P3 Societal DN, relevant other DN, personal norm and circular behaviours
Isabel Pacheco
2026-01-15
Sample descriptives
Model variable descriptives
Mobility
Current mobility descriptives
# owning a car
prop.table(table(dEU$nocar_0))##
## 0 1
## 0.8322421 0.1677579prop.table(table(dEU$nocar_0, dEU$country), margin=2)##
## UK Germany Netherlands Italy Lithuania
## 0 0.7863248 0.8209091 0.8649399 0.8977999 0.7658730
## 1 0.2136752 0.1790909 0.1350601 0.1022001 0.2341270car_own <- dEU %>%
group_by(country, nocar) %>%
summarise(count = n(), .groups = 'drop') %>%
mutate(percentage = count / sum(count) * 100)
# Car sharing options
table(dEU$shar_avl_cl)##
## 0 1
## 4088 1563table(dEU$shar_avl_cy)##
## 0 2
## 5103 548table(dEU$shar_avl_in)##
## 0 3
## 4491 1160prop.table(table(dEU$shar_avl_cl))##
## 0 1
## 0.7234118 0.2765882prop.table(table(dEU$shar_avl_cy))##
## 0 2
## 0.90302601 0.09697399prop.table(table(dEU$shar_avl_in))##
## 0 3
## 0.7947266 0.2052734prop.table(table(dEU$shar_avl_cl, dEU$country), margin=2)##
## UK Germany Netherlands Italy Lithuania
## 0 0.7549858 0.7118182 0.7539315 0.7877928 0.5803571
## 1 0.2450142 0.2881818 0.2460685 0.2122072 0.4196429prop.table(table(dEU$shar_avl_cy, dEU$country), margin=2)##
## UK Germany Netherlands Italy Lithuania
## 0 0.86799620 0.92090909 0.92876966 0.88360539 0.91964286
## 2 0.13200380 0.07909091 0.07123034 0.11639461 0.08035714prop.table(table(dEU$shar_avl_in, dEU$country), margin=2)##
## UK Germany Netherlands Italy Lithuania
## 0 0.7141500 0.8836364 0.7243293 0.8466998 0.7847222
## 3 0.2858500 0.1163636 0.2756707 0.1533002 0.2152778# View the result
print(car_own)## # A tibble: 30 × 4
## country nocar count percentage
## <fct> <dbl> <int> <dbl>
## 1 UK 1 532 9.41
## 2 UK 2 242 4.28
## 3 UK 3 36 0.637
## 4 UK 4 12 0.212
## 5 UK 5 6 0.106
## 6 UK NA 225 3.98
## 7 Germany 1 582 10.3
## 8 Germany 2 271 4.80
## 9 Germany 3 37 0.655
## 10 Germany 4 8 0.142
## # ℹ 20 more rows# Summarize data: Count car ownership by country
summary_nocar <- dEU %>%
group_by(country, nocar) %>%
summarise(count = n(), .groups = "drop")
# Plot
ggplot(summary_nocar, aes(x = country, y = count, fill = factor(nocar))) +
geom_bar(stat = "identity", position = "dodge") + # Use "stack" for stacked bars
labs(title = "Car Ownership by Country",
x = "Country",
y = "Count",
fill = "Car Ownership") +
scale_fill_manual(values = c("lightblue", "darkgreen", "orange", "purple", "red"), labels = c("No car", "At least one car")) +
theme_minimal()
summary_nocar$nocar_factor <- factor(summary_nocar$nocar,
levels = c(0, 1),
labels = c("No car", "At least one car"))
# Now plot using the cleaned-up variable
ggplot(summary_nocar, aes(x = country, y = count, fill = nocar_factor)) +
geom_bar(stat = "identity", position = "dodge") +
labs(title = "Car Ownership by Country",
x = "Country",
y = "Count",
fill = "Car Ownership") +
scale_fill_manual(values = c("lightblue", "darkgreen")) +
theme_minimal()
Mobility model descriptives
#recode items
dEU$nocar <- 1 - dEU$nocar_0 # 0 = no car, 1 = car
table(dEU$nocar) / 5651##
## 0 1
## 0.1677579 0.8322421dEU$willcarless <- 8 - as.numeric(as.character(dEU$willnocar))
dEU$willcarshare <- 8 - as.numeric(as.character(dEU$wdshedcar)) #Would you get rid of your car if adequate car sharing was available?
##social norms
dEU$mob_imp <- 8 - as.numeric(as.character(dEU$mob_desc_imp)) #Most people important to me do not own a car.
dEU$mob_nat <- 8 - as.numeric(as.character(dEU$mob_desc_nat)) #In my country most people do not own a car.
# personal norms
dEU$mob_pn <- 8 - as.numeric(as.character(dEU$mob_pn1))
#overview over new variables
describe(dEU[, c("mob_nat", "mob_imp", "mob_pn", "willcarless", "willcarshare")]) #overall## vars n mean sd median trimmed mad min max range skew
## mob_nat 1 5651 2.63 1.62 2 2.42 1.48 1 7 6 0.83
## mob_imp 2 5651 2.58 1.75 2 2.32 1.48 1 7 6 0.94
## mob_pn 3 5651 3.05 1.88 3 2.85 2.97 1 7 6 0.54
## willcarless 4 4703 3.76 1.99 4 3.70 2.97 1 7 6 0.09
## willcarshare 5 2636 2.78 1.84 2 2.54 1.48 1 7 6 0.73
## kurtosis se
## mob_nat -0.09 0.02
## mob_imp -0.12 0.02
## mob_pn -0.79 0.03
## willcarless -1.17 0.03
## willcarshare -0.59 0.04describeBy(dEU[, c("mob_nat", "mob_imp", "mob_pn", "willcarless", "willcarshare")], group = dEU$country) #, mat = TRUE) #per country##
## Descriptive statistics by group
## group: UK
## vars n mean sd median trimmed mad min max range skew
## mob_nat 1 1053 2.83 1.68 2 2.63 1.48 1 7 6 0.69
## mob_imp 2 1053 2.71 1.84 2 2.45 1.48 1 7 6 0.85
## mob_pn 3 1053 3.16 2.01 3 2.96 2.97 1 7 6 0.52
## willcarless 4 828 3.60 2.02 4 3.50 2.97 1 7 6 0.24
## willcarshare 5 459 2.23 1.58 2 1.94 1.48 1 7 6 1.27
## kurtosis se
## mob_nat -0.33 0.05
## mob_imp -0.37 0.06
## mob_pn -0.96 0.06
## willcarless -1.15 0.07
## willcarshare 0.88 0.07
## ------------------------------------------------------------
## group: Germany
## vars n mean sd median trimmed mad min max range skew
## mob_nat 1 1100 2.42 1.57 2 2.19 1.48 1 7 6 0.94
## mob_imp 2 1100 2.43 1.76 2 2.13 1.48 1 7 6 1.06
## mob_pn 3 1100 2.88 1.93 2 2.66 1.48 1 7 6 0.62
## willcarless 4 903 3.61 1.99 4 3.53 2.97 1 7 6 0.06
## willcarshare 5 573 2.55 1.73 2 2.33 1.48 1 7 6 0.77
## kurtosis se
## mob_nat -0.02 0.05
## mob_imp 0.01 0.05
## mob_pn -0.88 0.06
## willcarless -1.26 0.07
## willcarshare -0.60 0.07
## ------------------------------------------------------------
## group: Netherlands
## vars n mean sd median trimmed mad min max range skew
## mob_nat 1 1081 2.49 1.51 2 2.29 1.48 1 7 6 0.91
## mob_imp 2 1081 2.29 1.63 2 1.99 1.48 1 7 6 1.26
## mob_pn 3 1081 2.60 1.71 2 2.36 1.48 1 7 6 0.86
## willcarless 4 935 3.26 1.87 3 3.11 2.97 1 7 6 0.38
## willcarshare 5 511 2.34 1.59 2 2.10 1.48 1 7 6 1.02
## kurtosis se
## mob_nat 0.17 0.05
## mob_imp 0.72 0.05
## mob_pn -0.19 0.05
## willcarless -0.94 0.06
## willcarshare 0.10 0.07
## ------------------------------------------------------------
## group: Italy
## vars n mean sd median trimmed mad min max range skew
## mob_nat 1 1409 2.60 1.60 2 2.40 1.48 1 7 6 0.82
## mob_imp 2 1409 2.69 1.70 2 2.47 1.48 1 7 6 0.83
## mob_pn 3 1409 3.20 1.75 3 3.06 1.48 1 7 6 0.41
## willcarless 4 1265 4.03 1.96 4 4.04 2.97 1 7 6 -0.03
## willcarshare 5 783 3.34 1.95 3 3.19 2.97 1 7 6 0.40
## kurtosis se
## mob_nat -0.14 0.04
## mob_imp -0.22 0.05
## mob_pn -0.70 0.05
## willcarless -1.16 0.06
## willcarshare -1.03 0.07
## ------------------------------------------------------------
## group: Lithuania
## vars n mean sd median trimmed mad min max range skew
## mob_nat 1 1008 2.85 1.72 3 2.63 1.48 1 7 6 0.76
## mob_imp 2 1008 2.78 1.79 2 2.54 1.48 1 7 6 0.76
## mob_pn 3 1008 3.38 1.93 3 3.23 2.97 1 7 6 0.35
## willcarless 4 772 4.27 1.95 4 4.34 2.97 1 7 6 -0.16
## willcarshare 5 310 3.36 1.99 3 3.22 2.97 1 7 6 0.32
## kurtosis se
## mob_nat -0.19 0.05
## mob_imp -0.41 0.06
## mob_pn -0.94 0.06
## willcarless -1.05 0.07
## willcarshare -1.10 0.11mean(dEU$willcarless[!is.na(dEU$willcarless) & !is.na(dEU$willcarshare)])## [1] 3.518209mean(dEU$willcarshare[!is.na(dEU$willcarless) & !is.na(dEU$willcarshare)])## [1] 2.784522## APA table
library(flextable)##
## Attaching package: 'flextable'## The following object is masked from 'package:papaja':
##
## theme_apa## The following object is masked from 'package:xtable':
##
## align## The following object is masked from 'package:expss':
##
## set_caption## The following object is masked from 'package:purrr':
##
## composelibrary(officer)
desc_mob <- describeBy(
dEU[, c("mob_nat", "mob_imp", "mob_pn", "willcarless", "willcarshare")],
group = dEU$country,
mat = TRUE)
# Keep only what's needed
desc_mob_clean <- desc_mob %>%
dplyr::select(group1, vars, mean, sd) %>%
mutate(
vars = factor(vars, labels = c("mob_nat", "mob_imp", "mob_pn", "willcarless", "willcarshare")),
mean = round(mean, 2),
sd = round(sd, 2)
)
# Create a label for each variable-country-stat combo
desc_mob_long <- desc_mob_clean %>%
pivot_longer(cols = c(mean, sd), names_to = "stat", values_to = "value") %>%
unite("country_stat", group1, stat, sep = "_") %>%
pivot_wider(names_from = country_stat, values_from = value)
ft_mob <- flextable(desc_mob_long) %>%
autofit() %>%
set_caption("Table XX\nMeans and standard deviations per variable and country")
read_docx() %>%
body_add_par("Table XX. Means and standard deviations per variable and country", style = "heading 1") %>%
body_add_flextable(ft_mob) %>%
print(target = "APA_table for mobility descriptives.docx")Figure with all means, sd per country and variable
dEU_mob <- subset(dEU, select = c("country", "mob_nat", "mob_imp", "mob_pn", "willcarless", "willcarshare"))
dEU_mob_long <- dEU_mob %>%
pivot_longer(-country, names_to = "variable", values_to = "value")
dEU_mob_long <- dEU_mob_long %>%
mutate(variable = factor(variable,
levels = c("willcarshare","willcarless", "mob_pn", "mob_imp", "mob_nat"),
labels = c("Willingness to be carless if car sharing", "Willingness to be carless if adequate alternatives", "Personal norms", "Relevant other DN", "Societal DN")))
#filter out NA variables
dEU_mob_long_clean <- dEU_mob_long %>%
filter(!is.na(value), !is.na(variable))
ggplot(dEU_mob_long_clean) +
aes(x = value, y = variable, colour = country, fill = country) +
stat_summary(fun = mean, geom = "point", size = 3, position = position_dodge(width = 0.5)) + # Mean as points
stat_summary(fun.data = mean_sdl, fun.args = list(mult = 1),
geom = "errorbar", width = 0.2, position = position_dodge(width = 0.5)) + # SD as error bars
scale_colour_manual(values = brewer.pal(n = 5, name = "Dark2")) +
scale_x_continuous(limits = c(0, 7), breaks = 0:7) +
labs(
x = "Means ± SD", # Rename x-axis
y = "Variables", # Rename y-axis
colour = "Country", # Rename colour legend
fill = "Country"
) +
theme_gray()
Violin figures per country and variable
Housing
Current living situation
describeBy(dEU$sqmtre, dEU$country)# -> Approximately how much living space (in square feet) does your current home have?##
## Descriptive statistics by group
## group: UK
## vars n mean sd median trimmed mad min max range skew kurtosis
## X1 1 1053 136.55 116.25 100 116.61 74.13 8 500 492 1.53 1.91
## se
## X1 3.58
## ------------------------------------------------------------
## group: Germany
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1100 97.07 45.97 89.5 92.33 43.74 10 500 490 1.7 7.41 1.39
## ------------------------------------------------------------
## group: Netherlands
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1081 114.53 65.88 100 106.55 48.93 10 500 490 2.23 8.72 2
## ------------------------------------------------------------
## group: Italy
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1409 107.4 57.43 96 98.46 35.58 12 500 488 2.67 11.11 1.53
## ------------------------------------------------------------
## group: Lithuania
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1008 80.28 57.91 60 69.53 29.65 10 500 490 2.51 8.77 1.82ggplot(dEU, aes(x = sqmtre)) +
geom_histogram(binwidth = 10, fill = "steelblue", color = "black") +
facet_wrap(~ country) +
theme_minimal() +
labs(title = "Histogram of sqmtre by Country", x = "Square Meters", y = "Count")
dEU$sqmtrepp <- dEU$sqmtre / dEU$hhsize
describe(dEU$sqmtrepp)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 5651 51.78 44.26 40 44.48 23.72 1.2 500 498.8 3.7 22.62 0.59desc_list <- describeBy(dEU$sqmtrepp, group = dEU$hhsize, mat = FALSE)
desc_table <- do.call(rbind, desc_list)
print(desc_table)## vars n mean sd median trimmed mad min max range skew kurtosis
## 1 1 1166 84.42 66.16 69.00 72.46 35.58 8.00 500.00 492.00 2.99 12.06
## 2 1 2212 53.64 35.83 46.45 48.02 21.43 5.00 250.00 245.00 2.65 10.02
## 3 1 1127 37.32 23.59 33.33 33.86 14.83 3.33 166.67 163.33 2.25 7.63
## 4 1 821 31.11 19.98 25.00 27.87 11.12 2.50 125.00 122.50 2.16 6.02
## 5 1 228 25.89 18.24 20.50 22.89 11.12 4.00 100.00 96.00 2.15 5.57
## 6 1 62 22.26 14.47 16.67 19.93 9.88 1.67 75.00 73.33 1.63 2.78
## 7 1 24 20.88 14.35 18.57 19.44 12.18 2.29 64.29 62.00 1.12 1.22
## 8 1 5 22.70 10.07 25.00 22.70 9.27 7.25 31.25 24.00 -0.49 -1.68
## 9 1 1 3.11 NA 3.11 3.11 0.00 3.11 3.11 0.00 NA NA
## 10 1 5 6.28 4.35 5.20 6.28 5.93 1.20 11.50 10.30 0.10 -2.07
## se
## 1 1.94
## 2 0.76
## 3 0.70
## 4 0.70
## 5 1.21
## 6 1.84
## 7 2.93
## 8 4.50
## 9 NA
## 10 1.95##Current shared spaces
#First we need to recode the values, as 0 for no and 1 for yes (instead of 4,5,6 depending on number of option):
#dEU$currshr_ki #for kitchen it is not necessary as kitchen was option n1
dEU <- dEU %>%
mutate(currshr_ba = replace(currshr_ba, currshr_ba > 0, 1))
dEU <- dEU %>%
mutate(currshr_bs = replace(currshr_bs, currshr_bs > 0, 1))
dEU <- dEU %>%
mutate(currshr_gn = replace(currshr_gn, currshr_gn > 0, 1))
dEU <- dEU %>%
mutate(currshr_ur = replace(currshr_ur, currshr_ur > 0, 1))
dEU <- dEU %>%
mutate(currshr_eh = replace(currshr_eh, currshr_eh > 0, 1))
#no spaces shared: 0 = not selected -> spaces are shared, 1 = spaces are not shared (so selected)
dEU <- dEU %>%
mutate(currshr_no = replace(currshr_no, currshr_no > 0, 1))
#I do not need this variable?
