Voice of the Voiceless Analysis
Corbin M. Walls
2025-06-12
Variables
| Name | Use | Description | Possible Values |
|---|---|---|---|
| improving | DV | Overall, has your life been improving in the last 6 months? | 1 = Not at all 2 = Not really 3 = Neutral 4 = Mostly, yes 5 = Yes, very much |
| feedback_aware | IV | Are you aware of any way to provide feedback or complaints about assistance? | 0 = No 1 = Yes |
| consulted | IV | In the last 6 months, have you been asked by a humanitarian organization what aid you need? | 0 = No 1 = Yes |
| fem | Control | Gender | 0 = Male 1 = Female |
| age | Control | Age | Numeric |
| hoh | Control | Head of household? | 0 = No 1 = Yes |
Descriptive Statistics
| Variable | Mean | Median | Standard Deviation | Minimum | Maximum |
|---|---|---|---|---|---|
| Improving | 4.14 | 5 | 1.22 | 1 | 5 |
| Community_Level_Improvements | 1.20 | 1 | 1.14 | 0 | 7 |
| Individual_Level_Improvements | 0.90 | 1 | 0.97 | 0 | 6 |
| Institutional_Level_Improvements | 1.26 | 1 | 0.79 | 0 | 5 |
| Age | 33.64 | 30 | 13.09 | 18 | 90 |
| Proportion in Sample | |
|---|---|
| Aware of Feedback | 0.56 |
| Consulted | 0.54 |
| Female | 0.51 |
| Head of Household | 0.62 |
OLS Models
Awareness of Voice Opportunities
model_1 <- lm(improving ~ feedback_aware + fem + age + hoh, data = ds)
model_2 <- lm(improving ~ consulted + fem + age + hoh, data = ds)
model_3 <- lm(improving ~ feedback_aware + consulted + fem + age + hoh, data = ds)modelsummary(
list(model_1, model_2, model_3),
title = "Awareness of Voice Opportunities",
stars = c("*" = 0.05,"**" = 0.01,"***" = 0.001),
statistic = c("std.error"),
coef_map = c(
"feedback_aware" = "Voice Opportunities Awareness",
"consulted" = "Consulted by Humanitarian Org",
"fem" = "Female",
"age" = "Age",
"hoh" = "Head of Household",
"(Intercept)" = "Constant"),
gof_omit = "AIC|BIC|Log.Lik.|RMSE",
output = "html")| (1) | (2) | (3) | |
|---|---|---|---|
| * p < 0.05, ** p < 0.01, *** p < 0.001 | |||
| Voice Opportunities Awareness | 0.401*** | 0.337*** | |
| (0.081) | (0.082) | ||
| Consulted by Humanitarian Org | 0.378*** | 0.311*** | |
| (0.082) | (0.083) | ||
| Female | 0.246** | 0.278** | 0.264** |
| (0.093) | (0.094) | (0.093) | |
| Age | 0.004 | 0.004 | 0.004 |
| (0.003) | (0.003) | (0.003) | |
| Head of Household | 0.403*** | 0.392*** | 0.370*** |
| (0.100) | (0.101) | (0.100) | |
| Constant | 3.403*** | 3.407*** | 3.274*** |
| (0.140) | (0.141) | (0.143) | |
| Num.Obs. | 875 | 874 | 874 |
| R2 | 0.055 | 0.052 | 0.070 |
| R2 Adj. | 0.050 | 0.048 | 0.065 |
| F | 12.605 | 11.998 | 13.121 |
Awareness of Different Voice Tools
model_4 <- lm(improving ~ feedback_typesaware_cmpln_box + feedback_typesaware_office_fic + feedback_typesaware_majhee + feedback_typesaware_leader + feedback_typesaware_ngo_staff + feedback_typesaware_gov_mil + feedback_typesaware_ngo_vol + feedback_typesaware_voice_rcrd + fem + age + hoh, data = ds)modelsummary(
list(model_4),
title = "Awareness of Different Voice Tools",
stars = c("*" = 0.05,"**" = 0.01,"***" = 0.001),
statistic = c("std.error"),
coef_map = c(
"feedback_typesaware_cmpln_box" = "Complaint or Feedback Box",
"feedback_typesaware_office_fic" = "Feedback at an Office",
"feedback_typesaware_majhee" = "Speak with Majhi",
"feedback_typesaware_leader" = "Community or Religious Leader",
"feedback_typesaware_ngo_staff" = "Speak with NGO Staff",
"feedback_typesaware_gov_mil" = "Government or Military",
"feedback_typesaware_ngo_vol" = "NGO Volunteer, Mobiliser",
"feedback_typesaware_voice_rcrd" = "Voice Recorder in Safe Space",
"fem" = "Female",
"age" = "Age",
"hoh" = "Head of Household",
"(Intercept)" = "Constant"),
gof_omit = "AIC|BIC|Log.Lik.|RMSE",
output = "html")| (1) | |
|---|---|
| * p < 0.05, ** p < 0.01, *** p < 0.001 | |
| Complaint or Feedback Box | 0.414 |
| (0.244) | |
| Feedback at an Office | −0.498** |
| (0.165) | |
| Speak with Majhi | 0.659** |
| (0.216) | |
| Community or Religious Leader | 0.062 |
| (0.114) | |
| Speak with NGO Staff | 0.117 |
| (0.101) | |
| Government or Military | 0.343*** |
| (0.098) | |
| NGO Volunteer, Mobiliser | 0.434** |
| (0.157) | |
| Voice Recorder in Safe Space | −0.433 |
| (1.078) | |
| Female | 0.507*** |
| (0.118) | |
| Age | 0.002 |
| (0.004) | |
| Head of Household | 0.325** |
| (0.125) | |
| Constant | 2.903*** |
| (0.269) | |
| Num.Obs. | 493 |
| R2 | 0.117 |
| R2 Adj. | 0.096 |
| F | 5.773 |
Barriers
model_6_competence <- lm(improving ~ feedback_aware + feedback_barriers_no_skills + feedback_aware*feedback_barriers_no_skills + fem + age + hoh, data = ds)
model_6_empowerment <- lm(improving ~ feedback_aware + feedback_barriers_afraid + feedback_aware*feedback_barriers_afraid + fem + age + hoh, data = ds)
model_6_trust <- lm(improving ~ feedback_aware + feedback_barriers_no_trust + feedback_aware*feedback_barriers_no_trust + fem + age + hoh, data = ds)
model_6_effectiveness <- lm(improving ~ feedback_aware + feedback_barriers_no_action + feedback_aware*feedback_barriers_no_action + fem + age + hoh, data = ds)
model_7_competence <- lm(improving ~ consulted + feedback_barriers_no_skills + consulted*feedback_barriers_no_skills + fem + age + hoh, data = ds)
model_7_empowerment <- lm(improving ~ consulted + feedback_barriers_afraid + consulted*feedback_barriers_afraid + fem + age + hoh, data = ds)
model_7_trust <- lm(improving ~ consulted + feedback_barriers_no_trust + consulted*feedback_barriers_no_trust + fem + age + hoh, data = ds)
model_7_effectiveness <- lm(improving ~ consulted + feedback_barriers_no_action + consulted*feedback_barriers_no_action + fem + age + hoh, data = ds)Overall, the barriers don’t have much of an effect, and they don’t change the effect that the other IVs have on the DV. In only 3 of the 8 models do the barriers have a significant relationship with perceptions of life improvements, and in two of these cases a barrier (that the refugees don’t think anything will change) actually has a positive relationship with the dv and in one case a barrier (that refugees don’t have the skills needed) has a negative relationship with the dv. In none of the models are the interaction terms significant.
I think it’s best to just leave these out.
Results for Types of Improvements
Factor analysis, MCA, and PCA all did not work very well with these variables. Accordingly, we will simply sum them within three categories: institutional, individual, and community improvements.
