.577 0.061 9.418 0.000 0.561 0.561
Intercepts:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
.PC01_01 3.498 0.285 12.262 0.000 3.498 1.996
.PC01_02 3.931 0.297 13.239 0.000 3.931 2.200
.PC01_04 3.664 0.288 12.717 0.000 3.664 2.074
.PC01_05 3.536 0.296 11.964 0.000 3.536 1.983
.PC01_06 3.363 0.282 11.916 0.000 3.363 1.928
.PC01_07 3.594 0.286 12.562 0.000 3.594 2.052
.GR02_01 4.412 0.221 19.925 0.000 4.412 3.255
.GR02_02 4.607 0.240 19.169 0.000 4.607 3.216
.GR02_03 5.283 0.218 24.244 0.000 5.283 3.941
.GR02_04 5.031 0.219 23.024 0.000 5.031 3.793
.GR02_05 4.978 0.247 20.124 0.000 4.978 3.464
.PD01_01 4.628 0.280 16.502 0.000 4.628 2.684
.PD01_02 4.156 0.243 17.087 0.000 4.156 2.672
.PD01_03 4.435 0.264 16.823 0.000 4.435 2.832
.PD01_04 4.565 0.286 15.986 0.000 4.565 2.683
.PD01_05 5.081 0.267 19.039 0.000 5.081 3.085
.SE01_01 4.739 0.242 19.554 0.000 4.739 3.390
.SE01_02 5.620 0.231 24.359 0.000 5.620 4.100
.SE01_03 4.751 0.220 21.629 0.000 4.751 3.524
.SE01_04 4.635 0.231 20.053 0.000 4.635 3.392
.TR01_01 5.089 0.215 23.712 0.000 5.089 3.982
.TR01_02 4.958 0.189 26.240 0.000 4.958 4.422
.TR01_03 4.880 0.199 24.579 0.000 4.880 4.163
.TR01_04 5.485 0.203 26.974 0.000 5.485 4.472
.TR01_05 5.119 0.199 25.747 0.000 5.119 4.291
.TR01_06 5.229 0.189 27.617 0.000 5.229 4.576
.TR01_07 5.814 0.190 30.580 0.000 5.814 4.897
.TR01_08 4.870 0.215 22.701 0.000 4.870 3.757
.TR01_09 5.562 0.227 24.468 0.000 5.562 4.132
.words_log 1.092 0.366 2.983 0.003 1.092 0.478
male 0.501 0.021 24.320 0.000 0.501 1.002
age 45.546 0.641 71.087 0.000 45.546 2.927
edu 1.869 0.035 53.888 0.000 1.869 2.219
pri_con 0.000 0.000 0.000
grats_gen 0.000 0.000 0.000
pri_delib 0.000 0.000 0.000
self_eff 0.000 0.000 0.000
.trust_communty 0.000 0.000 0.000
.trust_provider 0.000 0.000 0.000
.trust_system 0.000 0.000 0.000
trust_spec 0.000 0.000 0.000
Variances:
Estimate Std.Err z-value P(>|z|) Std.lv Std.all
.PC01_01 0.436 0.056 7.806 0.000 0.436 0.142
.PC01_02 0.571 0.097 5.868 0.000 0.571 0.179
.PC01_04 0.637 0.074 8.605 0.000 0.637 0.204
.PC01_05 0.528 0.061 8.714 0.000 0.528 0.166
.PC01_06 1.059 0.113 9.379 0.000 1.059 0.348
.PC01_07 0.427 0.063 6.808 0.000 0.427 0.139
.GR02_01 0.514 0.051 10.019 0.000 0.514 0.280
.GR02_02 0.395 0.039 10.042 0.000 0.395 0.192
.GR02_03 0.447 0.070 6.420 0.000 0.447 0.249
.GR02_04 0.482 0.046 10.501 0.000 0.482 0.274
.GR02_05 0.546 0.059 9.296 0.000 0.546 0.264
.PD01_01 0.740 0.107 6.934 0.000 0.740 0.249
.PD01_02 1.306 0.125 10.421 0.000 1.306 0.540
.PD01_03 1.305 0.123 10.595 0.000 1.305 0.532
.PD01_04 1.280 0.139 9.177 0.000 1.280 0.442
.PD01_05 1.507 0.122 12.323 0.000 1.507 0.556
.SE01_01 0.616 0.083 7.419 0.000 0.616 0.315
.SE01_02 0.896 0.114 7.854 0.000 0.896 0.477
.SE01_03 0.672 0.090 7.507 0.000 0.672 0.370
.SE01_04 0.727 0.085 8.536 0.000 0.727 0.389
.TR01_01 0.521 0.063 8.240 0.000 0.521 0.319
.TR01_02 0.534 0.062 8.573 0.000 0.534 0.425
.TR01_03 0.435 0.045 9.667 0.000 0.435 0.317
.TR01_04 0.326 0.034 9.681 0.000 0.326 0.217
.TR01_05 0.505 0.053 9.566 0.000 0.505 0.355
.TR01_06 0.434 0.042 10.438 0.000 0.434 0.333
.TR01_07 0.796 0.067 11.919 0.000 0.796 0.565
.TR01_08 0.909 0.076 11.880 0.000 0.909 0.541
.TR01_09 0.516 0.058 8.930 0.000 0.516 0.285
.words_log 4.329 0.208 20.776 0.000 4.329 0.830
male 0.250 0.000 4879.994 0.000 0.250 1.000
age 242.192 9.451 25.626 0.000 242.192 1.000
edu 0.710 0.020 36.106 0.000 0.710 1.000
pri_con 2.606 0.146 17.869 0.000 1.000 1.000
grats_gen 1.319 0.112 11.741 0.000 1.000 1.000
pri_delib 2.150 0.152 14.111 0.000 1.000 1.000
self_eff 1.299 0.113 11.489 0.000 1.000 1.000
.trust_communty 0.272 0.044 6.201 0.000 0.250 0.250
.trust_provider 0.141 0.043 3.252 0.001 0.121 0.121
.trust_system -0.045 0.022 -2.067 0.039 -0.074 -0.074
trust_spec 0.815 0.100 8.187 0.000 1.000 1.000First, we can see that the analyses now include the data of 590 participants. However, when comparing the analyses, we see that results don’t differ in any meaningful way.