#sum of shared spaces
dEU$currshr <- rowSums(dEU [, c("currshr_ki", "currshr_ba", "currshr_bs", "currshr_gn", "currshr_ur", "currshr_eh")])
describe(dEU[, c("currshr_ki", "currshr_ba", "currshr_bs", "currshr_gn", "currshr_ur", "currshr_eh")])## vars n mean sd median trimmed mad min max range skew kurtosis
## currshr_ki 1 5651 0.08 0.27 0 0.00 0 0 1 1 3.07 7.40
## currshr_ba 2 5651 0.08 0.27 0 0.00 0 0 1 1 3.16 8.01
## currshr_bs 3 5651 0.08 0.27 0 0.00 0 0 1 1 3.04 7.24
## currshr_gn 4 5651 0.12 0.32 0 0.02 0 0 1 1 2.41 3.81
## currshr_ur 5 5651 0.06 0.24 0 0.00 0 0 1 1 3.72 11.83
## currshr_eh 6 5651 0.16 0.37 0 0.08 0 0 1 1 1.81 1.28
## se
## currshr_ki 0
## currshr_ba 0
## currshr_bs 0
## currshr_gn 0
## currshr_ur 0
## currshr_eh 0Housing model descriptives
#Willingness to downsize
dEU$willdown <- 8 - dEU$wudmv #To what extent would you be willing to live in a smaller home if one was readily available in your area?
describe(dEU$willdown)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 5651 3.24 2.03 3 3.05 2.97 1 7 6 0.42 -1.09 0.03describeBy(dEU$willdown, dEU$country)##
## Descriptive statistics by group
## group: UK
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1053 3.38 2.13 3 3.22 2.97 1 7 6 0.34 -1.25 0.07
## ------------------------------------------------------------
## group: Germany
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1100 3.27 2.01 3 3.12 2.97 1 7 6 0.33 -1.19 0.06
## ------------------------------------------------------------
## group: Netherlands
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1081 3.23 2.1 3 3.03 2.97 1 7 6 0.45 -1.15 0.06
## ------------------------------------------------------------
## group: Italy
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1409 3.32 1.95 3 3.17 2.97 1 7 6 0.37 -1.01 0.05
## ------------------------------------------------------------
## group: Lithuania
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1008 2.94 1.96 3 2.71 2.97 1 7 6 0.65 -0.73 0.06##Willingness for sharing living spaces: Where applicable, would you be willing to permanently share the following spaces with a non-family member (tenant, housemate, neighbour, or other)?
# Recode 90 to NA
dEU$wudshr_ki[dEU$wudshr_ki == 90] <- NA
dEU$wudshr_ba[dEU$wudshr_ba == 90] <- NA
dEU$wudshr_bs[dEU$wudshr_bs == 90] <- NA
dEU$wudshr_gn[dEU$wudshr_gn == 90] <- NA
dEU$wudshr_ur[dEU$wudshr_ur == 90] <- NA
dEU$wudshr_eh[dEU$wudshr_eh == 90] <- NA
#Recode so higher scores represent more willingness
dEU$willshare_ki <- 8 - dEU$wudshr_ki #not willing to very willing (higher scores = more willingness)
dEU$willshare_ba <- 8 - dEU$wudshr_ba # bathroom
dEU$willshare_bs <- 8 - dEU$wudshr_bs #basement
dEU$willshare_gn <- 8 - dEU$wudshr_gn #garden
dEU$willshare_ur <- 8 - dEU$wudshr_ur #utility room
dEU$willshare_eh <- 8 - dEU$wudshr_eh #entrance/hallway
dEU$build_nat <- 8 - dEU$build_desc_nat #In my country, most people live in a small home or share living spaces.
dEU$build_imp <- 8 - dEU$build_desc_imp #Most people important to me live in a small home or share living spaces.
dEU$build_pn <- 8 - dEU$build_pn1
describe(dEU$willshare_ki)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 5632 2.01 1.71 1 1.62 0 1 7 6 1.65 1.59 0.02describeBy(dEU$willshare_ki, dEU$country)##
## Descriptive statistics by group
## group: UK
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1050 2.07 1.84 1 1.65 0 1 7 6 1.59 1.2 0.06
## ------------------------------------------------------------
## group: Germany
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1099 1.91 1.64 1 1.53 0 1 7 6 1.71 1.69 0.05
## ------------------------------------------------------------
## group: Netherlands
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1075 1.8 1.59 1 1.39 0 1 7 6 2.04 3.1 0.05
## ------------------------------------------------------------
## group: Italy
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1408 2.11 1.69 1 1.75 0 1 7 6 1.5 1.23 0.04
## ------------------------------------------------------------
## group: Lithuania
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1000 2.16 1.77 1 1.78 0 1 7 6 1.49 1.18 0.06#one mean score for all rooms
dEU$willshare <- rowMeans(dEU [, c("willshare_ki", "willshare_ba", "willshare_bs", "willshare_gn", "willshare_ur", "willshare_eh")])
describe(dEU [, c("build_nat", "build_imp", "build_pn", "willdown", "willshare_ki")]) #overall ## vars n mean sd median trimmed mad min max range skew
## build_nat 1 5651 3.31 1.68 3 3.21 1.48 1 7 6 0.26
## build_imp 2 5651 2.86 1.74 3 2.66 1.48 1 7 6 0.62
## build_pn 3 5651 2.74 1.78 2 2.51 1.48 1 7 6 0.72
## willdown 4 5651 3.24 2.03 3 3.05 2.97 1 7 6 0.42
## willshare_ki 5 5632 2.01 1.71 1 1.62 0.00 1 7 6 1.65
## kurtosis se
## build_nat -0.68 0.02
## build_imp -0.55 0.02
## build_pn -0.54 0.02
## willdown -1.09 0.03
## willshare_ki 1.59 0.02describeBy(dEU [, c("build_nat", "build_imp", "build_pn", "willdown", "willshare_ki")], dEU$country) #per country##
## Descriptive statistics by group
## group: UK
## vars n mean sd median trimmed mad min max range skew
## build_nat 1 1053 3.71 1.72 4 3.67 1.48 1 7 6 0.07
## build_imp 2 1053 3.16 1.85 3 3.00 1.48 1 7 6 0.43
## build_pn 3 1053 3.00 1.90 3 2.79 2.97 1 7 6 0.57
## willdown 4 1053 3.38 2.13 3 3.22 2.97 1 7 6 0.34
## willshare_ki 5 1050 2.07 1.84 1 1.65 0.00 1 7 6 1.59
## kurtosis se
## build_nat -0.70 0.05
## build_imp -0.84 0.06
## build_pn -0.81 0.06
## willdown -1.25 0.07
## willshare_ki 1.20 0.06
## ------------------------------------------------------------
## group: Germany
## vars n mean sd median trimmed mad min max range skew
## build_nat 1 1100 3.29 1.68 3 3.19 1.48 1 7 6 0.19
## build_imp 2 1100 2.58 1.70 2 2.36 1.48 1 7 6 0.79
## build_pn 3 1100 2.54 1.75 2 2.29 1.48 1 7 6 0.85
## willdown 4 1100 3.27 2.01 3 3.12 2.97 1 7 6 0.33
## willshare_ki 5 1099 1.91 1.64 1 1.53 0.00 1 7 6 1.71
## kurtosis se
## build_nat -0.81 0.05
## build_imp -0.43 0.05
## build_pn -0.44 0.05
## willdown -1.19 0.06
## willshare_ki 1.69 0.05
## ------------------------------------------------------------
## group: Netherlands
## vars n mean sd median trimmed mad min max range skew
## build_nat 1 1081 2.99 1.53 3 2.90 1.48 1 7 6 0.34
## build_imp 2 1081 2.54 1.63 2 2.32 1.48 1 7 6 0.86
## build_pn 3 1081 2.44 1.65 2 2.19 1.48 1 7 6 0.92
## willdown 4 1081 3.23 2.10 3 3.03 2.97 1 7 6 0.45
## willshare_ki 5 1075 1.80 1.59 1 1.39 0.00 1 7 6 2.04
## kurtosis se
## build_nat -0.60 0.05
## build_imp -0.13 0.05
## build_pn -0.17 0.05
## willdown -1.15 0.06
## willshare_ki 3.10 0.05
## ------------------------------------------------------------
## group: Italy
## vars n mean sd median trimmed mad min max range skew
## build_nat 1 1409 3.39 1.63 4 3.30 1.48 1 7 6 0.22
## build_imp 2 1409 3.04 1.65 3 2.91 1.48 1 7 6 0.47
## build_pn 3 1409 2.88 1.74 3 2.67 1.48 1 7 6 0.64
## willdown 4 1409 3.32 1.95 3 3.17 2.97 1 7 6 0.37
## willshare_ki 5 1408 2.11 1.69 1 1.75 0.00 1 7 6 1.50
## kurtosis se
## build_nat -0.56 0.04
## build_imp -0.51 0.04
## build_pn -0.49 0.05
## willdown -1.01 0.05
## willshare_ki 1.23 0.04
## ------------------------------------------------------------
## group: Lithuania
## vars n mean sd median trimmed mad min max range skew
## build_nat 1 1008 3.13 1.76 3 2.98 1.48 1 7 6 0.45
## build_imp 2 1008 2.92 1.80 3 2.71 2.97 1 7 6 0.62
## build_pn 3 1008 2.79 1.80 2 2.58 1.48 1 7 6 0.63
## willdown 4 1008 2.94 1.96 3 2.71 2.97 1 7 6 0.65
## willshare_ki 5 1000 2.16 1.77 1 1.78 0.00 1 7 6 1.49
## kurtosis se
## build_nat -0.67 0.06
## build_imp -0.58 0.06
## build_pn -0.67 0.06
## willdown -0.73 0.06
## willshare_ki 1.18 0.06#Create table for APA
desc_build <- describeBy(
dEU[, c("build_nat", "build_imp", "build_pn", "willdown", "willshare_ki")],
group = dEU$country,
mat = TRUE
)
# Keep only what's needed
desc_build_clean <- desc_build %>%
dplyr::select(group1, vars, mean, sd) %>%
mutate(
vars = factor(vars, labels = c("build_nat", "build_imp", "build_pn", "willdown", "willshare_ki")),
mean = round(mean, 2),
sd = round(sd, 2)
)
# Create a label for each variable-country-stat combo
desc_build_long <- desc_build_clean %>%
pivot_longer(cols = c(mean, sd), names_to = "stat", values_to = "value") %>%
unite("country_stat", group1, stat, sep = "_") %>%
pivot_wider(names_from = country_stat, values_from = value)
ft_build <- flextable(desc_build_long) %>%
autofit() %>%
set_caption("Table XX\nMeans and standard deviations per variable and country")
read_docx() %>%
body_add_par("Table XX. Means and standard deviations per variable and country", style = "heading 1") %>%
body_add_flextable(ft_build) %>%
print(target = "APA_table for building descriptives per country.docx")Figure with all means, sd per country and variable
## Overview over variables
dEU_build <- subset(dEU, select = c("country", "build_nat", "build_imp", "build_pn", "willdown", "willshare_ki"))
# Reshape the data to long format
dEU_build_long <- dEU_build %>%
pivot_longer(-country, names_to = "variable", values_to = "value")
dEU_build_long$country <- as.factor(dEU_build_long$country)
dEU_build_long$variable <- as.factor(dEU_build_long$variable)
dEU_build_long <- dEU_build_long %>%
mutate(variable = factor(variable,
levels = c("willshare_ki","willdown", "build_pn", "build_imp", "build_nat"),
labels = c("Willingness to share the kitchen","Willingness to live smaller", "Personal norm", "Relevant other DN", "Societal DN")))
ggplot(dEU_build_long) +
aes(x = value, y = variable, colour = country, fill = country) +
stat_summary(fun = mean, geom = "point", size = 3, position = position_dodge(width = 0.5)) + # Mean as points
stat_summary(fun.data = mean_sdl, fun.args = list(mult = 1),
geom = "errorbar", width = 0.2, position = position_dodge(width = 0.5)) + # SD as error bars
scale_colour_manual(values = brewer.pal(n = 5, name = "Dark2")) +
scale_x_continuous(limits = c(0, 7), breaks = 0:7) +
labs(
x = "means ± SD", # Rename x-axis
y = "Variables", # Rename y-axis
colour = "country", # Rename colour legend
fill = "country"
) +
theme_gray()## Warning: Removed 19 rows containing non-finite outside the scale range