Community Level
model_8 <- lm(improve_community ~ feedback_aware + consulted + fem + age + hoh, data = ds)
summary(model_8)##
## Call:
## lm(formula = improve_community ~ feedback_aware + consulted +
## fem + age + hoh, data = ds)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5969 -0.7739 -0.1132 0.6877 5.4047
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.11322517 0.13436444 8.285 0.000000000000000445 ***
## feedback_aware 0.19881906 0.07726559 2.573 0.010242 *
## consulted 0.28391765 0.07756147 3.661 0.000267 ***
## fem -0.33744136 0.08702277 -3.878 0.000113 ***
## age -0.00008874 0.00299144 -0.030 0.976342
## hoh 0.00266294 0.09382531 0.028 0.977364
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.107 on 868 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.054, Adjusted R-squared: 0.04855
## F-statistic: 9.91 on 5 and 868 DF, p-value: 0.000000003127Individual Level
model_9 <- lm(improve_individual ~ feedback_aware + consulted + fem + age + hoh, data = ds)
summary(model_9)##
## Call:
## lm(formula = improve_individual ~ feedback_aware + consulted +
## fem + age + hoh, data = ds)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3676 -0.6027 -0.2200 0.4841 4.8185
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.148425 0.110969 10.349 < 0.0000000000000002 ***
## feedback_aware 0.065903 0.063812 1.033 0.302
## consulted 0.126837 0.064056 1.980 0.048 *
## fem -0.578133 0.071870 -8.044 0.00000000000000284 ***
## age -0.003436 0.002471 -1.391 0.165
## hoh 0.095175 0.077488 1.228 0.220
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9142 on 868 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.1152, Adjusted R-squared: 0.1101
## F-statistic: 22.6 on 5 and 868 DF, p-value: < 0.00000000000000022Institutional Level
model_10 <- lm(improve_institutional ~ feedback_aware + consulted + fem + age + hoh, data = ds)
summary(model_10)##
## Call:
## lm(formula = improve_institutional ~ feedback_aware + consulted +
## fem + age + hoh, data = ds)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5792 -0.4196 -0.1380 0.5949 3.4609
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.176989 0.092848 12.677 < 0.0000000000000002 ***
## feedback_aware 0.152354 0.053392 2.854 0.00443 **
## consulted 0.128558 0.053596 2.399 0.01667 *
## fem -0.266236 0.060134 -4.427 0.0000108 ***
## age 0.001146 0.002067 0.554 0.57958
## hoh 0.046828 0.064835 0.722 0.47033
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7649 on 868 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.05939, Adjusted R-squared: 0.05397
## F-statistic: 10.96 on 5 and 868 DF, p-value: 0.0000000003009stargazer(model_8, model_9, model_10, type = "text")##
## =========================================================================================
## Dependent variable:
## ----------------------------------------------------------
## improve_community improve_individual improve_institutional
## (1) (2) (3)
## -----------------------------------------------------------------------------------------
## feedback_aware 0.199** 0.066 0.152***
## (0.077) (0.064) (0.053)
##
## consulted 0.284*** 0.127** 0.129**
## (0.078) (0.064) (0.054)
##
## fem -0.337*** -0.578*** -0.266***
## (0.087) (0.072) (0.060)
##
## age -0.0001 -0.003 0.001
## (0.003) (0.002) (0.002)
##
## hoh 0.003 0.095 0.047
## (0.094) (0.077) (0.065)
##
## Constant 1.113*** 1.148*** 1.177***
## (0.134) (0.111) (0.093)
##
## -----------------------------------------------------------------------------------------
## Observations 874 874 874
## R2 0.054 0.115 0.059
## Adjusted R2 0.049 0.110 0.054
## Residual Std. Error (df = 868) 1.107 0.914 0.765
## F Statistic (df = 5; 868) 9.910*** 22.602*** 10.961***
## =========================================================================================
## Note: *p<0.1; **p<0.05; ***p<0.01Appendix
Proportions for Variables Used to Make Leveled Improvements
prop_table_aid_well <- ds %>%
summarize(
aid_well_improved_sanitation = mean(aid_well_improved_sanitation, na.rm = TRUE),
aid_well_clean_water = mean(aid_well_clean_water, na.rm = TRUE),
aid_well_ngo_training = mean(aid_well_ngo_training, na.rm = TRUE),
aid_well_prep_natural_disaster = mean(aid_well_prep_natural_disaster, na.rm = TRUE),
aid_well_more_safespaces_c = mean(aid_well_more_safespaces_c, na.rm = TRUE),
aid_well_more_safespaces_w = mean(aid_well_more_safespaces_w, na.rm = TRUE),
aid_well_better_relationships = mean(aid_well_better_relationships, na.rm = TRUE),
aid_well_psychosocial_support = mean(aid_well_psychosocial_support, na.rm = TRUE),
aid_well_collect_firewood = mean(aid_well_collect_firewood, na.rm = TRUE),
aid_well_diverse_food = mean(aid_well_diverse_food, na.rm = TRUE),
aid_well_employment_access = mean(aid_well_employment_access, na.rm = TRUE),
aid_well_community_groups = mean(aid_well_community_groups, na.rm = TRUE),
aid_well_more_learning = mean(aid_well_more_learning, na.rm = TRUE),
aid_well_id_card = mean(aid_well_id_card, na.rm = TRUE),
aid_well_stronger_shelter_mater = mean(aid_well_stronger_shelter_mater, na.rm = TRUE),
aid_well_health_services = mean(aid_well_health_services, na.rm = TRUE),
aid_well_aid_organised = mean(aid_well_aid_organised, na.rm = TRUE),
aid_well_structural_improvement = mean(aid_well_structural_improvement, na.rm = TRUE))
prop_table_aid_well <- t(prop_table_aid_well)
rownames(prop_table_aid_well) <- c("Improved Sanitation", "Clean Water", "NGO Training", "Natural Disaster Preparation", "More Safe Spaces for Children", "More Safe Spaces for Women", "Better Relationships", "Psychosocial Support", "Firewood Collection", "Food Diversity", "Employment Access", "Community Groups", "Learning Access", "ID Card", "Stronger Shelter Materials", "Health Services", "Aid More Organised", "Structural Improvements")
prop_table_aid_well %>%
kable(digits = 2, caption = "Proportions for Binary Variables", col.names = "Proportion in Sample", row.names = TRUE) %>%
kable_styling(full_width = TRUE)| Proportion in Sample | |
|---|---|
| Improved Sanitation | 0.46 |
| Clean Water | 0.30 |
| NGO Training | 0.20 |
| Natural Disaster Preparation | 0.09 |
| More Safe Spaces for Children | 0.10 |
| More Safe Spaces for Women | 0.04 |
| Better Relationships | 0.01 |
| Psychosocial Support | 0.07 |
| Firewood Collection | 0.41 |
| Food Diversity | 0.13 |
| Employment Access | 0.07 |
| Community Groups | 0.14 |
| Learning Access | 0.09 |
| ID Card | 0.03 |
| Stronger Shelter Materials | 0.27 |
| Health Services | 0.10 |
| Aid More Organised | 0.07 |
| Structural Improvements | 0.81 |
allprops_df <- data.frame(
Variable = rownames(prop_table_aid_well),
Proportion = as.numeric(prop_table_aid_well[, 1]))
datasummary_df(allprops_df,
title = "Proportions for Binary Variables",
fmt = 2,
output = "/Users/corbinwalls/Library/CloudStorage/OneDrive-american.edu/Graduate Assistantship/Voice in Refugee Camps/Analysis/Appendix A.docx")## NULLSUR models for Different Levels of Outcomes
ds$improve_individual_scaled <- scale(ds$improve_individual, center = FALSE)
ds$improve_community_scaled <- scale(ds$improve_community, center = FALSE)
ds$improve_institutional_scaled <- scale(ds$improve_institutional, center = FALSE)
indiv <- improve_individual_scaled ~ feedback_aware + consulted + fem + age + hoh
comm <- improve_community_scaled ~ feedback_aware + consulted + fem + age + hoh
inst <- improve_institutional_scaled ~ feedback_aware + consulted + fem + age + hoh
fitsur <- systemfit(list(indivreg = indiv, commreg= comm, instreg = inst), data = ds, method = "SUR")
summary(fitsur)##
## systemfit results
## method: SUR
##
## N DF SSR detRCov OLS-R2 McElroy-R2
## system 2622 2604 1031.41 0.04829 0.080666 0.05912
##
## N DF SSR MSE RMSE R2 Adj R2
## indivreg 874 868 413.543 0.476432 0.690241 0.115198 0.110101
## commreg 874 868 388.913 0.448057 0.669370 0.054003 0.048554
## instreg 874 868 228.951 0.263769 0.513584 0.059389 0.053971
##
## The covariance matrix of the residuals used for estimation
## indivreg commreg instreg
## indivreg 0.4764321 0.1152565 0.0627804
## commreg 0.1152565 0.4480565 0.0926173
## instreg 0.0627804 0.0926173 0.2637687
##
## The covariance matrix of the residuals
## indivreg commreg instreg
## indivreg 0.4764321 0.1152565 0.0627804
## commreg 0.1152565 0.4480565 0.0926173
## instreg 0.0627804 0.0926173 0.2637687
##
## The correlations of the residuals
## indivreg commreg instreg
## indivreg 1.000000 0.249459 0.177097
## commreg 0.249459 1.000000 0.269410
## instreg 0.177097 0.269410 1.000000
##
##
## SUR estimates for 'indivreg' (equation 1)
## Model Formula: improve_individual_scaled ~ feedback_aware + consulted + fem +
## age + hoh
##
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.86706646 0.08378208 10.34907 < 0.000000000000000222 ***