## (`stat_summary()`).
## Removed 19 rows containing non-finite outside the scale range
## (`stat_summary()`).
Circular citizenship behaviours
#recode variables so higher scores indicate higher willingness
dEU$gov <- 8 - dEU$ccb_gov
dEU$busi <- 8 - dEU$ccb_busi
dEU$cit <- 8 - dEU$ccb_cit
##social norms
dEU$ccb_nat <- 8 - dEU$ccb_desc_nat
dEU$ccb_imp <- 8 - dEU$ccb_desc_imp
dEU$ccb_pn <- 8 - dEU$ccb_pn
#overview
describe(dEU [, c("ccb_nat", "ccb_imp", "ccb_pn", "gov", "busi", "cit")]) #overall ## vars n mean sd median trimmed mad min max range skew kurtosis
## ccb_nat 1 5651 3.53 1.59 4 3.49 1.48 1 7 6 0.15 -0.53
## ccb_imp 2 5651 3.34 1.68 4 3.24 1.48 1 7 6 0.23 -0.74
## ccb_pn 3 5651 3.51 1.75 4 3.45 1.48 1 7 6 0.12 -0.88
## gov 4 5651 3.09 1.82 3 2.93 2.97 1 7 6 0.39 -0.91
## busi 5 5651 3.06 1.80 3 2.90 2.97 1 7 6 0.38 -0.90
## cit 6 5651 3.44 1.79 4 3.36 1.48 1 7 6 0.13 -0.96
## se
## ccb_nat 0.02
## ccb_imp 0.02
## ccb_pn 0.02
## gov 0.02
## busi 0.02
## cit 0.02describeBy(dEU [, c("ccb_nat", "ccb_imp", "ccb_pn", "gov", "busi", "cit")], dEU$country) #per country##
## Descriptive statistics by group
## group: UK
## vars n mean sd median trimmed mad min max range skew kurtosis
## ccb_nat 1 1053 3.76 1.67 4 3.73 1.48 1 7 6 0.12 -0.60
## ccb_imp 2 1053 3.44 1.78 4 3.34 1.48 1 7 6 0.27 -0.78
## ccb_pn 3 1053 3.59 1.88 4 3.52 2.97 1 7 6 0.12 -1.04
## gov 4 1053 3.29 1.94 3 3.14 2.97 1 7 6 0.34 -1.05
## busi 5 1053 3.15 1.94 3 2.98 2.97 1 7 6 0.42 -0.99
## cit 6 1053 3.60 1.89 4 3.53 2.97 1 7 6 0.11 -1.06
## se
## ccb_nat 0.05
## ccb_imp 0.05
## ccb_pn 0.06
## gov 0.06
## busi 0.06
## cit 0.06
## ------------------------------------------------------------
## group: Germany
## vars n mean sd median trimmed mad min max range skew kurtosis
## ccb_nat 1 1100 3.28 1.59 3 3.20 1.48 1 7 6 0.23 -0.68
## ccb_imp 2 1100 2.94 1.70 3 2.81 1.48 1 7 6 0.40 -0.90
## ccb_pn 3 1100 3.32 1.78 4 3.24 1.48 1 7 6 0.09 -1.14
## gov 4 1100 2.96 1.86 3 2.78 2.97 1 7 6 0.42 -1.10
## busi 5 1100 2.84 1.80 2 2.66 1.48 1 7 6 0.46 -1.08
## cit 6 1100 3.10 1.79 3 2.98 2.97 1 7 6 0.24 -1.15
## se
## ccb_nat 0.05
## ccb_imp 0.05
## ccb_pn 0.05
## gov 0.06
## busi 0.05
## cit 0.05
## ------------------------------------------------------------
## group: Netherlands
## vars n mean sd median trimmed mad min max range skew kurtosis
## ccb_nat 1 1081 3.26 1.47 3 3.22 1.48 1 7 6 0.12 -0.50
## ccb_imp 2 1081 3.06 1.56 3 2.98 1.48 1 7 6 0.26 -0.70
## ccb_pn 3 1081 3.16 1.66 3 3.06 1.48 1 7 6 0.24 -0.84
## gov 4 1081 2.50 1.63 2 2.29 1.48 1 7 6 0.74 -0.54
## busi 5 1081 2.54 1.62 2 2.35 1.48 1 7 6 0.68 -0.57
## cit 6 1081 2.75 1.63 2 2.61 1.48 1 7 6 0.46 -0.88
## se
## ccb_nat 0.04
## ccb_imp 0.05
## ccb_pn 0.05
## gov 0.05
## busi 0.05
## cit 0.05
## ------------------------------------------------------------
## group: Italy
## vars n mean sd median trimmed mad min max range skew kurtosis
## ccb_nat 1 1409 3.50 1.50 4 3.47 1.48 1 7 6 0.12 -0.47
## ccb_imp 2 1409 3.48 1.57 4 3.43 1.48 1 7 6 0.13 -0.62
## ccb_pn 3 1409 3.73 1.67 4 3.71 1.48 1 7 6 0.10 -0.75
## gov 4 1409 3.18 1.74 3 3.05 1.48 1 7 6 0.36 -0.82
## busi 5 1409 3.14 1.71 3 3.02 1.48 1 7 6 0.32 -0.81
## cit 6 1409 3.75 1.70 4 3.75 1.48 1 7 6 -0.06 -0.81
## se
## ccb_nat 0.04
## ccb_imp 0.04
## ccb_pn 0.04
## gov 0.05
## busi 0.05
## cit 0.05
## ------------------------------------------------------------
## group: Lithuania
## vars n mean sd median trimmed mad min max range skew kurtosis
## ccb_nat 1 1008 3.91 1.62 4 3.92 1.48 1 7 6 0.00 -0.49
## ccb_imp 2 1008 3.75 1.69 4 3.73 1.48 1 7 6 0.05 -0.66
## ccb_pn 3 1008 3.73 1.70 4 3.70 1.48 1 7 6 0.07 -0.68
## gov 4 1008 3.53 1.75 4 3.46 1.48 1 7 6 0.15 -0.75
## busi 5 1008 3.66 1.75 4 3.61 1.48 1 7 6 0.05 -0.78
## cit 6 1008 3.94 1.66 4 3.93 1.48 1 7 6 0.03 -0.57
## se
## ccb_nat 0.05
## ccb_imp 0.05
## ccb_pn 0.05
## gov 0.06
## busi 0.06
## cit 0.05#Create table for APA
desc_ccb <- describeBy(
dEU[, c("ccb_nat", "ccb_imp", "ccb_pn", "gov", "busi", "cit")],
group = dEU$country,
mat = TRUE
)
# Keep only what's needed
desc_ccb_clean <- desc_ccb %>%
dplyr::select(group1, vars, mean, sd) %>%
mutate(
vars = factor(vars, labels = c("ccb_nat", "ccb_imp", "ccb_pn", "gov", "busi", "cit")),
mean = round(mean, 2),
sd = round(sd, 2)
)
# Create a label for each variable-country-stat combo
desc_ccb_long <- desc_ccb_clean %>%
pivot_longer(cols = c(mean, sd), names_to = "stat", values_to = "value") %>%
unite("country_stat", group1, stat, sep = "_") %>%
pivot_wider(names_from = country_stat, values_from = value)
ft_ccb <- flextable(desc_ccb_long) %>%
autofit() %>%
set_caption("Table XX\nMeans and standard deviations per variable and country")
read_docx() %>%
body_add_par("Table XX. Means and standard deviations per variable and country", style = "heading 1") %>%
body_add_flextable(ft_ccb) %>%
print(target = "APA_table for CCB descriptives per coutnry.docx")Figure with overview of CCB variables’ means, SD
dEU_ccb <- subset(dEU, select = c("country", "ccb_nat", "ccb_imp", "ccb_pn", "gov", "busi", "cit"))
# Reshape the data to long format
dEU_ccb_long <- dEU_ccb %>%
pivot_longer(-country, names_to = "variable", values_to = "value")
dEU_ccb_long$country <- as.factor(dEU_ccb_long$country)
dEU_ccb_long$variable <- as.factor(dEU_ccb_long$variable)
dEU_ccb_long <- dEU_ccb_long %>%
mutate(variable = factor(variable,
levels = c("ccb_nat", "ccb_imp", "ccb_pn", "gov", "busi", "cit"),
labels = c("CCB @ other citizens", "CCB @ businesses", "CCB @ governments",
"Personal norms", "Relevant other DN", "Societal DN")))
ggplot(dEU_ccb_long) +
aes(x = value, y = variable, colour = country, fill = country) +
stat_summary(fun = mean, geom = "point", size = 3, position = position_dodge(width = 0.5)) + # Mean as points
stat_summary(fun.data = mean_sdl, fun.args = list(mult = 1),
geom = "errorbar", width = 0.2, position = position_dodge(width = 0.5)) + # SD as error bars
scale_colour_manual(values = brewer.pal(n = 5, name = "Dark2")) +
scale_x_continuous(limits = c(0, 7), breaks = 0:7) +
labs(
x = "Means ± SD", # Rename x-axis
y = "Variables", # Rename y-axis
colour = "Country", # Rename colour legend
fill = "Country"
) +
theme_gray()
Country differences for variables
First, we need to check whether there are significant differences in the social norms, personal norms, and behaviours for mobility between the countries. For that, we first run an anova to see whether there are significant differences, and, if so, look at the effect size.
Mobility
library(effectsize)##
## Attaching package: 'effectsize'## The following object is masked from 'package:xtable':
##
## display## The following object is masked from 'package:psych':
##
## philibrary(rstatix)##
## Attaching package: 'rstatix'## The following objects are masked from 'package:effectsize':
##
## cohens_d, eta_squared## The following object is masked from 'package:stats':
##
## filter# Descriptive norms on societal level
aov_mob_nat <- aov(mob_nat ~ country, data = dEU)
summary(aov_mob_nat)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 161 40.35 15.52 1.24e-12 ***
## Residuals 5646 14678 2.60
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_mob_nat) # = 0.01## country
## 0.01087566# Descriptive norms of relevant others
aov_mob_imp <- aov(mob_imp ~ country, data = dEU)
summary(aov_mob_imp)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 191 47.71 15.74 8.16e-13 ***
## Residuals 5646 17115 3.03
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_mob_imp) # = 0.01## country
## 0.01102768# Personal norms
aov_mob_pn <- aov(mob_pn ~ country, data = dEU)
summary(aov_mob_pn)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 406 101.52 29.3 <2e-16 ***
## Residuals 5646 19561 3.46
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_mob_pn) # = 0.02## country
## 0.02033698#refuse
aov_mob_r0 <- aov(willcarless ~ country, data = dEU)
summary(aov_mob_r0)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 571 142.85 37.26 <2e-16 ***
## Residuals 4698 18012 3.83
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 948 observations deleted due to missingnesseta_squared(aov_mob_r0) # = 0.03## country
## 0.03074698#rethink
aov_mob_r1 <- aov(willcarshare ~ country, data = dEU)
summary(aov_mob_r1)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 620 155.10 48.92 <2e-16 ***
## Residuals 2631 8341 3.17
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 3015 observations deleted due to missingnesseta_squared(aov_mob_r1) # = 0.07## country
## 0.0692266## post hoc tests
car::leveneTest(willcarshare ~ country, data = dEU) #not equal variance## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 4 21.858 < 2.2e-16 ***
## 2631
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1dEU |>
games_howell_test(willcarshare ~ country)## # A tibble: 10 × 8
## .y. group1 group2 estimate conf.low conf.high p.adj p.adj.signif
## * <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 willcarshare UK Germa… 0.323 0.0403 0.605 1.6 e- 2 *
## 2 willcarshare UK Nethe… 0.112 -0.167 0.390 8.08e- 1 ns
## 3 willcarshare UK Italy 1.11 0.835 1.39 4.37e-14 ****
## 4 willcarshare UK Lithu… 1.14 0.767 1.50 4.67e-10 ****
## 5 willcarshare Germany Nethe… -0.211 -0.486 0.0643 2.23e- 1 ns
## 6 willcarshare Germany Italy 0.790 0.515 1.06 0 ****
## 7 willcarshare Germany Lithu… 0.813 0.447 1.18 2.38e- 8 ****
## 8 willcarshare Nether… Italy 1.00 0.730 1.27 0 ****
## 9 willcarshare Nether… Lithu… 1.02 0.660 1.39 3.92e-10 ****
## 10 willcarshare Italy Lithu… 0.0235 -0.339 0.386 1 e+ 0 ns–> For all variables regarding mobility, there are significant country difference (based on the ANOVA). However, when looking at the effect sizes, they are all between 0.01 and 0.03, thus very small. Only the country differences for Rethink have an effect size of 0.07.
Housing
# Descriptive norms on societal level
aov_build_nat <- aov(build_nat ~ country, data = dEU)
summary(aov_build_nat)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 315 78.67 28.52 <2e-16 ***
## Residuals 5646 15574 2.76
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_build_nat) # = 0.02## country
## 0.01980525# Descriptive norms of relevant others
aov_build_imp <- aov(build_imp ~ country, data = dEU)
summary(aov_build_imp)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 343 85.71 28.91 <2e-16 ***
## Residuals 5646 16737 2.96
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_build_imp) # = 0.02## country
## 0.02007249# Personal norms
aov_build_pn <- aov(build_pn ~ country, data = dEU)
summary(aov_build_pn)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 243 60.76 19.41 7.04e-16 ***
## Residuals 5646 17672 3.13
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_build_pn) # = 0.01## country
## 0.01356646#reduce
aov_build_r2 <- aov(willdown ~ country, data = dEU)
summary(aov_build_r2)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 117 29.337 7.143 9.85e-06 ***
## Residuals 5646 23188 4.107
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_build_r2) # = 0.00## country
## 0.005035155#rethink
aov_build_r1 <- aov(willshare_ki ~ country, data = dEU)
summary(aov_build_r1)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 100 24.973 8.616 6.28e-07 ***
## Residuals 5627 16310 2.899
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 19 observations deleted due to missingnesseta_squared(aov_build_r1) # = 0.00## country
## 0.006087226–> The influence of country on the variables is very small (effect sizes between 0.00 and 0.02). We therefore assume no country differences.
CCB
# Descriptive norms on societal level
aov_ccb_nat <- aov(ccb_nat ~ country, data = dEU)
summary(aov_ccb_nat)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 356 88.92 36.19 <2e-16 ***
## Residuals 5646 13873 2.46
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_ccb_nat) # = 0.02## country
## 0.02499704# Descriptive norms of relevant others
aov_ccb_imp <- aov(ccb_imp ~ country, data = dEU)
summary(aov_ccb_imp)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 462 115.59 42.2 <2e-16 ***
## Residuals 5646 15466 2.74
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_ccb_imp) # = 0.03## country
## 0.02902733# Personal norms
aov_ccb_pn <- aov(ccb_pn ~ country, data = dEU)
summary(aov_ccb_pn)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 296 74.04 24.53 <2e-16 ***
## Residuals 5646 17040 3.02
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_ccb_pn) # = 0.02## country
## 0.01708388#governments
aov_gov <- aov(gov ~ country, data = dEU)
summary(aov_gov)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 648 161.97 50.84 <2e-16 ***
## Residuals 5646 17990 3.19
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_gov) # = 0.03## country
## 0.0347626#businesses
aov_busi <- aov(busi ~ country, data = dEU)
summary(aov_busi)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 719 179.79 57.83 <2e-16 ***
## Residuals 5646 17552 3.11
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_busi) # = 0.04## country
## 0.03936066#other citizens
aov_cit <- aov(cit ~ country, data = dEU)
summary(aov_cit)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 1050 262.60 87.14 <2e-16 ***
## Residuals 5646 17015 3.01
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov_cit) # = 0.06## country
## 0.05814637## post hoc tests
car::leveneTest(cit ~ country, data = dEU) #not equal variance## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 4 18.574 3.533e-15 ***
## 5646
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1dEU |>
games_howell_test(cit ~ country)## # A tibble: 10 × 8
## .y. group1 group2 estimate conf.low conf.high p.adj p.adj.signif
## * <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 cit UK Germany -0.498 -0.715 -0.280 4.84e- 9 ****
## 2 cit UK Netherla… -0.848 -1.06 -0.639 5.89e-11 ****
## 3 cit UK Italy 0.152 -0.0499 0.353 2.41e- 1 ns
## 4 cit UK Lithuania 0.337 0.123 0.551 1.72e- 4 ***
## 5 cit Germany Netherla… -0.351 -0.551 -0.150 1.83e- 5 ****
## 6 cit Germany Italy 0.649 0.457 0.842 2.79e-11 ****
## 7 cit Germany Lithuania 0.835 0.629 1.04 6.22e-11 ****
## 8 cit Netherlands Italy 1.000 0.817 1.18 0 ****
## 9 cit Netherlands Lithuania 1.19 0.989 1.38 5.89e-11 ****
## 10 cit Italy Lithuania 0.186 -0.00319 0.375 5.7 e- 2 ns–> The country influences on CCB variables are relatively small (effect sizes around 0.02, 0.03). For CCB aimed at businesses the effect size is 0.04, for CCBs aimed at other citizens 0.06. –> Therefore, there are slight country differences.
Correlation tables
dUK <- subset(dEU, (country == "UK"))
dGER <- subset(dEU, (country == "Germany"))
dNL <- subset(dEU, (country == "Netherlands"))
dIT <- subset(dEU, (country == "Italy"))
dLIT <- subset(dEU, (country == "Lithuania"))Mobility correlation tables
#overall
mob_cor(dEU, mob_labels)
cor_results <- corr.test(dEU[, mob_vars])
round(cor_results$p, 3)## mob_nat mob_imp mob_pn willcarless willcarshare
## mob_nat 0 0 0 0 0
## mob_imp 0 0 0 0 0
## mob_pn 0 0 0 0 0
## willcarless 0 0 0 0 0
## willcarshare 0 0 0 0 0#test sig. difference in correlation of both SN with behaviours
library(cocor)
#for willcarless
dEU_cc_mob <- na.omit(dEU[, c("mob_nat", "mob_imp", "mob_pn", "willcarless", "willcarshare")])
dEU_cc_mob <- as.data.frame(dEU_cc_mob)
#carless
cocor(~ mob_nat + willcarless | mob_imp + willcarless, data = dEU_cc_mob) ##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (willcarless, mob_nat) = 0.1278 and r.jh (willcarless, mob_imp) = 0.2021
## Difference: r.jk - r.jh = -0.0744
## Related correlation: r.kh = 0.5379
## Data: dEU_cc_mob: j = willcarless, k = mob_nat, h = mob_imp
## Group size: n = 2636
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -4.0474, p-value = 0.0001
## Null hypothesis rejected
##
## hotelling1940: Hotelling's t (1940)
## t = -4.0547, df = 2633, p-value = 0.0001
## Null hypothesis rejected
##
## williams1959: Williams' t (1959)
## t = -4.0507, df = 2633, p-value = 0.0001
## Null hypothesis rejected
##
## olkin1967: Olkin's z (1967)
## z = -4.0474, p-value = 0.0001
## Null hypothesis rejected
##
## dunn1969: Dunn and Clark's z (1969)
## z = -4.0426, p-value = 0.0001
## Null hypothesis rejected
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -4.0547, df = 2633, p-value = 0.0001
## Null hypothesis rejected
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -4.0403, p-value = 0.0001
## Null hypothesis rejected
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -4.0381, p-value = 0.0001
## Null hypothesis rejected
## 95% confidence interval for r.jk - r.jh: -0.1136 -0.0394
## Null hypothesis rejected (Interval does not include 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -4.0402, p-value = 0.0001
## Null hypothesis rejected
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.1104 -0.0383
## Null hypothesis rejected (Interval does not include 0)cocor(~ mob_imp + willcarless | mob_pn + willcarless, data = dEU_cc_mob) ##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (willcarless, mob_imp) = 0.2021 and r.jh (willcarless, mob_pn) = 0.4119
## Difference: r.jk - r.jh = -0.2098
## Related correlation: r.kh = 0.4295
## Data: dEU_cc_mob: j = willcarless, k = mob_imp, h = mob_pn
## Group size: n = 2636
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -10.8704, p-value = 0.0000
## Null hypothesis rejected
##
## hotelling1940: Hotelling's t (1940)
## t = -11.0639, df = 2633, p-value = 0.0000
## Null hypothesis rejected
##
## williams1959: Williams' t (1959)
## t = -10.9930, df = 2633, p-value = 0.0000
## Null hypothesis rejected
##
## olkin1967: Olkin's z (1967)
## z = -10.8704, p-value = 0.0000
## Null hypothesis rejected
##
## dunn1969: Dunn and Clark's z (1969)
## z = -10.8588, p-value = 0.0000
## Null hypothesis rejected
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -11.0639, df = 2633, p-value = 0.0000
## Null hypothesis rejected
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -10.8115, p-value = 0.0000
## Null hypothesis rejected
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -10.7672, p-value = 0.0000
## Null hypothesis rejected
## 95% confidence interval for r.jk - r.jh: -0.2754 -0.1905
## Null hypothesis rejected (Interval does not include 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -10.8021, p-value = 0.0000
## Null hypothesis rejected
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.2476 -0.1719
## Null hypothesis rejected (Interval does not include 0)#carshare
cocor(~ mob_nat + willcarshare | mob_imp + willcarshare, data = dEU_cc_mob) ##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (willcarshare, mob_nat) = 0.2234 and r.jh (willcarshare, mob_imp) = 0.2743
## Difference: r.jk - r.jh = -0.0509
## Related correlation: r.kh = 0.5379
## Data: dEU_cc_mob: j = willcarshare, k = mob_nat, h = mob_imp
## Group size: n = 2636
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -2.8298, p-value = 0.0047
## Null hypothesis rejected
##
## hotelling1940: Hotelling's t (1940)
## t = -2.8372, df = 2633, p-value = 0.0046
## Null hypothesis rejected
##
## williams1959: Williams' t (1959)
## t = -2.8306, df = 2633, p-value = 0.0047
## Null hypothesis rejected
##
## olkin1967: Olkin's z (1967)
## z = -2.8298, p-value = 0.0047
## Null hypothesis rejected
##
## dunn1969: Dunn and Clark's z (1969)
## z = -2.8279, p-value = 0.0047
## Null hypothesis rejected
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -2.8372, df = 2633, p-value = 0.0046
## Null hypothesis rejected
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -2.8271, p-value = 0.0047
## Null hypothesis rejected
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -2.8264, p-value = 0.0047
## Null hypothesis rejected
## 95% confidence interval for r.jk - r.jh: -0.0919 -0.0166
## Null hypothesis rejected (Interval does not include 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -2.8270, p-value = 0.0047
## Null hypothesis rejected
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.0861 -0.0156
## Null hypothesis rejected (Interval does not include 0)cocor(~ mob_imp + willcarshare | mob_pn + willcarshare, data = dEU_cc_mob) ##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (willcarshare, mob_imp) = 0.2743 and r.jh (willcarshare, mob_pn) = 0.4204
## Difference: r.jk - r.jh = -0.1461
## Related correlation: r.kh = 0.4295
## Data: dEU_cc_mob: j = willcarshare, k = mob_imp, h = mob_pn
## Group size: n = 2636
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -7.6765, p-value = 0.0000
## Null hypothesis rejected
##
## hotelling1940: Hotelling's t (1940)
## t = -7.7885, df = 2633, p-value = 0.0000
## Null hypothesis rejected
##
## williams1959: Williams' t (1959)
## t = -7.7235, df = 2633, p-value = 0.0000
## Null hypothesis rejected
##
## olkin1967: Olkin's z (1967)
## z = -7.6765, p-value = 0.0000
## Null hypothesis rejected
##
## dunn1969: Dunn and Clark's z (1969)
## z = -7.6782, p-value = 0.0000
## Null hypothesis rejected
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -7.7885, df = 2633, p-value = 0.0000
## Null hypothesis rejected
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -7.6616, p-value = 0.0000
## Null hypothesis rejected
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -7.6462, p-value = 0.0000
## Null hypothesis rejected
## 95% confidence interval for r.jk - r.jh: -0.2095 -0.1240
## Null hypothesis rejected (Interval does not include 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -7.6573, p-value = 0.0000
## Null hypothesis rejected
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.1835 -0.1088
## Null hypothesis rejected (Interval does not include 0)countries <- list(
Germany = dGER,
Italy = dIT,
Lithuania = dLIT,
Netherlands = dNL,
UK = dUK
)
lapply(countries, mob_cor, labels = mob_labels)