## feedback_aware 0.04975725 0.04817846 1.03277 0.301999
## consulted 0.09576286 0.04836295 1.98009 0.048009 *
## fem -0.43649306 0.05426249 -8.04410 0.0000000000000028866 ***
## age -0.00259389 0.00186529 -1.39060 0.164702
## hoh 0.07185787 0.05850417 1.22825 0.219685
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.690241 on 868 degrees of freedom
## Number of observations: 874 Degrees of Freedom: 868
## SSR: 413.543052 MSE: 0.476432 Root MSE: 0.690241
## Multiple R-Squared: 0.115198 Adjusted R-Squared: 0.110101
##
##
## SUR estimates for 'commreg' (equation 2)
## Model Formula: improve_community_scaled ~ feedback_aware + consulted + fem +
## age + hoh
##
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.6731559604 0.0812488133 8.28512 0.00000000000000044409 ***
## feedback_aware 0.1202238643 0.0467217177 2.57319 0.01024159 *
## consulted 0.1716821195 0.0469006354 3.66055 0.00026688 ***
## fem -0.2040473646 0.0526217879 -3.87762 0.00011345 ***
## age -0.0000536593 0.0018088939 -0.02966 0.97634172
## hoh 0.0016102512 0.0567352154 0.02838 0.97736411
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.66937 on 868 degrees of freedom
## Number of observations: 874 Degrees of Freedom: 868
## SSR: 388.913074 MSE: 0.448057 Root MSE: 0.66937
## Multiple R-Squared: 0.054003 Adjusted R-Squared: 0.048554
##
##
## SUR estimates for 'instreg' (equation 3)
## Model Formula: improve_institutional_scaled ~ feedback_aware + consulted + fem +
## age + hoh
##
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.790248205 0.062339351 12.67655 < 0.000000000000000222 ***
## feedback_aware 0.102292980 0.035847927 2.85353 0.0044266 **
## consulted 0.086315829 0.035985204 2.39865 0.0166658 *
## fem -0.178755227 0.040374843 -4.42739 0.000010754 ***
## age 0.000769181 0.001387901 0.55420 0.5795814
## hoh 0.031440730 0.043530931 0.72226 0.4703280
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.513584 on 868 degrees of freedom
## Number of observations: 874 Degrees of Freedom: 868
## SSR: 228.951261 MSE: 0.263769 Root MSE: 0.513584
## Multiple R-Squared: 0.059389 Adjusted R-Squared: 0.053971comm_indiv_feedback <- glht(fitsur,linfct = c("commreg_feedback_aware - indivreg_feedback_aware = 0"))
summary(comm_indiv_feedback) ##
## Simultaneous Tests for General Linear Hypotheses
##
## Fit: systemfit(formula = list(indivreg = indiv, commreg = comm, instreg = inst),
## method = "SUR", data = ds)
##
## Linear Hypotheses:
## Estimate Std. Error z value Pr(>|z|)
## commreg_feedback_aware - indivreg_feedback_aware == 0 0.07047 0.05815 1.212 0.226
## (Adjusted p values reported -- single-step method)inst_indiv_feedback <- glht(fitsur,linfct = c("instreg_feedback_aware - indivreg_feedback_aware = 0"))
summary(inst_indiv_feedback) ##
## Simultaneous Tests for General Linear Hypotheses
##
## Fit: systemfit(formula = list(indivreg = indiv, commreg = comm, instreg = inst),
## method = "SUR", data = ds)
##
## Linear Hypotheses:
## Estimate Std. Error z value Pr(>|z|)
## instreg_feedback_aware - indivreg_feedback_aware == 0 0.05254 0.05472 0.96 0.337
## (Adjusted p values reported -- single-step method)comm_inst_feedback <- glht(fitsur,linfct = c("commreg_feedback_aware - instreg_feedback_aware = 0"))
summary(comm_inst_feedback) ##
## Simultaneous Tests for General Linear Hypotheses
##
## Fit: systemfit(formula = list(indivreg = indiv, commreg = comm, instreg = inst),
## method = "SUR", data = ds)
##
## Linear Hypotheses:
## Estimate Std. Error z value Pr(>|z|)
## commreg_feedback_aware - instreg_feedback_aware == 0 0.01793 0.05065 0.354 0.723
## (Adjusted p values reported -- single-step method)comm_indiv_consulted <- glht(fitsur,linfct = c("commreg_consulted - indivreg_consulted = 0"))
summary(comm_indiv_consulted)##
## Simultaneous Tests for General Linear Hypotheses
##
## Fit: systemfit(formula = list(indivreg = indiv, commreg = comm, instreg = inst),
## method = "SUR", data = ds)
##
## Linear Hypotheses:
## Estimate Std. Error z value Pr(>|z|)
## commreg_consulted - indivreg_consulted == 0 0.07592 0.05837 1.301 0.193
## (Adjusted p values reported -- single-step method)inst_indiv_consulted <- glht(fitsur,linfct = c("instreg_consulted - indivreg_consulted = 0"))
summary(inst_indiv_consulted) ##
## Simultaneous Tests for General Linear Hypotheses
##
## Fit: systemfit(formula = list(indivreg = indiv, commreg = comm, instreg = inst),
## method = "SUR", data = ds)
##
## Linear Hypotheses:
## Estimate Std. Error z value Pr(>|z|)
## instreg_consulted - indivreg_consulted == 0 -0.009447 0.054932 -0.172 0.863
## (Adjusted p values reported -- single-step method)comm_inst_consulted <- glht(fitsur,linfct = c("commreg_consulted - instreg_consulted = 0"))
summary(comm_inst_consulted) # significant at alpha = 0.10##
## Simultaneous Tests for General Linear Hypotheses
##
## Fit: systemfit(formula = list(indivreg = indiv, commreg = comm, instreg = inst),
## method = "SUR", data = ds)
##
## Linear Hypotheses:
## Estimate Std. Error z value Pr(>|z|)
## commreg_consulted - instreg_consulted == 0 0.08537 0.05085 1.679 0.0932 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## (Adjusted p values reported -- single-step method)Mediation Analysis
Here, I will use the lavaan package and will estimate
the indirect effect via the product of coefficients approach. To test
for significance, I will use both the Sobel test and the percentile
based bootstrapping method.
Specify Path Analyses
mediation_path_1a <- "
# Path c' (direct effect)
improving ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_no_skills ~ a*feedback_aware + fem + age + hoh
# Path b
improving ~ b*feedback_barriers_no_skills + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_1b <- "
# Path c' (direct effect)
improving ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_afraid ~ a*feedback_aware + fem + age + hoh
# Path b
improving ~ b*feedback_barriers_afraid + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_1c <- "
# Path c' (direct effect)
improving ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_no_trust ~ a*feedback_aware + fem + age + hoh
# Path b
improving ~ b*feedback_barriers_no_trust + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_1d <- "
# Path c' (direct effect)
improving ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_no_action ~ a*feedback_aware + fem + age + hoh
# Path b
improving ~ b*feedback_barriers_no_action + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_2a <- "
# Path c' (direct effect)
improving ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_no_skills ~ a*consulted + fem + age + hoh
# Path b
improving ~ b*feedback_barriers_no_skills + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_2b <- "
# Path c' (direct effect)
improving ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_afraid ~ a*consulted + fem + age + hoh
# Path b
improving ~ b*feedback_barriers_afraid + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_2c <- "
# Path c' (direct effect)
improving ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_no_trust ~ a*consulted + fem + age + hoh
# Path b
improving ~ b*feedback_barriers_no_trust + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_2d <- "
# Path c' (direct effect)
improving ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_no_action ~ a*consulted + fem + age + hoh
# Path b
improving ~ b*feedback_barriers_no_action + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_3a <- "
# Path c' (direct effect)
improve_community ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_no_skills ~ a*feedback_aware + fem + age + hoh
# Path b
improve_community ~ b*feedback_barriers_no_skills + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_3b <- "
# Path c' (direct effect)
improve_community ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_afraid ~ a*feedback_aware + fem + age + hoh
# Path b
improve_community ~ b*feedback_barriers_afraid + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_3c <- "
# Path c' (direct effect)
improve_community ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_no_trust ~ a*feedback_aware + fem + age + hoh
# Path b
improve_community ~ b*feedback_barriers_no_trust + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_3d <- "
# Path c' (direct effect)
improve_community ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_no_action ~ a*feedback_aware + fem + age + hoh
# Path b
improve_community ~ b*feedback_barriers_no_action + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_4a <- "
# Path c' (direct effect)
improve_community ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_no_skills ~ a*consulted + fem + age + hoh
# Path b
improve_community ~ b*feedback_barriers_no_skills + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_4b <- "
# Path c' (direct effect)
improve_community ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_afraid ~ a*consulted + fem + age + hoh
# Path b
improve_community ~ b*feedback_barriers_afraid + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_4c <- "