## $Germany
## $Germany$corr
## Societal DN Relevant other DN
## Societal DN 1.0000000 0.5602302
## Relevant other DN 0.5602302 1.0000000
## Personal norms 0.3530951 0.4721004
## Willingness if \nadequate alternatives 0.1637927 0.2589307
## Willingness if \ncar sharing 0.2325029 0.2676186
## Personal norms
## Societal DN 0.3530951
## Relevant other DN 0.4721004
## Personal norms 1.0000000
## Willingness if \nadequate alternatives 0.4188718
## Willingness if \ncar sharing 0.3879080
## Willingness if \nadequate alternatives
## Societal DN 0.1637927
## Relevant other DN 0.2589307
## Personal norms 0.4188718
## Willingness if \nadequate alternatives 1.0000000
## Willingness if \ncar sharing 0.6081731
## Willingness if \ncar sharing
## Societal DN 0.2325029
## Relevant other DN 0.2676186
## Personal norms 0.3879080
## Willingness if \nadequate alternatives 0.6081731
## Willingness if \ncar sharing 1.0000000
##
## $Germany$corrPos
## xName
## 1 Societal DN
## 2 Societal DN
## 3 Societal DN
## 4 Societal DN
## 5 Relevant other DN
## 6 Relevant other DN
## 7 Relevant other DN
## 8 Personal norms
## 9 Personal norms
## 10 Willingness if \nadequate alternatives
## yName x y corr
## 1 Relevant other DN 1 4 0.5602302
## 2 Personal norms 1 3 0.3530951
## 3 Willingness if \nadequate alternatives 1 2 0.1637927
## 4 Willingness if \ncar sharing 1 1 0.2325029
## 5 Personal norms 2 3 0.4721004
## 6 Willingness if \nadequate alternatives 2 2 0.2589307
## 7 Willingness if \ncar sharing 2 1 0.2676186
## 8 Willingness if \nadequate alternatives 3 2 0.4188718
## 9 Willingness if \ncar sharing 3 1 0.3879080
## 10 Willingness if \ncar sharing 4 1 0.6081731
##
## $Germany$arg
## $Germany$arg$type
## [1] "lower"
##
##
##
## $Italy
## $Italy$corr
## Societal DN Relevant other DN
## Societal DN 1.00000000 0.5544954
## Relevant other DN 0.55449535 1.0000000
## Personal norms 0.32139572 0.3454452
## Willingness if \nadequate alternatives 0.03309988 0.1195940
## Willingness if \ncar sharing 0.19462952 0.2686377
## Personal norms
## Societal DN 0.3213957
## Relevant other DN 0.3454452
## Personal norms 1.0000000
## Willingness if \nadequate alternatives 0.4125896
## Willingness if \ncar sharing 0.3791946
## Willingness if \nadequate alternatives
## Societal DN 0.03309988
## Relevant other DN 0.11959404
## Personal norms 0.41258958
## Willingness if \nadequate alternatives 1.00000000
## Willingness if \ncar sharing 0.54946172
## Willingness if \ncar sharing
## Societal DN 0.1946295
## Relevant other DN 0.2686377
## Personal norms 0.3791946
## Willingness if \nadequate alternatives 0.5494617
## Willingness if \ncar sharing 1.0000000
##
## $Italy$corrPos
## xName
## 1 Societal DN
## 2 Societal DN
## 3 Societal DN
## 4 Societal DN
## 5 Relevant other DN
## 6 Relevant other DN
## 7 Relevant other DN
## 8 Personal norms
## 9 Personal norms
## 10 Willingness if \nadequate alternatives
## yName x y corr
## 1 Relevant other DN 1 4 0.55449535
## 2 Personal norms 1 3 0.32139572
## 3 Willingness if \nadequate alternatives 1 2 0.03309988
## 4 Willingness if \ncar sharing 1 1 0.19462952
## 5 Personal norms 2 3 0.34544516
## 6 Willingness if \nadequate alternatives 2 2 0.11959404
## 7 Willingness if \ncar sharing 2 1 0.26863775
## 8 Willingness if \nadequate alternatives 3 2 0.41258958
## 9 Willingness if \ncar sharing 3 1 0.37919460
## 10 Willingness if \ncar sharing 4 1 0.54946172
##
## $Italy$arg
## $Italy$arg$type
## [1] "lower"
##
##
##
## $Lithuania
## $Lithuania$corr
## Societal DN Relevant other DN
## Societal DN 1.00000000 0.6575966
## Relevant other DN 0.65759663 1.0000000
## Personal norms 0.50788566 0.5155574
## Willingness if \nadequate alternatives 0.07879312 0.1264584
## Willingness if \ncar sharing 0.23458370 0.2788990
## Personal norms
## Societal DN 0.5078857
## Relevant other DN 0.5155574
## Personal norms 1.0000000
## Willingness if \nadequate alternatives 0.2366767
## Willingness if \ncar sharing 0.4058799
## Willingness if \nadequate alternatives
## Societal DN 0.07879312
## Relevant other DN 0.12645845
## Personal norms 0.23667671
## Willingness if \nadequate alternatives 1.00000000
## Willingness if \ncar sharing 0.48581137
## Willingness if \ncar sharing
## Societal DN 0.2345837
## Relevant other DN 0.2788990
## Personal norms 0.4058799
## Willingness if \nadequate alternatives 0.4858114
## Willingness if \ncar sharing 1.0000000
##
## $Lithuania$corrPos
## xName
## 1 Societal DN
## 2 Societal DN
## 3 Societal DN
## 4 Societal DN
## 5 Relevant other DN
## 6 Relevant other DN
## 7 Relevant other DN
## 8 Personal norms
## 9 Personal norms
## 10 Willingness if \nadequate alternatives
## yName x y corr
## 1 Relevant other DN 1 4 0.65759663
## 2 Personal norms 1 3 0.50788566
## 3 Willingness if \nadequate alternatives 1 2 0.07879312
## 4 Willingness if \ncar sharing 1 1 0.23458370
## 5 Personal norms 2 3 0.51555745
## 6 Willingness if \nadequate alternatives 2 2 0.12645845
## 7 Willingness if \ncar sharing 2 1 0.27889902
## 8 Willingness if \nadequate alternatives 3 2 0.23667671
## 9 Willingness if \ncar sharing 3 1 0.40587992
## 10 Willingness if \ncar sharing 4 1 0.48581137
##
## $Lithuania$arg
## $Lithuania$arg$type
## [1] "lower"
##
##
##
## $Netherlands
## $Netherlands$corr
## Societal DN Relevant other DN
## Societal DN 1.0000000 0.3850340
## Relevant other DN 0.3850340 1.0000000
## Personal norms 0.3301719 0.3604023
## Willingness if \nadequate alternatives 0.1171585 0.1731649
## Willingness if \ncar sharing 0.1389723 0.2239635
## Personal norms
## Societal DN 0.3301719
## Relevant other DN 0.3604023
## Personal norms 1.0000000
## Willingness if \nadequate alternatives 0.3866654
## Willingness if \ncar sharing 0.3681165
## Willingness if \nadequate alternatives
## Societal DN 0.1171585
## Relevant other DN 0.1731649
## Personal norms 0.3866654
## Willingness if \nadequate alternatives 1.0000000
## Willingness if \ncar sharing 0.5036720
## Willingness if \ncar sharing
## Societal DN 0.1389723
## Relevant other DN 0.2239635
## Personal norms 0.3681165
## Willingness if \nadequate alternatives 0.5036720
## Willingness if \ncar sharing 1.0000000
##
## $Netherlands$corrPos
## xName
## 1 Societal DN
## 2 Societal DN
## 3 Societal DN
## 4 Societal DN
## 5 Relevant other DN
## 6 Relevant other DN
## 7 Relevant other DN
## 8 Personal norms
## 9 Personal norms
## 10 Willingness if \nadequate alternatives
## yName x y corr
## 1 Relevant other DN 1 4 0.3850340
## 2 Personal norms 1 3 0.3301719
## 3 Willingness if \nadequate alternatives 1 2 0.1171585
## 4 Willingness if \ncar sharing 1 1 0.1389723
## 5 Personal norms 2 3 0.3604023
## 6 Willingness if \nadequate alternatives 2 2 0.1731649
## 7 Willingness if \ncar sharing 2 1 0.2239635
## 8 Willingness if \nadequate alternatives 3 2 0.3866654
## 9 Willingness if \ncar sharing 3 1 0.3681165
## 10 Willingness if \ncar sharing 4 1 0.5036720
##
## $Netherlands$arg
## $Netherlands$arg$type
## [1] "lower"
##
##
##
## $UK
## $UK$corr
## Societal DN Relevant other DN
## Societal DN 1.0000000 0.4871454
## Relevant other DN 0.4871454 1.0000000
## Personal norms 0.3435400 0.4365869
## Willingness if \nadequate alternatives 0.2049509 0.2407855
## Willingness if \ncar sharing 0.2649218 0.2206446
## Personal norms
## Societal DN 0.3435400
## Relevant other DN 0.4365869
## Personal norms 1.0000000
## Willingness if \nadequate alternatives 0.4092918
## Willingness if \ncar sharing 0.4210254
## Willingness if \nadequate alternatives
## Societal DN 0.2049509
## Relevant other DN 0.2407855
## Personal norms 0.4092918
## Willingness if \nadequate alternatives 1.0000000
## Willingness if \ncar sharing 0.5468601
## Willingness if \ncar sharing
## Societal DN 0.2649218
## Relevant other DN 0.2206446
## Personal norms 0.4210254
## Willingness if \nadequate alternatives 0.5468601
## Willingness if \ncar sharing 1.0000000
##
## $UK$corrPos
## xName
## 1 Societal DN
## 2 Societal DN
## 3 Societal DN
## 4 Societal DN
## 5 Relevant other DN
## 6 Relevant other DN
## 7 Relevant other DN
## 8 Personal norms
## 9 Personal norms
## 10 Willingness if \nadequate alternatives
## yName x y corr
## 1 Relevant other DN 1 4 0.4871454
## 2 Personal norms 1 3 0.3435400
## 3 Willingness if \nadequate alternatives 1 2 0.2049509
## 4 Willingness if \ncar sharing 1 1 0.2649218
## 5 Personal norms 2 3 0.4365869
## 6 Willingness if \nadequate alternatives 2 2 0.2407855
## 7 Willingness if \ncar sharing 2 1 0.2206446
## 8 Willingness if \nadequate alternatives 3 2 0.4092918
## 9 Willingness if \ncar sharing 3 1 0.4210254
## 10 Willingness if \ncar sharing 4 1 0.5468601
##
## $UK$arg
## $UK$arg$type
## [1] "lower"# apa correlation table overall
#apa.cor.table(dEU[, c("mob_nat", "mob_imp", "mob_pn", "willcarless","willcarshare")],
# filename = "Mobility_EUcor_table.doc")Housing correlation tables
#overall
hous_cor(dEU, hous_labels)
cor_results <- corr.test(dEU[, hous_vars])
round(cor_results$p, 3)## build_nat build_imp build_pn willdown willshare_ki
## build_nat 0 0 0 0 0
## build_imp 0 0 0 0 0
## build_pn 0 0 0 0 0
## willdown 0 0 0 0 0
## willshare_ki 0 0 0 0 0#test sig. difference in correlation of both SN with behaviours
dEU_cc_build <- na.omit(dEU[, c("build_nat", "build_imp", "build_pn", "willdown", "willshare_ki")])
dEU_cc_build <- as.data.frame(dEU_cc_build)
#downsize
cocor(~ build_nat + willdown | build_imp + willdown, data = dEU_cc_build)##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (willdown, build_nat) = 0.2567 and r.jh (willdown, build_imp) = 0.3103
## Difference: r.jk - r.jh = -0.0536
## Related correlation: r.kh = 0.6635
## Data: dEU_cc_build: j = willdown, k = build_nat, h = build_imp
## Group size: n = 5632
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -5.1561, p-value = 0.0000
## Null hypothesis rejected
##
## hotelling1940: Hotelling's t (1940)
## t = -5.1719, df = 5629, p-value = 0.0000
## Null hypothesis rejected
##
## williams1959: Williams' t (1959)
## t = -5.1641, df = 5629, p-value = 0.0000
## Null hypothesis rejected
##
## olkin1967: Olkin's z (1967)
## z = -5.1561, p-value = 0.0000
## Null hypothesis rejected
##
## dunn1969: Dunn and Clark's z (1969)
## z = -5.1558, p-value = 0.0000
## Null hypothesis rejected
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -5.1719, df = 5629, p-value = 0.0000
## Null hypothesis rejected
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -5.1537, p-value = 0.0000
## Null hypothesis rejected
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -5.1521, p-value = 0.0000
## Null hypothesis rejected
## 95% confidence interval for r.jk - r.jh: -0.0805 -0.0361
## Null hypothesis rejected (Interval does not include 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -5.1534, p-value = 0.0000
## Null hypothesis rejected
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.0740 -0.0332
## Null hypothesis rejected (Interval does not include 0)cocor(~ build_imp + willdown | build_pn + willdown, data = dEU_cc_build)##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (willdown, build_imp) = 0.3103 and r.jh (willdown, build_pn) = 0.4296
## Difference: r.jk - r.jh = -0.1194
## Related correlation: r.kh = 0.6018
## Data: dEU_cc_build: j = willdown, k = build_imp, h = build_pn
## Group size: n = 5632
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -10.9953, p-value = 0.0000
## Null hypothesis rejected
##
## hotelling1940: Hotelling's t (1940)
## t = -11.1411, df = 5629, p-value = 0.0000
## Null hypothesis rejected
##
## williams1959: Williams' t (1959)
## t = -11.0949, df = 5629, p-value = 0.0000
## Null hypothesis rejected
##
## olkin1967: Olkin's z (1967)
## z = -10.9953, p-value = 0.0000
## Null hypothesis rejected
##
## dunn1969: Dunn and Clark's z (1969)
## z = -11.0222, p-value = 0.0000
## Null hypothesis rejected
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -11.1411, df = 5629, p-value = 0.0000
## Null hypothesis rejected
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -11.0003, p-value = 0.0000
## Null hypothesis rejected
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -10.9830, p-value = 0.0000
## Null hypothesis rejected
## 95% confidence interval for r.jk - r.jh: -0.1633 -0.1139
## Null hypothesis rejected (Interval does not include 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -10.9948, p-value = 0.0000
## Null hypothesis rejected
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.1406 -0.0981
## Null hypothesis rejected (Interval does not include 0)#shre kitchen
cocor(~ build_nat + willshare_ki | build_imp + willshare_ki, data = dEU_cc_build)##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (willshare_ki, build_nat) = 0.2803 and r.jh (willshare_ki, build_imp) = 0.3549
## Difference: r.jk - r.jh = -0.0746
## Related correlation: r.kh = 0.6635
## Data: dEU_cc_build: j = willshare_ki, k = build_nat, h = build_imp
## Group size: n = 5632
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -7.2742, p-value = 0.0000
## Null hypothesis rejected
##
## hotelling1940: Hotelling's t (1940)
## t = -7.3151, df = 5629, p-value = 0.0000
## Null hypothesis rejected
##
## williams1959: Williams' t (1959)
## t = -7.3007, df = 5629, p-value = 0.0000
## Null hypothesis rejected
##
## olkin1967: Olkin's z (1967)
## z = -7.2742, p-value = 0.0000
## Null hypothesis rejected
##
## dunn1969: Dunn and Clark's z (1969)
## z = -7.2777, p-value = 0.0000
## Null hypothesis rejected
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -7.3151, df = 5629, p-value = 0.0000
## Null hypothesis rejected
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -7.2718, p-value = 0.0000
## Null hypothesis rejected
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -7.2673, p-value = 0.0000
## Null hypothesis rejected
## 95% confidence interval for r.jk - r.jh: -0.1055 -0.0607
## Null hypothesis rejected (Interval does not include 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -7.2708, p-value = 0.0000
## Null hypothesis rejected
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.0947 -0.0545
## Null hypothesis rejected (Interval does not include 0)cocor(~ build_imp + willshare_ki | build_pn + willshare_ki, data = dEU_cc_build)##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (willshare_ki, build_imp) = 0.3549 and r.jh (willshare_ki, build_pn) = 0.3689
## Difference: r.jk - r.jh = -0.0139
## Related correlation: r.kh = 0.6018
## Data: dEU_cc_build: j = willshare_ki, k = build_imp, h = build_pn
## Group size: n = 5632
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -1.2767, p-value = 0.2017
## Null hypothesis retained
##
## hotelling1940: Hotelling's t (1940)
## t = -1.2814, df = 5629, p-value = 0.2001
## Null hypothesis retained
##
## williams1959: Williams' t (1959)
## t = -1.2765, df = 5629, p-value = 0.2018
## Null hypothesis retained
##
## olkin1967: Olkin's z (1967)
## z = -1.2767, p-value = 0.2017
## Null hypothesis retained
##
## dunn1969: Dunn and Clark's z (1969)
## z = -1.2764, p-value = 0.2018
## Null hypothesis retained
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -1.2814, df = 5629, p-value = 0.2001
## Null hypothesis retained
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -1.2763, p-value = 0.2018
## Null hypothesis retained
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -1.2763, p-value = 0.2018
## Null hypothesis retained
## 95% confidence interval for r.jk - r.jh: -0.0407 0.0086
## Null hypothesis retained (Interval includes 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -1.2763, p-value = 0.2018
## Null hypothesis retained
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.0353 0.0075
## Null hypothesis retained (Interval includes 0)#per country
lapply(countries, hous_cor, labels = hous_labels)
## $Germany
## $Germany$corr
## Societal DN Relevant other DN Personal norms
## Societal DN 1.0000000 0.6307011 0.4399499
## Relevant other DN 0.6307011 1.0000000 0.6076939
## Personal norms 0.4399499 0.6076939 1.0000000
## Willingness to\ndownsize 0.2148409 0.3426860 0.4603726
## Willingness to\nshare kitchen 0.3092162 0.4363299 0.4641356
## Willingness to\ndownsize
## Societal DN 0.2148409
## Relevant other DN 0.3426860
## Personal norms 0.4603726
## Willingness to\ndownsize 1.0000000
## Willingness to\nshare kitchen 0.3395500
## Willingness to\nshare kitchen
## Societal DN 0.3092162
## Relevant other DN 0.4363299
## Personal norms 0.4641356
## Willingness to\ndownsize 0.3395500
## Willingness to\nshare kitchen 1.0000000
##
## $Germany$corrPos
## xName yName x y corr
## 1 Societal DN Relevant other DN 1 4 0.6307011
## 2 Societal DN Personal norms 1 3 0.4399499
## 3 Societal DN Willingness to\ndownsize 1 2 0.2148409
## 4 Societal DN Willingness to\nshare kitchen 1 1 0.3092162
## 5 Relevant other DN Personal norms 2 3 0.6076939
## 6 Relevant other DN Willingness to\ndownsize 2 2 0.3426860
## 7 Relevant other DN Willingness to\nshare kitchen 2 1 0.4363299
## 8 Personal norms Willingness to\ndownsize 3 2 0.4603726
## 9 Personal norms Willingness to\nshare kitchen 3 1 0.4641356
## 10 Willingness to\ndownsize Willingness to\nshare kitchen 4 1 0.3395500
##
## $Germany$arg
## $Germany$arg$type
## [1] "lower"
##
##
##
## $Italy
## $Italy$corr
## Societal DN Relevant other DN Personal norms
## Societal DN 1.0000000 0.6925397 0.4521862
## Relevant other DN 0.6925397 1.0000000 0.5651577
## Personal norms 0.4521862 0.5651577 1.0000000
## Willingness to\ndownsize 0.2918030 0.3354845 0.4625815
## Willingness to\nshare kitchen 0.2220636 0.2694306 0.2819311
## Willingness to\ndownsize
## Societal DN 0.2918030
## Relevant other DN 0.3354845
## Personal norms 0.4625815
## Willingness to\ndownsize 1.0000000
## Willingness to\nshare kitchen 0.2226077
## Willingness to\nshare kitchen
## Societal DN 0.2220636
## Relevant other DN 0.2694306
## Personal norms 0.2819311
## Willingness to\ndownsize 0.2226077
## Willingness to\nshare kitchen 1.0000000
##
## $Italy$corrPos
## xName yName x y corr
## 1 Societal DN Relevant other DN 1 4 0.6925397
## 2 Societal DN Personal norms 1 3 0.4521862
## 3 Societal DN Willingness to\ndownsize 1 2 0.2918030
## 4 Societal DN Willingness to\nshare kitchen 1 1 0.2220636
## 5 Relevant other DN Personal norms 2 3 0.5651577
## 6 Relevant other DN Willingness to\ndownsize 2 2 0.3354845
## 7 Relevant other DN Willingness to\nshare kitchen 2 1 0.2694306
## 8 Personal norms Willingness to\ndownsize 3 2 0.4625815
## 9 Personal norms Willingness to\nshare kitchen 3 1 0.2819311
## 10 Willingness to\ndownsize Willingness to\nshare kitchen 4 1 0.2226077
##
## $Italy$arg
## $Italy$arg$type
## [1] "lower"
##
##
##
## $Lithuania
## $Lithuania$corr
## Societal DN Relevant other DN Personal norms
## Societal DN 1.0000000 0.7056002 0.5564420
## Relevant other DN 0.7056002 1.0000000 0.6787633
## Personal norms 0.5564420 0.6787633 1.0000000
## Willingness to\ndownsize 0.2802569 0.3240509 0.4207930
## Willingness to\nshare kitchen 0.3186806 0.3792390 0.3960862
## Willingness to\ndownsize
## Societal DN 0.2802569
## Relevant other DN 0.3240509
## Personal norms 0.4207930
## Willingness to\ndownsize 1.0000000
## Willingness to\nshare kitchen 0.3223879
## Willingness to\nshare kitchen
## Societal DN 0.3186806
## Relevant other DN 0.3792390
## Personal norms 0.3960862
## Willingness to\ndownsize 0.3223879
## Willingness to\nshare kitchen 1.0000000
##
## $Lithuania$corrPos
## xName yName x y corr
## 1 Societal DN Relevant other DN 1 4 0.7056002
## 2 Societal DN Personal norms 1 3 0.5564420
## 3 Societal DN Willingness to\ndownsize 1 2 0.2802569
## 4 Societal DN Willingness to\nshare kitchen 1 1 0.3186806
## 5 Relevant other DN Personal norms 2 3 0.6787633
## 6 Relevant other DN Willingness to\ndownsize 2 2 0.3240509
## 7 Relevant other DN Willingness to\nshare kitchen 2 1 0.3792390
## 8 Personal norms Willingness to\ndownsize 3 2 0.4207930
## 9 Personal norms Willingness to\nshare kitchen 3 1 0.3960862
## 10 Willingness to\ndownsize Willingness to\nshare kitchen 4 1 0.3223879
##
## $Lithuania$arg
## $Lithuania$arg$type
## [1] "lower"
##
##
##
## $Netherlands
## $Netherlands$corr
## Societal DN Relevant other DN Personal norms
## Societal DN 1.0000000 0.6344090 0.3965704
## Relevant other DN 0.6344090 1.0000000 0.5549450
## Personal norms 0.3965704 0.5549450 1.0000000
## Willingness to\ndownsize 0.1602144 0.2090782 0.3848313
## Willingness to\nshare kitchen 0.2164511 0.2792832 0.3251306
## Willingness to\ndownsize
## Societal DN 0.1602144
## Relevant other DN 0.2090782
## Personal norms 0.3848313
## Willingness to\ndownsize 1.0000000
## Willingness to\nshare kitchen 0.1867192
## Willingness to\nshare kitchen
## Societal DN 0.2164511
## Relevant other DN 0.2792832
## Personal norms 0.3251306
## Willingness to\ndownsize 0.1867192
## Willingness to\nshare kitchen 1.0000000
##
## $Netherlands$corrPos
## xName yName x y corr
## 1 Societal DN Relevant other DN 1 4 0.6344090
## 2 Societal DN Personal norms 1 3 0.3965704
## 3 Societal DN Willingness to\ndownsize 1 2 0.1602144
## 4 Societal DN Willingness to\nshare kitchen 1 1 0.2164511
## 5 Relevant other DN Personal norms 2 3 0.5549450
## 6 Relevant other DN Willingness to\ndownsize 2 2 0.2090782
## 7 Relevant other DN Willingness to\nshare kitchen 2 1 0.2792832
## 8 Personal norms Willingness to\ndownsize 3 2 0.3848313
## 9 Personal norms Willingness to\nshare kitchen 3 1 0.3251306
## 10 Willingness to\ndownsize Willingness to\nshare kitchen 4 1 0.1867192
##
## $Netherlands$arg
## $Netherlands$arg$type
## [1] "lower"
##
##
##
## $UK
## $UK$corr
## Societal DN Relevant other DN Personal norms
## Societal DN 1.0000000 0.6351326 0.4723675
## Relevant other DN 0.6351326 1.0000000 0.5766889
## Personal norms 0.4723675 0.5766889 1.0000000
## Willingness to\ndownsize 0.3091050 0.3419929 0.4247782
## Willingness to\nshare kitchen 0.3281362 0.3935943 0.3751258
## Willingness to\ndownsize
## Societal DN 0.3091050
## Relevant other DN 0.3419929
## Personal norms 0.4247782
## Willingness to\ndownsize 1.0000000
## Willingness to\nshare kitchen 0.3182971
## Willingness to\nshare kitchen
## Societal DN 0.3281362
## Relevant other DN 0.3935943
## Personal norms 0.3751258
## Willingness to\ndownsize 0.3182971
## Willingness to\nshare kitchen 1.0000000
##
## $UK$corrPos
## xName yName x y corr
## 1 Societal DN Relevant other DN 1 4 0.6351326
## 2 Societal DN Personal norms 1 3 0.4723675
## 3 Societal DN Willingness to\ndownsize 1 2 0.3091050
## 4 Societal DN Willingness to\nshare kitchen 1 1 0.3281362
## 5 Relevant other DN Personal norms 2 3 0.5766889
## 6 Relevant other DN Willingness to\ndownsize 2 2 0.3419929
## 7 Relevant other DN Willingness to\nshare kitchen 2 1 0.3935943
## 8 Personal norms Willingness to\ndownsize 3 2 0.4247782
## 9 Personal norms Willingness to\nshare kitchen 3 1 0.3751258
## 10 Willingness to\ndownsize Willingness to\nshare kitchen 4 1 0.3182971
##
## $UK$arg
## $UK$arg$type
## [1] "lower"# apa correlation table overall
#apa.cor.table(dEU[, c("build_nat", "build_imp", "build_pn", "willdown","willshare_ki")],
# filename = "Housing_EUcor_table.doc")CCBs correlation tables
#overall
ccb_cor(dEU, ccb_labels)
cor_results <- corr.test(dEU[, ccb_vars])
round(cor_results$p, 3)## ccb_nat ccb_imp ccb_pn gov busi cit
## ccb_nat 0 0 0 0 0 0
## ccb_imp 0 0 0 0 0 0
## ccb_pn 0 0 0 0 0 0
## gov 0 0 0 0 0 0
## busi 0 0 0 0 0 0
## cit 0 0 0 0 0 0#test sig. difference in correlation of both SN with behaviours
dEU_cc_ccb <- na.omit(dEU[, c("ccb_nat", "ccb_imp", "ccb_pn", "gov", "busi", "cit")])
dEU_cc_ccb <- as.data.frame(dEU_cc_ccb)
#governments
cocor(~ ccb_nat + gov | ccb_imp + gov, data = dEU_cc_ccb)##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (gov, ccb_nat) = 0.5023 and r.jh (gov, ccb_imp) = 0.6016
## Difference: r.jk - r.jh = -0.0993
## Related correlation: r.kh = 0.7199
## Data: dEU_cc_ccb: j = gov, k = ccb_nat, h = ccb_imp
## Group size: n = 5651
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -12.2614, p-value = 0.0000
## Null hypothesis rejected
##
## hotelling1940: Hotelling's t (1940)
## t = -12.5821, df = 5648, p-value = 0.0000
## Null hypothesis rejected
##
## williams1959: Williams' t (1959)
## t = -12.5131, df = 5648, p-value = 0.0000
## Null hypothesis rejected
##
## olkin1967: Olkin's z (1967)
## z = -12.2614, p-value = 0.0000
## Null hypothesis rejected
##
## dunn1969: Dunn and Clark's z (1969)
## z = -12.4193, p-value = 0.0000
## Null hypothesis rejected
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -12.5821, df = 5648, p-value = 0.0000
## Null hypothesis rejected
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -12.3836, p-value = 0.0000
## Null hypothesis rejected
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -12.3664, p-value = 0.0000
## Null hypothesis rejected
## 95% confidence interval for r.jk - r.jh: -0.1660 -0.1206
## Null hypothesis rejected (Interval does not include 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -12.3684, p-value = 0.0000
## Null hypothesis rejected
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.1153 -0.0835