# Path c' (direct effect)
improve_community ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_no_trust ~ a*consulted + fem + age + hoh
# Path b
improve_community ~ b*feedback_barriers_no_trust + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_4d <- "
# Path c' (direct effect)
improve_community ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_no_action ~ a*consulted + fem + age + hoh
# Path b
improve_community ~ b*feedback_barriers_no_action + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_5a <- "
# Path c' (direct effect)
improve_individual ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_no_skills ~ a*feedback_aware + fem + age + hoh
# Path b
improve_individual ~ b*feedback_barriers_no_skills + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_5b <- "
# Path c' (direct effect)
improve_individual ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_afraid ~ a*feedback_aware + fem + age + hoh
# Path b
improve_individual ~ b*feedback_barriers_afraid + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_5c <- "
# Path c' (direct effect)
improve_individual ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_no_trust ~ a*feedback_aware + fem + age + hoh
# Path b
improve_individual ~ b*feedback_barriers_no_trust + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_5d <- "
# Path c' (direct effect)
improve_individual ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_no_action ~ a*feedback_aware + fem + age + hoh
# Path b
improve_individual ~ b*feedback_barriers_no_action + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_6a <- "
# Path c' (direct effect)
improve_individual ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_no_skills ~ a*consulted + fem + age + hoh
# Path b
improve_individual ~ b*feedback_barriers_no_skills + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_6b <- "
# Path c' (direct effect)
improve_individual ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_afraid ~ a*consulted + fem + age + hoh
# Path b
improve_individual ~ b*feedback_barriers_afraid + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_6c <- "
# Path c' (direct effect)
improve_individual ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_no_trust ~ a*consulted + fem + age + hoh
# Path b
improve_individual ~ b*feedback_barriers_no_trust + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_6d <- "
# Path c' (direct effect)
improve_individual ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_no_action ~ a*consulted + fem + age + hoh
# Path b
improve_individual ~ b*feedback_barriers_no_action + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_7a <- "
# Path c' (direct effect)
improve_institutional ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_no_skills ~ a*feedback_aware + fem + age + hoh
# Path b
improve_institutional ~ b*feedback_barriers_no_skills + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_7b <- "
# Path c' (direct effect)
improve_institutional ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_afraid ~ a*feedback_aware + fem + age + hoh
# Path b
improve_institutional ~ b*feedback_barriers_afraid + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_7c <- "
# Path c' (direct effect)
improve_institutional ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_no_trust ~ a*feedback_aware + fem + age + hoh
# Path b
improve_institutional ~ b*feedback_barriers_no_trust + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_7d <- "
# Path c' (direct effect)
improve_institutional ~ c*feedback_aware + fem + age + hoh
# Path a
feedback_barriers_no_action ~ a*feedback_aware + fem + age + hoh
# Path b
improve_institutional ~ b*feedback_barriers_no_action + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_8a <- "
# Path c' (direct effect)
improve_institutional ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_no_skills ~ a*consulted + fem + age + hoh
# Path b
improve_institutional ~ b*feedback_barriers_no_skills + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_8b <- "
# Path c' (direct effect)
improve_institutional ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_afraid ~ a*consulted + fem + age + hoh
# Path b
improve_institutional ~ b*feedback_barriers_afraid + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_8c <- "
# Path c' (direct effect)
improve_institutional ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_no_trust ~ a*consulted + fem + age + hoh
# Path b
improve_institutional ~ b*feedback_barriers_no_trust + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"
mediation_path_8d <- "
# Path c' (direct effect)
improve_institutional ~ c*consulted + fem + age + hoh
# Path a
feedback_barriers_no_action ~ a*consulted + fem + age + hoh
# Path b
improve_institutional ~ b*feedback_barriers_no_action + fem + age + hoh
# Indirect Effect (a*b)
ab := a*b
"Fit Models
mediation_model_1a <- sem(mediation_path_1a, data = ds)
mediation_model_1b <- sem(mediation_path_1b, data = ds)
mediation_model_1c <- sem(mediation_path_1c, data = ds)## Warning: lavaan->lav_data_full():
## some observed variances are (at least) a factor 1000 times larger than others; use varTable(fit) to investigatemediation_model_1d <- sem(mediation_path_1d, data = ds)
mediation_model_2a <- sem(mediation_path_2a, data = ds)
mediation_model_2b <- sem(mediation_path_2b, data = ds)
mediation_model_2c <- sem(mediation_path_2c, data = ds)## Warning: lavaan->lav_data_full():
## some observed variances are (at least) a factor 1000 times larger than others; use varTable(fit) to investigatemediation_model_2d <- sem(mediation_path_2d, data = ds)
mediation_model_3a <- sem(mediation_path_3a, data = ds)
mediation_model_3b <- sem(mediation_path_3b, data = ds)
mediation_model_3c <- sem(mediation_path_3c, data = ds)## Warning: lavaan->lav_data_full():
## some observed variances are (at least) a factor 1000 times larger than others; use varTable(fit) to investigatemediation_model_3d <- sem(mediation_path_3d, data = ds)
mediation_model_4a <- sem(mediation_path_4a, data = ds)
mediation_model_4b <- sem(mediation_path_4b, data = ds)
mediation_model_4c <- sem(mediation_path_4c, data = ds)## Warning: lavaan->lav_data_full():
## some observed variances are (at least) a factor 1000 times larger than others; use varTable(fit) to investigatemediation_model_4d <- sem(mediation_path_4d, data = ds)
mediation_model_5a <- sem(mediation_path_5a, data = ds)
mediation_model_5b <- sem(mediation_path_5b, data = ds)
mediation_model_5c <- sem(mediation_path_5c, data = ds)
mediation_model_5d <- sem(mediation_path_5d, data = ds)
mediation_model_6a <- sem(mediation_path_6a, data = ds)
mediation_model_6b <- sem(mediation_path_6b, data = ds)
mediation_model_6c <- sem(mediation_path_6c, data = ds)
mediation_model_6d <- sem(mediation_path_6d, data = ds)
mediation_model_7a <- sem(mediation_path_7a, data = ds)
mediation_model_7b <- sem(mediation_path_7b, data = ds)
mediation_model_7c <- sem(mediation_path_7c, data = ds)
mediation_model_7d <- sem(mediation_path_7d, data = ds)
mediation_model_8a <- sem(mediation_path_8a, data = ds)
mediation_model_8b <- sem(mediation_path_8b, data = ds)
mediation_model_8c <- sem(mediation_path_8c, data = ds)
mediation_model_8d <- sem(mediation_path_8d, data = ds)Summarize Models
summary(mediation_model_1a, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 90.287
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1209.359
## Loglikelihood unrestricted model (H1) -1209.359
##
## Akaike (AIC) 2440.719
## Bayesian (BIC) 2493.235
## Sample-size adjusted Bayesian (SABIC) 2458.302
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improving ~
## feedbck_wr (c) 0.420 0.081 5.163 0.000
## fem 0.212 0.094 2.251 0.024
## age 0.004 0.003 1.196 0.232
## hoh 0.384 0.100 3.840 0.000
## feedback_barriers_no_skills ~
## feedbck_wr (a) -0.044 0.013 -3.234 0.001
## fem 0.079 0.015 5.123 0.000
## age 0.000 0.001 0.911 0.362
## hoh 0.046 0.017 2.748 0.006
## improving ~
## fdbck_br__ (b) 0.429 0.203 2.113 0.035
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improving 1.400 0.067 20.917 0.000
## .fdbck_brrrs_n_ 0.039 0.002 20.917 0.000
##
## R-Square:
## Estimate
## improving 0.060
## fdbck_brrrs_n_ 0.041
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.019 0.011 -1.769 0.077summary(mediation_model_1b, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 59.626
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -569.553
## Loglikelihood unrestricted model (H1) -569.553
##
## Akaike (AIC) 1161.106
## Bayesian (BIC) 1213.623
## Sample-size adjusted Bayesian (SABIC) 1178.689
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improving ~
## feedbck_wr (c) 0.400 0.081 4.936 0.000
## fem 0.241 0.093 2.589 0.010
## age 0.004 0.003 1.127 0.260
## hoh 0.407 0.100 4.085 0.000
## feedback_barriers_afraid ~
## feedbck_wr (a) 0.002 0.006 0.382 0.703
## fem 0.008 0.007 1.065 0.287
## age 0.001 0.000 2.401 0.016
## hoh -0.006 0.008 -0.694 0.488
## improving ~
## fdbck_brr_ (b) 0.672 0.423 1.590 0.112
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improving 1.404 0.067 20.917 0.000