## Null hypothesis rejected (Interval does not include 0)cocor(~ ccb_imp + gov | ccb_pn + gov, data = dEU_cc_ccb)##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (gov, ccb_imp) = 0.6016 and r.jh (gov, ccb_pn) = 0.6093
## Difference: r.jk - r.jh = -0.0077
## Related correlation: r.kh = 0.6864
## Data: dEU_cc_ccb: j = gov, k = ccb_imp, h = ccb_pn
## Group size: n = 5651
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -0.9633, p-value = 0.3354
## Null hypothesis retained
##
## hotelling1940: Hotelling's t (1940)
## t = -0.9723, df = 5648, p-value = 0.3310
## Null hypothesis retained
##
## williams1959: Williams' t (1959)
## t = -0.9632, df = 5648, p-value = 0.3355
## Null hypothesis retained
##
## olkin1967: Olkin's z (1967)
## z = -0.9633, p-value = 0.3354
## Null hypothesis retained
##
## dunn1969: Dunn and Clark's z (1969)
## z = -0.9631, p-value = 0.3355
## Null hypothesis retained
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -0.9723, df = 5648, p-value = 0.3310
## Null hypothesis retained
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -0.9631, p-value = 0.3355
## Null hypothesis retained
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -0.9631, p-value = 0.3355
## Null hypothesis retained
## 95% confidence interval for r.jk - r.jh: -0.0369 0.0126
## Null hypothesis retained (Interval includes 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -0.9631, p-value = 0.3355
## Null hypothesis retained
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.0234 0.0080
## Null hypothesis retained (Interval includes 0)#businesses
cocor(~ ccb_nat + busi | ccb_imp + busi, data = dEU_cc_ccb)##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (busi, ccb_nat) = 0.5204 and r.jh (busi, ccb_imp) = 0.6136
## Difference: r.jk - r.jh = -0.0932
## Related correlation: r.kh = 0.7199
## Data: dEU_cc_ccb: j = busi, k = ccb_nat, h = ccb_imp
## Group size: n = 5651
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -11.6787, p-value = 0.0000
## Null hypothesis rejected
##
## hotelling1940: Hotelling's t (1940)
## t = -11.9740, df = 5648, p-value = 0.0000
## Null hypothesis rejected
##
## williams1959: Williams' t (1959)
## t = -11.9028, df = 5648, p-value = 0.0000
## Null hypothesis rejected
##
## olkin1967: Olkin's z (1967)
## z = -11.6787, p-value = 0.0000
## Null hypothesis rejected
##
## dunn1969: Dunn and Clark's z (1969)
## z = -11.8237, p-value = 0.0000
## Null hypothesis rejected
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -11.9740, df = 5648, p-value = 0.0000
## Null hypothesis rejected
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -11.7928, p-value = 0.0000
## Null hypothesis rejected
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -11.7781, p-value = 0.0000
## Null hypothesis rejected
## 95% confidence interval for r.jk - r.jh: -0.1607 -0.1148
## Null hypothesis rejected (Interval does not include 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -11.7787, p-value = 0.0000
## Null hypothesis rejected
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.1089 -0.0776
## Null hypothesis rejected (Interval does not include 0)cocor(~ ccb_imp + busi | ccb_pn + busi, data = dEU_cc_ccb)##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (busi, ccb_imp) = 0.6136 and r.jh (busi, ccb_pn) = 0.6138
## Difference: r.jk - r.jh = -2e-04
## Related correlation: r.kh = 0.6864
## Data: dEU_cc_ccb: j = busi, k = ccb_imp, h = ccb_pn
## Group size: n = 5651
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -0.0225, p-value = 0.9821
## Null hypothesis retained
##
## hotelling1940: Hotelling's t (1940)
## t = -0.0227, df = 5648, p-value = 0.9819
## Null hypothesis retained
##
## williams1959: Williams' t (1959)
## t = -0.0225, df = 5648, p-value = 0.9821
## Null hypothesis retained
##
## olkin1967: Olkin's z (1967)
## z = -0.0225, p-value = 0.9821
## Null hypothesis retained
##
## dunn1969: Dunn and Clark's z (1969)
## z = -0.0225, p-value = 0.9821
## Null hypothesis retained
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -0.0227, df = 5648, p-value = 0.9819
## Null hypothesis retained
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -0.0225, p-value = 0.9821
## Null hypothesis retained
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -0.0225, p-value = 0.9821
## Null hypothesis retained
## 95% confidence interval for r.jk - r.jh: -0.0252 0.0246
## Null hypothesis retained (Interval includes 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -0.0225, p-value = 0.9821
## Null hypothesis retained
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.0157 0.0153
## Null hypothesis retained (Interval includes 0)#other citizens
cocor(~ ccb_nat + cit | ccb_imp + cit, data = dEU_cc_ccb)##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (cit, ccb_nat) = 0.525 and r.jh (cit, ccb_imp) = 0.6174
## Difference: r.jk - r.jh = -0.0924
## Related correlation: r.kh = 0.7199
## Data: dEU_cc_ccb: j = cit, k = ccb_nat, h = ccb_imp
## Group size: n = 5651
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -11.6329, p-value = 0.0000
## Null hypothesis rejected
##
## hotelling1940: Hotelling's t (1940)
## t = -11.9290, df = 5648, p-value = 0.0000
## Null hypothesis rejected
##
## williams1959: Williams' t (1959)
## t = -11.8564, df = 5648, p-value = 0.0000
## Null hypothesis rejected
##
## olkin1967: Olkin's z (1967)
## z = -11.6329, p-value = 0.0000
## Null hypothesis rejected
##
## dunn1969: Dunn and Clark's z (1969)
## z = -11.7787, p-value = 0.0000
## Null hypothesis rejected
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -11.9290, df = 5648, p-value = 0.0000
## Null hypothesis rejected
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -11.7481, p-value = 0.0000
## Null hypothesis rejected
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -11.7336, p-value = 0.0000
## Null hypothesis rejected
## 95% confidence interval for r.jk - r.jh: -0.1606 -0.1146
## Null hypothesis rejected (Interval does not include 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -11.7340, p-value = 0.0000
## Null hypothesis rejected
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.1081 -0.0769
## Null hypothesis rejected (Interval does not include 0)cocor(~ ccb_imp + cit | ccb_pn + cit, data = dEU_cc_ccb)##
## Results of a comparison of two overlapping correlations based on dependent groups
##
## Comparison between r.jk (cit, ccb_imp) = 0.6174 and r.jh (cit, ccb_pn) = 0.6615
## Difference: r.jk - r.jh = -0.044
## Related correlation: r.kh = 0.6864
## Data: dEU_cc_ccb: j = cit, k = ccb_imp, h = ccb_pn
## Group size: n = 5651
## Null hypothesis: r.jk is equal to r.jh
## Alternative hypothesis: r.jk is not equal to r.jh (two-sided)
## Alpha: 0.05
##
## pearson1898: Pearson and Filon's z (1898)
## z = -5.7455, p-value = 0.0000
## Null hypothesis rejected
##
## hotelling1940: Hotelling's t (1940)
## t = -5.8410, df = 5648, p-value = 0.0000
## Null hypothesis rejected
##
## williams1959: Williams' t (1959)
## t = -5.7742, df = 5648, p-value = 0.0000
## Null hypothesis rejected
##
## olkin1967: Olkin's z (1967)
## z = -5.7455, p-value = 0.0000
## Null hypothesis rejected
##
## dunn1969: Dunn and Clark's z (1969)
## z = -5.7663, p-value = 0.0000
## Null hypothesis rejected
##
## hendrickson1970: Hendrickson, Stanley, and Hills' (1970) modification of Williams' t (1959)
## t = -5.8410, df = 5648, p-value = 0.0000
## Null hypothesis rejected
##
## steiger1980: Steiger's (1980) modification of Dunn and Clark's z (1969) using average correlations
## z = -5.7631, p-value = 0.0000
## Null hypothesis rejected
##
## meng1992: Meng, Rosenthal, and Rubin's z (1992)
## z = -5.7615, p-value = 0.0000
## Null hypothesis rejected
## 95% confidence interval for r.jk - r.jh: -0.1000 -0.0492
## Null hypothesis rejected (Interval does not include 0)
##
## hittner2003: Hittner, May, and Silver's (2003) modification of Dunn and Clark's z (1969) using a backtransformed average Fisher's (1921) Z procedure
## z = -5.7608, p-value = 0.0000
## Null hypothesis rejected
##
## zou2007: Zou's (2007) confidence interval
## 95% confidence interval for r.jk - r.jh: -0.0591 -0.0290
## Null hypothesis rejected (Interval does not include 0)lapply(countries, ccb_cor, labels = ccb_labels)
## $Germany
## $Germany$corr
## Societal DN Relevant other DN Personal norms
## Societal DN 1.0000000 0.6358230 0.4677867
## Relevant other DN 0.6358230 1.0000000 0.7118587
## Personal norms 0.4677867 0.7118587 1.0000000
## CCB @ governments 0.4524008 0.6374183 0.6585350
## CCB @ businesses 0.4813978 0.6628514 0.6553074
## CCB @ other citizens 0.4493971 0.6590673 0.7258107
## CCB @ governments CCB @ businesses CCB @ other citizens
## Societal DN 0.4524008 0.4813978 0.4493971
## Relevant other DN 0.6374183 0.6628514 0.6590673
## Personal norms 0.6585350 0.6553074 0.7258107
## CCB @ governments 1.0000000 0.7296357 0.6813543
## CCB @ businesses 0.7296357 1.0000000 0.7861241
## CCB @ other citizens 0.6813543 0.7861241 1.0000000
##
## $Germany$corrPos
## xName yName x y corr
## 1 Societal DN Relevant other DN 1 5 0.6358230
## 2 Societal DN Personal norms 1 4 0.4677867
## 3 Societal DN CCB @ governments 1 3 0.4524008
## 4 Societal DN CCB @ businesses 1 2 0.4813978
## 5 Societal DN CCB @ other citizens 1 1 0.4493971
## 6 Relevant other DN Personal norms 2 4 0.7118587
## 7 Relevant other DN CCB @ governments 2 3 0.6374183
## 8 Relevant other DN CCB @ businesses 2 2 0.6628514
## 9 Relevant other DN CCB @ other citizens 2 1 0.6590673
## 10 Personal norms CCB @ governments 3 3 0.6585350
## 11 Personal norms CCB @ businesses 3 2 0.6553074
## 12 Personal norms CCB @ other citizens 3 1 0.7258107
## 13 CCB @ governments CCB @ businesses 4 2 0.7296357
## 14 CCB @ governments CCB @ other citizens 4 1 0.6813543
## 15 CCB @ businesses CCB @ other citizens 5 1 0.7861241
##
## $Germany$arg
## $Germany$arg$type
## [1] "lower"
##
##
##
## $Italy
## $Italy$corr
## Societal DN Relevant other DN Personal norms
## Societal DN 1.0000000 0.7092466 0.5416878
## Relevant other DN 0.7092466 1.0000000 0.6302736
## Personal norms 0.5416878 0.6302736 1.0000000
## CCB @ governments 0.4720788 0.5319018 0.5625675
## CCB @ businesses 0.4958256 0.5252589 0.5523016
## CCB @ other citizens 0.4770799 0.5234199 0.6260999
## CCB @ governments CCB @ businesses CCB @ other citizens
## Societal DN 0.4720788 0.4958256 0.4770799
## Relevant other DN 0.5319018 0.5252589 0.5234199
## Personal norms 0.5625675 0.5523016 0.6260999
## CCB @ governments 1.0000000 0.7310898 0.6082288
## CCB @ businesses 0.7310898 1.0000000 0.6425374
## CCB @ other citizens 0.6082288 0.6425374 1.0000000
##
## $Italy$corrPos
## xName yName x y corr
## 1 Societal DN Relevant other DN 1 5 0.7092466
## 2 Societal DN Personal norms 1 4 0.5416878
## 3 Societal DN CCB @ governments 1 3 0.4720788
## 4 Societal DN CCB @ businesses 1 2 0.4958256
## 5 Societal DN CCB @ other citizens 1 1 0.4770799
## 6 Relevant other DN Personal norms 2 4 0.6302736
## 7 Relevant other DN CCB @ governments 2 3 0.5319018
## 8 Relevant other DN CCB @ businesses 2 2 0.5252589
## 9 Relevant other DN CCB @ other citizens 2 1 0.5234199
## 10 Personal norms CCB @ governments 3 3 0.5625675
## 11 Personal norms CCB @ businesses 3 2 0.5523016
## 12 Personal norms CCB @ other citizens 3 1 0.6260999
## 13 CCB @ governments CCB @ businesses 4 2 0.7310898
## 14 CCB @ governments CCB @ other citizens 4 1 0.6082288
## 15 CCB @ businesses CCB @ other citizens 5 1 0.6425374
##
## $Italy$arg
## $Italy$arg$type
## [1] "lower"
##
##
##
## $Lithuania
## $Lithuania$corr
## Societal DN Relevant other DN Personal norms
## Societal DN 1.0000000 0.7412838 0.5472925
## Relevant other DN 0.7412838 1.0000000 0.6326697
## Personal norms 0.5472925 0.6326697 1.0000000
## CCB @ governments 0.5189180 0.5792305 0.5615270
## CCB @ businesses 0.4715517 0.5205113 0.5311992
## CCB @ other citizens 0.5293687 0.5424458 0.5407025
## CCB @ governments CCB @ businesses CCB @ other citizens
## Societal DN 0.5189180 0.4715517 0.5293687
## Relevant other DN 0.5792305 0.5205113 0.5424458
## Personal norms 0.5615270 0.5311992 0.5407025
## CCB @ governments 1.0000000 0.7170843 0.6442270
## CCB @ businesses 0.7170843 1.0000000 0.6534550
## CCB @ other citizens 0.6442270 0.6534550 1.0000000
##
## $Lithuania$corrPos
## xName yName x y corr
## 1 Societal DN Relevant other DN 1 5 0.7412838
## 2 Societal DN Personal norms 1 4 0.5472925
## 3 Societal DN CCB @ governments 1 3 0.5189180
## 4 Societal DN CCB @ businesses 1 2 0.4715517
## 5 Societal DN CCB @ other citizens 1 