## .fdbck_brrrs_fr 0.009 0.000 20.917 0.000
##
## R-Square:
## Estimate
## improving 0.058
## fdbck_brrrs_fr 0.009
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.002 0.004 0.371 0.710summary(mediation_model_1c, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 52.481
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) 333.112
## Loglikelihood unrestricted model (H1) 333.112
##
## Akaike (AIC) -644.224
## Bayesian (BIC) -591.708
## Sample-size adjusted Bayesian (SABIC) -626.641
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improving ~
## feedbck_wr (c) 0.402 0.081 4.955 0.000
## fem 0.245 0.093 2.638 0.008
## age 0.004 0.003 1.248 0.212
## hoh 0.404 0.100 4.047 0.000
## feedback_barriers_no_trust ~
## feedbck_wr (a) 0.002 0.002 0.845 0.398
## fem -0.002 0.003 -0.684 0.494
## age -0.000 0.000 -1.130 0.258
## hoh 0.002 0.003 0.550 0.582
## improving ~
## fdbck_br__ (b) -0.298 1.189 -0.250 0.802
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improving 1.407 0.067 20.917 0.000
## .fdbck_brrrs_n_ 0.001 0.000 20.917 0.000
##
## R-Square:
## Estimate
## improving 0.055
## fdbck_brrrs_n_ 0.004
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.001 0.002 -0.240 0.810summary(mediation_model_1d, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 65.112
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -892.020
## Loglikelihood unrestricted model (H1) -892.020
##
## Akaike (AIC) 1806.040
## Bayesian (BIC) 1858.556
## Sample-size adjusted Bayesian (SABIC) 1823.623
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improving ~
## feedbck_wr (c) 0.400 0.081 4.944 0.000
## fem 0.227 0.093 2.440 0.015
## age 0.004 0.003 1.218 0.223
## hoh 0.407 0.099 4.088 0.000
## feedback_barriers_no_action ~
## feedbck_wr (a) 0.003 0.009 0.269 0.788
## fem 0.028 0.011 2.557 0.011
## age 0.000 0.000 0.550 0.582
## hoh -0.005 0.012 -0.409 0.682
## improving ~
## fdbck_br__ (b) 0.685 0.291 2.352 0.019
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improving 1.399 0.067 20.917 0.000
## .fdbck_brrrs_n_ 0.019 0.001 20.917 0.000
##
## R-Square:
## Estimate
## improving 0.061
## fdbck_brrrs_n_ 0.012
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.002 0.006 0.267 0.789summary(mediation_model_2a, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 82.987
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1212.304
## Loglikelihood unrestricted model (H1) -1212.304
##
## Akaike (AIC) 2446.609
## Bayesian (BIC) 2499.113
## Sample-size adjusted Bayesian (SABIC) 2464.179
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improving ~
## consulted (c) 0.369 0.082 4.504 0.000
## fem 0.260 0.095 2.746 0.006
## age 0.004 0.003 1.304 0.192
## hoh 0.384 0.101 3.807 0.000
## feedback_barriers_no_skills ~
## consulted (a) 0.040 0.014 2.960 0.003
## fem 0.079 0.016 5.105 0.000
## age 0.001 0.001 0.984 0.325
## hoh 0.036 0.017 2.146 0.032
## improving ~
## fdbck_br__ (b) 0.223 0.203 1.094 0.274
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improving 1.410 0.067 20.905 0.000
## .fdbck_brrrs_n_ 0.039 0.002 20.905 0.000
##
## R-Square:
## Estimate
## improving 0.054
## fdbck_brrrs_n_ 0.039
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.009 0.009 1.027 0.305summary(mediation_model_2b, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 64.449
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -567.202
## Loglikelihood unrestricted model (H1) -567.202
##
## Akaike (AIC) 1156.405
## Bayesian (BIC) 1208.909
## Sample-size adjusted Bayesian (SABIC) 1173.975
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improving ~
## consulted (c) 0.368 0.082 4.498 0.000
## fem 0.273 0.093 2.926 0.003
## age 0.004 0.003 1.236 0.216
## hoh 0.396 0.101 3.936 0.000
## feedback_barriers_afraid ~
## consulted (a) 0.019 0.006 2.901 0.004
## fem 0.009 0.007 1.157 0.247
## age 0.001 0.000 2.470 0.013
## hoh -0.008 0.008 -1.011 0.312
## improving ~
## fdbck_brr_ (b) 0.513 0.426 1.204 0.228
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improving 1.410 0.067 20.905 0.000
## .fdbck_brrrs_fr 0.009 0.000 20.905 0.000
##
## R-Square:
## Estimate
## improving 0.054
## fdbck_brrrs_fr 0.018
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.010 0.009 1.112 0.266summary(mediation_model_2c, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 50.051
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) 330.796
## Loglikelihood unrestricted model (H1) 330.796
##
## Akaike (AIC) -639.592
## Bayesian (BIC) -587.089
## Sample-size adjusted Bayesian (SABIC) -622.022
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improving ~
## consulted (c) 0.379 0.082 4.638 0.000
## fem 0.277 0.093 2.968 0.003
## age 0.004 0.003 1.331 0.183
## hoh 0.392 0.101 3.898 0.000
## feedback_barriers_no_trust ~
## consulted (a) 0.002 0.002 0.780 0.436
## fem -0.002 0.003 -0.640 0.522
## age -0.000 0.000 -1.116 0.264
## hoh 0.001 0.003 0.512 0.609
## improving ~
## fdbck_br__ (b) -0.273 1.191 -0.229 0.819
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improving 1.412 0.068 20.905 0.000
## .fdbck_brrrs_n_ 0.001 0.000 20.905 0.000
##
## R-Square:
## Estimate
## improving 0.052
## fdbck_brrrs_n_ 0.003
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.000 0.002 -0.220 0.826summary(mediation_model_2d, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 75.127
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -886.697
## Loglikelihood unrestricted model (H1) -886.697
##
## Akaike (AIC) 1795.394
## Bayesian (BIC) 1847.897
## Sample-size adjusted Bayesian (SABIC) 1812.964
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improving ~
## consulted (c) 0.359 0.082 4.370 0.000
## fem 0.262 0.094 2.803 0.005
## age 0.004 0.003 1.304 0.192
## hoh 0.397 0.100 3.952 0.000
## feedback_barriers_no_action ~
## consulted (a) 0.036 0.009 3.848 0.000
## fem 0.029 0.011 2.684 0.007
## age 0.000 0.000 0.634 0.526
## hoh -0.010 0.012 -0.850 0.395
## improving ~
## fdbck_br__ (b) 0.533 0.295 1.808 0.071
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improving 1.407 0.067 20.905 0.000
## .fdbck_brrrs_n_ 0.019 0.001 20.905 0.000
##
## R-Square:
## Estimate
## improving 0.056
## fdbck_brrrs_n_ 0.028
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.019 0.012 1.637 0.102summary(mediation_model_3a, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 71.295
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1154.903
## Loglikelihood unrestricted model (H1) -1154.903
##
## Akaike (AIC) 2331.806
## Bayesian (BIC) 2384.323
## Sample-size adjusted Bayesian (SABIC) 2349.389
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_community ~
## feedbck_wr (c) 0.255 0.076 3.337 0.001
## fem -0.348 0.088 -3.929 0.000
## age -0.000 0.003 -0.113 0.910
## hoh 0.044 0.094 0.465 0.642
## feedback_barriers_no_skills ~
## feedbck_wr (a) -0.044 0.013 -3.234 0.001
## fem 0.079 0.015 5.123 0.000
## age 0.000 0.001 0.911 0.362
## hoh 0.046 0.017 2.748 0.006
## improve_community ~
## fdbck_br__ (b) 0.084 0.191 0.441 0.659
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_cmmnty 1.237 0.059 20.917 0.000
## .fdbck_brrrs_n_ 0.039 0.002 20.917 0.000
##
## R-Square:
## Estimate
## improve_cmmnty 0.039
## fdbck_brrrs_n_ 0.041
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.004 0.008 -0.437 0.662summary(mediation_model_3b, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 42.370
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -514.229
## Loglikelihood unrestricted model (H1) -514.229
##
## Akaike (AIC) 1050.458
## Bayesian (BIC) 1102.974
## Sample-size adjusted Bayesian (SABIC) 1068.041
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_community ~
## feedbck_wr (c) 0.252 0.076 3.308 0.001
## fem -0.341 0.087 -3.908 0.000
## age -0.000 0.003 -0.099 0.921
## hoh 0.047 0.094 0.507 0.612
## feedback_barriers_afraid ~
## feedbck_wr (a) 0.002 0.006 0.382 0.703
## fem 0.008 0.007 1.065 0.287
## age 0.001 0.000 2.401 0.016
## hoh -0.006 0.008 -0.694 0.488
## improve_community ~
## fdbck_brr_ (b) -0.002 0.397 -0.006 0.996
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_cmmnty 1.237 0.059 20.917 0.000
## .fdbck_brrrs_fr 0.009 0.000 20.917 0.000
##
## R-Square:
## Estimate
## improve_cmmnty 0.039
## fdbck_brrrs_fr 0.009
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.000 0.001 -0.006 0.996summary(mediation_model_3c, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 37.895
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) 389.771
## Loglikelihood unrestricted model (H1) 389.771
##
## Akaike (AIC) -757.542
## Bayesian (BIC) -705.026
## Sample-size adjusted Bayesian (SABIC) -739.959
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_community ~
## feedbck_wr (c) 0.253 0.076 3.321 0.001
## fem -0.342 0.087 -3.920 0.000
## age -0.000 0.003 -0.117 0.907
## hoh 0.048 0.094 0.516 0.606
## feedback_barriers_no_trust ~
## feedbck_wr (a) 0.002 0.002 0.845 0.398
## fem -0.002 0.003 -0.684 0.494
## age -0.000 0.000 -1.130 0.258
## hoh 0.002 0.003 0.550 0.582
## improve_community ~
## fdbck_br__ (b) -0.510 1.115 -0.457 0.647
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_cmmnty 1.236 0.059 20.917 0.000
## .fdbck_brrrs_n_ 0.001 0.000 20.917 0.000
##
## R-Square:
## Estimate
## improve_cmmnty 0.039
## fdbck_brrrs_n_ 0.004
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.001 0.002 -0.402 0.688summary(mediation_model_3d, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 45.020
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -838.114
## Loglikelihood unrestricted model (H1) -838.114
##
## Akaike (AIC) 1698.227
## Bayesian (BIC) 1750.744
## Sample-size adjusted Bayesian (SABIC) 1715.810
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_community ~
## feedbck_wr (c) 0.251 0.076 3.305 0.001
## fem -0.344 0.088 -3.930 0.000
## age -0.000 0.003 -0.107 0.915
## hoh 0.048 0.094 0.513 0.608
## feedback_barriers_no_action ~
## feedbck_wr (a) 0.003 0.009 0.269 0.788
## fem 0.028 0.011 2.557 0.011
## age 0.000 0.000 0.550 0.582
## hoh -0.005 0.012 -0.409 0.682
## improve_community ~
## fdbck_br__ (b) 0.108 0.274 0.396 0.692
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_cmmnty 1.237 0.059 20.917 0.000
## .fdbck_brrrs_n_ 0.019 0.001 20.917 0.000
##
## R-Square:
## Estimate
## improve_cmmnty 0.039
## fdbck_brrrs_n_ 0.012
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.000 0.001 0.222 0.824summary(mediation_model_4a, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 76.802
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1151.203
## Loglikelihood unrestricted model (H1) -1151.203
##
## Akaike (AIC) 2324.406
## Bayesian (BIC) 2376.910
## Sample-size adjusted Bayesian (SABIC) 2341.976
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_community ~
## consulted (c) 0.326 0.076 4.269 0.000
## fem -0.324 0.088 -3.672 0.000
## age -0.000 0.003 -0.017 0.987
## hoh 0.018 0.094 0.190 0.850
## feedback_barriers_no_skills ~
## consulted (a) 0.040 0.014 2.960 0.003
## fem 0.079 0.016 5.105 0.000
## age 0.001 0.001 0.984 0.325
## hoh 0.036 0.017 2.146 0.032
## improve_community ~
## fdbck_br__ (b) -0.065 0.190 -0.341 0.733
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_cmmnty 1.226 0.059 20.905 0.000
## .fdbck_brrrs_n_ 0.039 0.002 20.905 0.000
##
## R-Square:
## Estimate
## improve_cmmnty 0.047
## fdbck_brrrs_n_ 0.039
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.003 0.008 -0.339 0.735summary(mediation_model_4b, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 58.043
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -506.212
## Loglikelihood unrestricted model (H1) -506.212
##
## Akaike (AIC) 1034.425
## Bayesian (BIC) 1086.928
## Sample-size adjusted Bayesian (SABIC) 1051.995
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_community ~
## consulted (c) 0.326 0.076 4.273 0.000
## fem -0.328 0.087 -3.767 0.000
## age 0.000 0.003 0.004 0.997
## hoh 0.014 0.094 0.152 0.879
## feedback_barriers_afraid ~
## consulted (a) 0.019 0.006 2.901 0.004
## fem 0.009 0.007 1.157 0.247
## age 0.001 0.000 2.470 0.013
## hoh -0.008 0.008 -1.011 0.312
## improve_community ~
## fdbck_brr_ (b) -0.151 0.397 -0.382 0.703
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_cmmnty 1.226 0.059 20.905 0.000
## .fdbck_brrrs_fr 0.009 0.000 20.905 0.000
##
## R-Square:
## Estimate
## improve_cmmnty 0.047
## fdbck_brrrs_fr 0.018
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.003 0.008 -0.378 0.705summary(mediation_model_4c, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 45.124
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) 392.526
## Loglikelihood unrestricted model (H1) 392.526
##
## Akaike (AIC) -763.053
## Bayesian (BIC) -710.549
## Sample-size adjusted Bayesian (SABIC) -745.482
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_community ~
## consulted (c) 0.325 0.076 4.267 0.000
## fem -0.330 0.087 -3.795 0.000
## age -0.000 0.003 -0.046 0.963
## hoh 0.016 0.094 0.174 0.862
## feedback_barriers_no_trust ~
## consulted (a) 0.002 0.002 0.780 0.436
## fem -0.002 0.003 -0.640 0.522
## age -0.000 0.000 -1.116 0.264
## hoh 0.001 0.003 0.512 0.609
## improve_community ~
## fdbck_br__ (b) -0.531 1.110 -0.479 0.632
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_cmmnty 1.226 0.059 20.905 0.000
## .fdbck_brrrs_n_ 0.001 0.000 20.905 0.000
##
## R-Square:
## Estimate
## improve_cmmnty 0.047
## fdbck_brrrs_n_ 0.003
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.001 0.002 -0.408 0.683summary(mediation_model_4d, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 66.775
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -826.679
## Loglikelihood unrestricted model (H1) -826.679
##
## Akaike (AIC) 1675.358
## Bayesian (BIC) 1727.862
## Sample-size adjusted Bayesian (SABIC) 1692.929
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_community ~
## consulted (c) 0.325 0.077 4.236 0.000
## fem -0.328 0.087 -3.758 0.000
## age -0.000 0.003 -0.025 0.980
## hoh 0.015 0.094 0.162 0.872
## feedback_barriers_no_action ~
## consulted (a) 0.036 0.009 3.848 0.000
## fem 0.029 0.011 2.684 0.007
## age 0.000 0.000 0.634 0.526
## hoh -0.010 0.012 -0.850 0.395
## improve_community ~
## fdbck_br__ (b) -0.034 0.275 -0.125 0.901
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_cmmnty 1.226 0.059 20.905 0.000
## .fdbck_brrrs_n_ 0.019 0.001 20.905 0.000
##
## R-Square:
## Estimate
## improve_cmmnty 0.047
## fdbck_brrrs_n_ 0.028
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.001 0.010 -0.125 0.901summary(mediation_model_5a, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 141.049
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -981.332
## Loglikelihood unrestricted model (H1) -981.332
##
## Akaike (AIC) 1984.665
## Bayesian (BIC) 2037.181
## Sample-size adjusted Bayesian (SABIC) 2002.248
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_individual ~
## feedbck_wr (c) 0.082 0.063 1.315 0.188
## fem -0.567 0.073 -7.820 0.000
## age -0.003 0.002 -1.398 0.162
## hoh 0.121 0.077 1.571 0.116
## feedback_barriers_no_skills ~
## feedbck_wr (a) -0.044 0.013 -3.234 0.001
## fem 0.079 0.015 5.123 0.000
## age 0.000 0.001 0.911 0.362
## hoh 0.046 0.017 2.748 0.006
## improve_individual ~
## fdbck_br__ (b) -0.185 0.156 -1.183 0.237
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_indvdl 0.832 0.040 20.917 0.000
## .fdbck_brrrs_n_ 0.039 0.002 20.917 0.000
##
## R-Square:
## Estimate
## improve_indvdl 0.113
## fdbck_brrrs_n_ 0.041
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.008 0.007 1.111 0.266summary(mediation_model_5b, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 110.929
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -341.256
## Loglikelihood unrestricted model (H1) -341.256
##
## Akaike (AIC) 704.512
## Bayesian (BIC) 757.028
## Sample-size adjusted Bayesian (SABIC) 722.095
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_individual ~
## feedbck_wr (c) 0.090 0.062 1.450 0.147
## fem -0.582 0.072 -8.133 0.000
## age -0.004 0.002 -1.437 0.151
## hoh 0.113 0.077 1.468 0.142
## feedback_barriers_afraid ~
## feedbck_wr (a) 0.002 0.006 0.382 0.703
## fem 0.008 0.007 1.065 0.287
## age 0.001 0.000 2.401 0.016
## hoh -0.006 0.008 -0.694 0.488
## improve_individual ~
## fdbck_brr_ (b) 0.031 0.326 0.096 0.924
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_indvdl 0.833 0.040 20.917 0.000
## .fdbck_brrrs_fr 0.009 0.000 20.917 0.000
##
## R-Square:
## Estimate
## improve_indvdl 0.111
## fdbck_brrrs_fr 0.009
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.000 0.001 0.093 0.926summary(mediation_model_5c, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 106.360
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) 562.697
## Loglikelihood unrestricted model (H1) 562.697
##
## Akaike (AIC) -1103.395
## Bayesian (BIC) -1050.879
## Sample-size adjusted Bayesian (SABIC) -1085.812
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_individual ~
## feedbck_wr (c) 0.091 0.062 1.461 0.144
## fem -0.583 0.072 -8.142 0.000
## age -0.004 0.002 -1.446 0.148
## hoh 0.113 0.077 1.473 0.141
## feedback_barriers_no_trust ~
## feedbck_wr (a) 0.002 0.002 0.845 0.398
## fem -0.002 0.003 -0.684 0.494
## age -0.000 0.000 -1.130 0.258
## hoh 0.002 0.003 0.550 0.582
## improve_individual ~
## fdbck_br__ (b) -0.324 0.915 -0.354 0.723
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_indvdl 0.833 0.040 20.917 0.000
## .fdbck_brrrs_n_ 0.001 0.000 20.917 0.000
##
## R-Square:
## Estimate
## improve_indvdl 0.111
## fdbck_brrrs_n_ 0.004
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.001 0.002 -0.326 0.744summary(mediation_model_5d, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 114.738
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -664.561
## Loglikelihood unrestricted model (H1) -664.561
##
## Akaike (AIC) 1351.123
## Bayesian (BIC) 1403.639
## Sample-size adjusted Bayesian (SABIC) 1368.706
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_individual ~
## feedbck_wr (c) 0.091 0.062 1.463 0.144
## fem -0.575 0.072 -8.012 0.000
## age -0.003 0.002 -1.413 0.158
## hoh 0.111 0.077 1.452 0.147
## feedback_barriers_no_action ~
## feedbck_wr (a) 0.003 0.009 0.269 0.788
## fem 0.028 0.011 2.557 0.011
## age 0.000 0.000 0.550 0.582
## hoh -0.005 0.012 -0.409 0.682
## improve_individual ~
## fdbck_br__ (b) -0.259 0.225 -1.151 0.250
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_indvdl 0.832 0.040 20.917 0.000
## .fdbck_brrrs_n_ 0.019 0.001 20.917 0.000
##
## R-Square:
## Estimate
## improve_indvdl 0.113
## fdbck_brrrs_n_ 0.012
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.001 0.002 -0.262 0.793summary(mediation_model_6a, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 143.155
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -980.050
## Loglikelihood unrestricted model (H1) -980.050
##
## Akaike (AIC) 1982.100
## Bayesian (BIC) 2034.604
## Sample-size adjusted Bayesian (SABIC) 1999.670
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_individual ~
## consulted (c) 0.150 0.063 2.384 0.017
## fem -0.556 0.073 -7.662 0.000
## age -0.003 0.002 -1.343 0.179
## hoh 0.108 0.077 1.400 0.161
## feedback_barriers_no_skills ~
## consulted (a) 0.040 0.014 2.960 0.003
## fem 0.079 0.016 5.105 0.000
## age 0.001 0.001 0.984 0.325
## hoh 0.036 0.017 2.146 0.032
## improve_individual ~
## fdbck_br__ (b) -0.244 0.156 -1.567 0.117
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_indvdl 0.829 0.040 20.905 0.000
## .fdbck_brrrs_n_ 0.039 0.002 20.905 0.000
##
## R-Square:
## Estimate
## improve_indvdl 0.117
## fdbck_brrrs_n_ 0.039
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.010 0.007 -1.385 0.166summary(mediation_model_6b, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 121.925
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -336.294
## Loglikelihood unrestricted model (H1) -336.294
##
## Akaike (AIC) 694.588
## Bayesian (BIC) 747.092
## Sample-size adjusted Bayesian (SABIC) 712.159
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_individual ~
## consulted (c) 0.141 0.063 2.236 0.025
## fem -0.575 0.072 -8.024 0.000
## age -0.003 0.002 -1.380 0.167
## hoh 0.099 0.077 1.284 0.199
## feedback_barriers_afraid ~
## consulted (a) 0.019 0.006 2.901 0.004
## fem 0.009 0.007 1.157 0.247
## age 0.001 0.000 2.470 0.013
## hoh -0.008 0.008 -1.011 0.312
## improve_individual ~
## fdbck_brr_ (b) -0.034 0.327 -0.104 0.917
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_indvdl 0.831 0.040 20.905 0.000
## .fdbck_brrrs_fr 0.009 0.000 20.905 0.000
##
## R-Square:
## Estimate
## improve_indvdl 0.114
## fdbck_brrrs_fr 0.018
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.001 0.006 -0.104 0.917summary(mediation_model_6c, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 109.051
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) 562.467
## Loglikelihood unrestricted model (H1) 562.467
##
## Akaike (AIC) -1102.933
## Bayesian (BIC) -1050.429
## Sample-size adjusted Bayesian (SABIC) -1085.363
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_individual ~
## consulted (c) 0.141 0.063 2.245 0.025
## fem -0.576 0.072 -8.041 0.000
## age -0.003 0.002 -1.407 0.159
## hoh 0.100 0.077 1.295 0.195
## feedback_barriers_no_trust ~
## consulted (a) 0.002 0.002 0.780 0.436
## fem -0.002 0.003 -0.640 0.522
## age -0.000 0.000 -1.116 0.264
## hoh 0.001 0.003 0.512 0.609
## improve_individual ~
## fdbck_br__ (b) -0.340 0.914 -0.372 0.710
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_indvdl 0.831 0.040 20.905 0.000
## .fdbck_brrrs_n_ 0.001 0.000 20.905 0.000
##
## R-Square:
## Estimate
## improve_indvdl 0.114
## fdbck_brrrs_n_ 0.003
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.001 0.002 -0.336 0.737summary(mediation_model_6d, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 132.851
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -655.664
## Loglikelihood unrestricted model (H1) -655.664
##
## Akaike (AIC) 1333.329
## Bayesian (BIC) 1385.833
## Sample-size adjusted Bayesian (SABIC) 1350.899
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_individual ~
## consulted (c) 0.152 0.063 2.406 0.016
## fem -0.566 0.072 -7.881 0.000
## age -0.003 0.002 -1.364 0.172
## hoh 0.096 0.077 1.248 0.212
## feedback_barriers_no_action ~
## consulted (a) 0.036 0.009 3.848 0.000
## fem 0.029 0.011 2.684 0.007
## age 0.000 0.000 0.634 0.526
## hoh -0.010 0.012 -0.850 0.395
## improve_individual ~
## fdbck_br__ (b) -0.326 0.226 -1.441 0.150
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improve_indvdl 0.829 0.040 20.905 0.000
## .fdbck_brrrs_n_ 0.019 0.001 20.905 0.000
##
## R-Square:
## Estimate
## improve_indvdl 0.116
## fdbck_brrrs_n_ 0.028
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.012 0.009 -1.349 0.177summary(mediation_model_7a, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 99.287
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -819.883
## Loglikelihood unrestricted model (H1) -819.883
##
## Akaike (AIC) 1661.766
## Bayesian (BIC) 1714.283
## Sample-size adjusted Bayesian (SABIC) 1679.349
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_institutional ~
## feedbck_wr (c) 0.201 0.052 3.853 0.000
## fem -0.314 0.060 -5.200 0.000
## age 0.001 0.002 0.387 0.699
## hoh 0.037 0.064 0.582 0.561
## feedback_barriers_no_skills ~
## feedbck_wr (a) -0.044 0.013 -3.234 0.001
## fem 0.079 0.015 5.123 0.000
## age 0.000 0.001 0.911 0.362
## hoh 0.046 0.017 2.748 0.006
## improve_institutional ~
## fdbck_br__ (b) 0.500 0.130 3.841 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improv_nstttnl 0.575 0.027 20.917 0.000
## .fdbck_brrrs_n_ 0.039 0.002 20.917 0.000
##
## R-Square:
## Estimate
## improv_nstttnl 0.069
## fdbck_brrrs_n_ 0.041
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.022 0.009 -2.474 0.013summary(mediation_model_7b, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 58.303
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -185.238
## Loglikelihood unrestricted model (H1) -185.238
##
## Akaike (AIC) 392.476
## Bayesian (BIC) 444.992
## Sample-size adjusted Bayesian (SABIC) 410.059
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_institutional ~
## feedbck_wr (c) 0.178 0.052 3.412 0.001
## fem -0.277 0.060 -4.632 0.000
## age 0.001 0.002 0.376 0.707
## hoh 0.062 0.064 0.970 0.332
## feedback_barriers_afraid ~
## feedbck_wr (a) 0.002 0.006 0.382 0.703
## fem 0.008 0.007 1.065 0.287
## age 0.001 0.000 2.401 0.016
## hoh -0.006 0.008 -0.694 0.488
## improve_institutional ~
## fdbck_brr_ (b) 0.420 0.272 1.543 0.123
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improv_nstttnl 0.583 0.028 20.917 0.000
## .fdbck_brrrs_fr 0.009 0.000 20.917 0.000
##
## R-Square:
## Estimate
## improv_nstttnl 0.056
## fdbck_brrrs_fr 0.009
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.001 0.003 0.371 0.711summary(mediation_model_7c, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 51.685
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) 717.691
## Loglikelihood unrestricted model (H1) 717.691
##
## Akaike (AIC) -1413.381
## Bayesian (BIC) -1360.865
## Sample-size adjusted Bayesian (SABIC) -1395.798
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_institutional ~
## feedbck_wr (c) 0.178 0.052 3.408 0.001
## fem -0.273 0.060 -4.558 0.000
## age 0.001 0.002 0.527 0.598
## hoh 0.059 0.064 0.921 0.357
## feedback_barriers_no_trust ~
## feedbck_wr (a) 0.002 0.002 0.845 0.398
## fem -0.002 0.003 -0.684 0.494
## age -0.000 0.000 -1.130 0.258
## hoh 0.002 0.003 0.550 0.582
## improve_institutional ~
## fdbck_br__ (b) 0.510 0.766 0.665 0.506
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improv_nstttnl 0.584 0.028 20.917 0.000
## .fdbck_brrrs_n_ 0.001 0.000 20.917 0.000
##
## R-Square:
## Estimate
## improv_nstttnl 0.054
## fdbck_brrrs_n_ 0.004
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.001 0.002 0.522 0.601summary(mediation_model_7d, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 69.670
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -504.765
## Loglikelihood unrestricted model (H1) -504.765
##
## Akaike (AIC) 1031.529
## Bayesian (BIC) 1084.046
## Sample-size adjusted Bayesian (SABIC) 1049.112
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_institutional ~
## feedbck_wr (c) 0.178 0.052 3.419 0.001
## fem -0.291 0.060 -4.876 0.000
## age 0.001 0.002 0.442 0.658
## hoh 0.063 0.064 0.986 0.324
## feedback_barriers_no_action ~
## feedbck_wr (a) 0.003 0.009 0.269 0.788
## fem 0.028 0.011 2.557 0.011
## age 0.000 0.000 0.550 0.582
## hoh -0.005 0.012 -0.409 0.682
## improve_institutional ~
## fdbck_br__ (b) 0.630 0.187 3.365 0.001
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improv_nstttnl 0.577 0.028 20.917 0.000
## .fdbck_brrrs_n_ 0.019 0.001 20.917 0.000
##
## R-Square:
## Estimate
## improv_nstttnl 0.066
## fdbck_brrrs_n_ 0.012
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.002 0.006 0.268 0.789summary(mediation_model_8a, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 89.939
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -824.103
## Loglikelihood unrestricted model (H1) -824.103
##
## Akaike (AIC) 1670.207
## Bayesian (BIC) 1722.710
## Sample-size adjusted Bayesian (SABIC) 1687.777
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_institutional ~
## consulted (c) 0.143 0.053 2.712 0.007
## fem -0.292 0.061 -4.815 0.000
## age 0.001 0.002 0.454 0.650
## hoh 0.042 0.065 0.650 0.516
## feedback_barriers_no_skills ~
## consulted (a) 0.040 0.014 2.960 0.003
## fem 0.079 0.016 5.105 0.000
## age 0.001 0.001 0.984 0.325
## hoh 0.036 0.017 2.146 0.032
## improve_institutional ~
## fdbck_br__ (b) 0.409 0.131 3.136 0.002
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improv_nstttnl 0.580 0.028 20.905 0.000
## .fdbck_brrrs_n_ 0.039 0.002 20.905 0.000
##
## R-Square:
## Estimate
## improv_nstttnl 0.061
## fdbck_brrrs_n_ 0.039
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.016 0.008 2.153 0.031summary(mediation_model_8b, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 63.044
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -183.180
## Loglikelihood unrestricted model (H1) -183.180
##
## Akaike (AIC) 388.360
## Bayesian (BIC) 440.863
## Sample-size adjusted Bayesian (SABIC) 405.930
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_institutional ~
## consulted (c) 0.152 0.053 2.885 0.004
## fem -0.263 0.060 -4.372 0.000
## age 0.001 0.002 0.446 0.656
## hoh 0.060 0.065 0.919 0.358
## feedback_barriers_afraid ~
## consulted (a) 0.019 0.006 2.901 0.004
## fem 0.009 0.007 1.157 0.247
## age 0.001 0.000 2.470 0.013
## hoh -0.008 0.008 -1.011 0.312
## improve_institutional ~
## fdbck_brr_ (b) 0.355 0.274 1.295 0.195
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improv_nstttnl 0.585 0.028 20.905 0.000
## .fdbck_brrrs_fr 0.009 0.000 20.905 0.000
##
## R-Square:
## Estimate
## improv_nstttnl 0.052
## fdbck_brrrs_fr 0.018
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.007 0.006 1.183 0.237summary(mediation_model_8c, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 48.833
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) 714.912
## Loglikelihood unrestricted model (H1) 714.912
##
## Akaike (AIC) -1407.825
## Bayesian (BIC) -1355.321
## Sample-size adjusted Bayesian (SABIC) -1390.254
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_institutional ~
## consulted (c) 0.158 0.053 3.004 0.003
## fem -0.259 0.060 -4.306 0.000
## age 0.001 0.002 0.581 0.561
## hoh 0.056 0.065 0.862 0.389
## feedback_barriers_no_trust ~
## consulted (a) 0.002 0.002 0.780 0.436
## fem -0.002 0.003 -0.640 0.522
## age -0.000 0.000 -1.116 0.264
## hoh 0.001 0.003 0.512 0.609
## improve_institutional ~
## fdbck_br__ (b) 0.524 0.767 0.683 0.494
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improv_nstttnl 0.586 0.028 20.905 0.000
## .fdbck_brrrs_n_ 0.001 0.000 20.905 0.000
##
## R-Square:
## Estimate
## improv_nstttnl 0.051
## fdbck_brrrs_n_ 0.003
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.001 0.002 0.514 0.607summary(mediation_model_8d, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 79.308
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -499.881
## Loglikelihood unrestricted model (H1) -499.881
##
## Akaike (AIC) 1021.761
## Bayesian (BIC) 1074.265
## Sample-size adjusted Bayesian (SABIC) 1039.332
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_institutional ~
## consulted (c) 0.138 0.053 2.623 0.009
## fem -0.276 0.060 -4.599 0.000
## age 0.001 0.002 0.493 0.622
## hoh 0.062 0.065 0.965 0.334
## feedback_barriers_no_action ~
## consulted (a) 0.036 0.009 3.848 0.000
## fem 0.029 0.011 2.684 0.007
## age 0.000 0.000 0.634 0.526
## hoh -0.010 0.012 -0.850 0.395
## improve_institutional ~
## fdbck_br__ (b) 0.572 0.189 3.021 0.003
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improv_nstttnl 0.580 0.028 20.905 0.000
## .fdbck_brrrs_n_ 0.019 0.001 20.905 0.000
##
## R-Square:
## Estimate
## improv_nstttnl 0.060
## fdbck_brrrs_n_ 0.028
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.021 0.009 2.376 0.017summary(mediation_model_1a, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 90.287
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1209.359
## Loglikelihood unrestricted model (H1) -1209.359
##
## Akaike (AIC) 2440.719
## Bayesian (BIC) 2493.235
## Sample-size adjusted Bayesian (SABIC) 2458.302
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improving ~
## feedbck_wr (c) 0.420 0.081 5.163 0.000
## fem 0.212 0.094 2.251 0.024
## age 0.004 0.003 1.196 0.232
## hoh 0.384 0.100 3.840 0.000
## feedback_barriers_no_skills ~
## feedbck_wr (a) -0.044 0.013 -3.234 0.001
## fem 0.079 0.015 5.123 0.000
## age 0.000 0.001 0.911 0.362
## hoh 0.046 0.017 2.748 0.006
## improving ~
## fdbck_br__ (b) 0.429 0.203 2.113 0.035
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improving 1.400 0.067 20.917 0.000
## .fdbck_brrrs_n_ 0.039 0.002 20.917 0.000
##
## R-Square:
## Estimate
## improving 0.060
## fdbck_brrrs_n_ 0.041
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.019 0.011 -1.769 0.077summary(mediation_model_7a, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 875 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 99.287
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -819.883
## Loglikelihood unrestricted model (H1) -819.883
##
## Akaike (AIC) 1661.766
## Bayesian (BIC) 1714.283
## Sample-size adjusted Bayesian (SABIC) 1679.349
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_institutional ~
## feedbck_wr (c) 0.201 0.052 3.853 0.000
## fem -0.314 0.060 -5.200 0.000
## age 0.001 0.002 0.387 0.699
## hoh 0.037 0.064 0.582 0.561
## feedback_barriers_no_skills ~
## feedbck_wr (a) -0.044 0.013 -3.234 0.001
## fem 0.079 0.015 5.123 0.000
## age 0.000 0.001 0.911 0.362
## hoh 0.046 0.017 2.748 0.006
## improve_institutional ~
## fdbck_br__ (b) 0.500 0.130 3.841 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improv_nstttnl 0.575 0.027 20.917 0.000
## .fdbck_brrrs_n_ 0.039 0.002 20.917 0.000
##
## R-Square:
## Estimate
## improv_nstttnl 0.069
## fdbck_brrrs_n_ 0.041
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab -0.022 0.009 -2.474 0.013summary(mediation_model_8a, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 89.939
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -824.103
## Loglikelihood unrestricted model (H1) -824.103
##
## Akaike (AIC) 1670.207
## Bayesian (BIC) 1722.710
## Sample-size adjusted Bayesian (SABIC) 1687.777
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_institutional ~
## consulted (c) 0.143 0.053 2.712 0.007
## fem -0.292 0.061 -4.815 0.000
## age 0.001 0.002 0.454 0.650
## hoh 0.042 0.065 0.650 0.516
## feedback_barriers_no_skills ~
## consulted (a) 0.040 0.014 2.960 0.003
## fem 0.079 0.016 5.105 0.000
## age 0.001 0.001 0.984 0.325
## hoh 0.036 0.017 2.146 0.032
## improve_institutional ~
## fdbck_br__ (b) 0.409 0.131 3.136 0.002
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improv_nstttnl 0.580 0.028 20.905 0.000
## .fdbck_brrrs_n_ 0.039 0.002 20.905 0.000
##
## R-Square:
## Estimate
## improv_nstttnl 0.061
## fdbck_brrrs_n_ 0.039
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.016 0.008 2.153 0.031summary(mediation_model_8d, fit.measures = TRUE, rsquare = TRUE)## lavaan 0.6-19 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 11
##
## Used Total
## Number of observations 874 876
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 79.308
## Degrees of freedom 9
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -499.881
## Loglikelihood unrestricted model (H1) -499.881
##
## Akaike (AIC) 1021.761
## Bayesian (BIC) 1074.265
## Sample-size adjusted Bayesian (SABIC) 1039.332
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## improve_institutional ~
## consulted (c) 0.138 0.053 2.623 0.009
## fem -0.276 0.060 -4.599 0.000
## age 0.001 0.002 0.493 0.622
## hoh 0.062 0.065 0.965 0.334
## feedback_barriers_no_action ~
## consulted (a) 0.036 0.009 3.848 0.000
## fem 0.029 0.011 2.684 0.007
## age 0.000 0.000 0.634 0.526
## hoh -0.010 0.012 -0.850 0.395
## improve_institutional ~
## fdbck_br__ (b) 0.572 0.189 3.021 0.003
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .improv_nstttnl 0.580 0.028 20.905 0.000
## .fdbck_brrrs_n_ 0.019 0.001 20.905 0.000
##
## R-Square:
## Estimate
## improv_nstttnl 0.060
## fdbck_brrrs_n_ 0.028
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.021 0.009 2.376 0.0177a, 8a, 8d