1 0.5293687
## 6 Relevant other DN Personal norms 2 4 0.6326697
## 7 Relevant other DN CCB @ governments 2 3 0.5792305
## 8 Relevant other DN CCB @ businesses 2 2 0.5205113
## 9 Relevant other DN CCB @ other citizens 2 1 0.5424458
## 10 Personal norms CCB @ governments 3 3 0.5615270
## 11 Personal norms CCB @ businesses 3 2 0.5311992
## 12 Personal norms CCB @ other citizens 3 1 0.5407025
## 13 CCB @ governments CCB @ businesses 4 2 0.7170843
## 14 CCB @ governments CCB @ other citizens 4 1 0.6442270
## 15 CCB @ businesses CCB @ other citizens 5 1 0.6534550
##
## $Lithuania$arg
## $Lithuania$arg$type
## [1] "lower"
##
##
##
## $Netherlands
## $Netherlands$corr
## Societal DN Relevant other DN Personal norms
## Societal DN 1.0000000 0.7522799 0.6041427
## Relevant other DN 0.7522799 1.0000000 0.7313953
## Personal norms 0.6041427 0.7313953 1.0000000
## CCB @ governments 0.5281815 0.6223075 0.6069776
## CCB @ businesses 0.5486238 0.6676164 0.6385815
## CCB @ other citizens 0.5761457 0.6971165 0.6701829
## CCB @ governments CCB @ businesses CCB @ other citizens
## Societal DN 0.5281815 0.5486238 0.5761457
## Relevant other DN 0.6223075 0.6676164 0.6971165
## Personal norms 0.6069776 0.6385815 0.6701829
## CCB @ governments 1.0000000 0.8471926 0.7648220
## CCB @ businesses 0.8471926 1.0000000 0.7958050
## CCB @ other citizens 0.7648220 0.7958050 1.0000000
##
## $Netherlands$corrPos
## xName yName x y corr
## 1 Societal DN Relevant other DN 1 5 0.7522799
## 2 Societal DN Personal norms 1 4 0.6041427
## 3 Societal DN CCB @ governments 1 3 0.5281815
## 4 Societal DN CCB @ businesses 1 2 0.5486238
## 5 Societal DN CCB @ other citizens 1 1 0.5761457
## 6 Relevant other DN Personal norms 2 4 0.7313953
## 7 Relevant other DN CCB @ governments 2 3 0.6223075
## 8 Relevant other DN CCB @ businesses 2 2 0.6676164
## 9 Relevant other DN CCB @ other citizens 2 1 0.6971165
## 10 Personal norms CCB @ governments 3 3 0.6069776
## 11 Personal norms CCB @ businesses 3 2 0.6385815
## 12 Personal norms CCB @ other citizens 3 1 0.6701829
## 13 CCB @ governments CCB @ businesses 4 2 0.8471926
## 14 CCB @ governments CCB @ other citizens 4 1 0.7648220
## 15 CCB @ businesses CCB @ other citizens 5 1 0.7958050
##
## $Netherlands$arg
## $Netherlands$arg$type
## [1] "lower"
##
##
##
## $UK
## $UK$corr
## Societal DN Relevant other DN Personal norms
## Societal DN 1.0000000 0.7422757 0.5898225
## Relevant other DN 0.7422757 1.0000000 0.7109571
## Personal norms 0.5898225 0.7109571 1.0000000
## CCB @ governments 0.4967106 0.6097489 0.6230447
## CCB @ businesses 0.5467442 0.6504958 0.6610538
## CCB @ other citizens 0.5569499 0.6263941 0.6951986
## CCB @ governments CCB @ businesses CCB @ other citizens
## Societal DN 0.4967106 0.5467442 0.5569499
## Relevant other DN 0.6097489 0.6504958 0.6263941
## Personal norms 0.6230447 0.6610538 0.6951986
## CCB @ governments 1.0000000 0.6735855 0.6328394
## CCB @ businesses 0.6735855 1.0000000 0.7598245
## CCB @ other citizens 0.6328394 0.7598245 1.0000000
##
## $UK$corrPos
## xName yName x y corr
## 1 Societal DN Relevant other DN 1 5 0.7422757
## 2 Societal DN Personal norms 1 4 0.5898225
## 3 Societal DN CCB @ governments 1 3 0.4967106
## 4 Societal DN CCB @ businesses 1 2 0.5467442
## 5 Societal DN CCB @ other citizens 1 1 0.5569499
## 6 Relevant other DN Personal norms 2 4 0.7109571
## 7 Relevant other DN CCB @ governments 2 3 0.6097489
## 8 Relevant other DN CCB @ businesses 2 2 0.6504958
## 9 Relevant other DN CCB @ other citizens 2 1 0.6263941
## 10 Personal norms CCB @ governments 3 3 0.6230447
## 11 Personal norms CCB @ businesses 3 2 0.6610538
## 12 Personal norms CCB @ other citizens 3 1 0.6951986
## 13 CCB @ governments CCB @ businesses 4 2 0.6735855
## 14 CCB @ governments CCB @ other citizens 4 1 0.6328394
## 15 CCB @ businesses CCB @ other citizens 5 1 0.7598245
##
## $UK$arg
## $UK$arg$type
## [1] "lower"# apa correlation table overall
#apa.cor.table(dEU[, c("ccb_nat", "ccb_imp", "ccb_pn", "gov","busi", "cit")],
# filename = "CCB_EUcor_table.doc")Model testing
Mobility
library(lavaan)
library(lavaanPlot)
library(rsvg)## Linking to librsvg 2.61.0library(DiagrammeRsvg)
model_mob <- '
willcarless ~ f1*mob_nat + d1*mob_imp + e1*mob_pn
willcarshare ~ f2*mob_nat + d2*mob_imp + e2*mob_pn
mob_pn ~ b*mob_nat + c*mob_imp
mob_imp ~ a*mob_nat
#indirect effect
ind_willcarless := a*d1 + b*e1 + a*c*e1
ind_willcarshare := a*d2 + b*e2 + a*c*e2
#total effect
total_willcarless := f1 + a*d1 + b*e1 + a*c*e1
total_willcarshare := f2 + a*d2 + b*e2 + a*c*e2
'
#path analysis overall
fit_mob <- lavaan::sem(model_mob, dEU, meanstructure = TRUE)
#fit_mob <- lavaan::sem(model_mob, dEU, meanstructure = TRUE, se = "bootstrap", bootstrap = 5000)
summary(fit_mob, standardized = T, fit.measures = T , rsquare = TRUE)## lavaan 0.6-20 ended normally after 16 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 18
##
## Used Total
## Number of observations 2636 5651
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 3261.807
## Degrees of freedom 10
## 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) -19345.900
## Loglikelihood unrestricted model (H1) -19345.900
##
## Akaike (AIC) 38727.801
## Bayesian (BIC) 38833.587
## Sample-size adjusted Bayesian (SABIC) 38776.396
##
## 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|) Std.lv Std.all
## willcarless ~
## mob_nat (f1) -0.073 0.028 -2.572 0.010 -0.073 -0.055
## mob_imp (d1) 0.069 0.027 2.567 0.010 0.069 0.056
## mob_pn (e1) 0.484 0.024 20.441 0.000 0.484 0.408
## willcarshare ~
## mob_nat (f2) 0.042 0.026 1.584 0.113 0.042 0.034
## mob_imp (d2) 0.114 0.025 4.566 0.000 0.114 0.099
## mob_pn (e2) 0.403 0.022 18.464 0.000 0.403 0.365
## mob_pn ~
## mob_nat (b) 0.225 0.023 9.777 0.000 0.225 0.200
## mob_imp (c) 0.334 0.021 15.695 0.000 0.334 0.322
## mob_imp ~
## mob_nat (a) 0.580 0.018 32.759 0.000 0.580 0.538
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless ~~
## .willcarshare 1.427 0.065 22.109 0.000 1.427 0.477
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless 2.293 0.076 30.053 0.000 2.293 1.159
## .willcarshare 1.392 0.070 19.765 0.000 1.392 0.755
## .mob_pn 1.276 0.058 22.114 0.000 1.276 0.764
## .mob_imp 0.871 0.050 17.435 0.000 0.871 0.542
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless 3.241 0.089 36.304 0.000 3.241 0.827
## .willcarshare 2.760 0.076 36.304 0.000 2.760 0.812
## .mob_pn 2.196 0.060 36.304 0.000 2.196 0.787
## .mob_imp 1.836 0.051 36.304 0.000 1.836 0.711
##
## R-Square:
## Estimate
## willcarless 0.173
## willcarshare 0.188
## mob_pn 0.213
## mob_imp 0.289
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_willcarlss 0.243 0.019 12.827 0.000 0.243 0.183
## ind_willcarshr 0.235 0.017 13.645 0.000 0.235 0.190
## total_wllcrlss 0.170 0.026 6.614 0.000 0.170 0.128
## total_wllcrshr 0.276 0.023 11.767 0.000 0.276 0.223lavaanPlot(model = fit_mob, graph_options = list(rankdir = "LR"), node_options = list(shape = "box", fontname = "Helvetica"), edge_options = list(color = "grey"), coefs = TRUE, covs = FALSE, stand = TRUE)#path analysis per country
summary(lavaan::sem(model_mob, dGER, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 9 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 11 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Used Total
## Number of observations 573 1100
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 775.925
## Degrees of freedom 10
## 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) -4011.480
## Loglikelihood unrestricted model (H1) -4011.480
##
## Akaike (AIC) 8050.960
## Bayesian (BIC) 8111.873
## Sample-size adjusted Bayesian (SABIC) 8067.429
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4991
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## willcarless ~
## mob_nat (f1) -0.031 0.071 -0.437 0.662 -0.031 -0.022
## mob_imp (d1) 0.121 0.074 1.639 0.101 0.121 0.090
## mob_pn (e1) 0.473 0.052 9.067 0.000 0.473 0.384
## willcarshare ~
## mob_nat (f2) 0.098 0.064 1.527 0.127 0.098 0.078
## mob_imp (d2) 0.084 0.066 1.264 0.206 0.084 0.069
## mob_pn (e2) 0.363 0.060 6.005 0.000 0.363 0.328
## mob_pn ~
## mob_nat (b) 0.147 0.061 2.398 0.016 0.147 0.129
## mob_imp (c) 0.436 0.071 6.173 0.000 0.436 0.400
## mob_imp ~
## mob_nat (a) 0.583 0.045 12.898 0.000 0.583 0.560
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless ~~
## .willcarshare 1.462 0.126 11.577 0.000 1.462 0.532
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless 3.024 0.152 19.850 0.000 3.024 0.819
## .willcarshare 2.498 0.147 16.953 0.000 2.498 0.836
## .mob_pn 1.861 0.139 13.424 0.000 1.861 0.766
## .mob_imp 1.404 0.150 9.390 0.000 1.404 0.686
##
## R-Square:
## Estimate
## willcarless 0.181
## willcarshare 0.164
## mob_pn 0.234
## mob_imp 0.314
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_willcarlss 0.260 0.046 5.609 0.000 0.260 0.186
## ind_willcarshr 0.194 0.043 4.476 0.000 0.194 0.154
## total_wllcrlss 0.229 0.059 3.867 0.000 0.229 0.164
## total_wllcrshr 0.292 0.053 5.569 0.000 0.292 0.233summary(lavaan::sem(model_mob, dIT, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 15 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 11 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Used Total
## Number of observations 783 1409
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 913.862
## Degrees of freedom 10
## 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) -5841.487
## Loglikelihood unrestricted model (H1) -5841.487
##
## Akaike (AIC) 11710.974
## Bayesian (BIC) 11776.258
## Sample-size adjusted Bayesian (SABIC) 11731.801
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4985
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## willcarless ~
## mob_nat (f1) -0.165 0.053 -3.122 0.002 -0.165 -0.131
## mob_imp (d1) 0.047 0.049 0.956 0.339 0.047 0.040
## mob_pn (e1) 0.504 0.040 12.501 0.000 0.504 0.441
## willcarshare ~
## mob_nat (f2) 0.006 0.054 0.119 0.905 0.006 0.005
## mob_imp (d2) 0.181 0.056 3.223 0.001 0.181 0.154
## mob_pn (e2) 0.372 0.047 7.878 0.000 0.372 0.324
## mob_pn ~
## mob_nat (b) 0.207 0.052 3.983 0.000 0.207 0.187
## mob_imp (c) 0.248 0.050 4.998 0.000 0.248 0.241
## mob_imp ~
## mob_nat (a) 0.597 0.038 15.882 0.000 0.597 0.554
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless ~~
## .willcarshare 1.506 0.129 11.646 0.000 1.506 0.481
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless 3.090 0.129 23.934 0.000 3.090 0.818
## .willcarshare 3.177 0.150 21.185 0.000 3.177 0.835
## .mob_pn 2.475 0.143 17.355 0.000 2.475 0.856
## .mob_imp 1.900 0.138 13.778 0.000 1.900 0.693
##
## R-Square:
## Estimate
## willcarless 0.182
## willcarshare 0.165
## mob_pn 0.144
## mob_imp 0.307
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_willcarlss 0.207 0.038 5.450 0.000 0.207 0.164
## ind_willcarshr 0.241 0.037 6.547 0.000 0.241 0.190
## total_wllcrlss 0.042 0.047 0.899 0.369 0.042 0.033
## total_wllcrshr 0.247 0.047 5.224 0.000 0.247 0.195summary(lavaan::sem(model_mob, dLIT, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 9 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 14 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Used Total
## Number of observations 310 1008
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 437.518
## Degrees of freedom 10
## 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) -2326.077
## Loglikelihood unrestricted model (H1) -2326.077
##
## Akaike (AIC) 4680.154
## Bayesian (BIC) 4732.466
## Sample-size adjusted Bayesian (SABIC) 4688.064
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4991
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## willcarless ~
## mob_nat (f1) -0.095 0.092 -1.033 0.302 -0.095 -0.083
## mob_imp (d1) 0.059 0.089 0.662 0.508 0.059 0.051
## mob_pn (e1) 0.280 0.084 3.327 0.001 0.280 0.253
## willcarshare ~
## mob_nat (f2) -0.019 0.097 -0.201 0.840 -0.019 -0.017
## mob_imp (d2) 0.119 0.094 1.266 0.206 0.119 0.104
## mob_pn (e2) 0.393 0.078 5.071 0.000 0.393 0.361
## mob_pn ~
## mob_nat (b) 0.309 0.088 3.496 0.000 0.309 0.298
## mob_imp (c) 0.337 0.082 4.085 0.000 0.337 0.320
## mob_imp ~
## mob_nat (a) 0.648 0.060 10.740 0.000 0.648 0.658
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless ~~
## .willcarshare 1.554 0.226 6.881 0.000 1.554 0.440
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless 3.830 0.226 16.913 0.000 3.830 0.940
## .willcarshare 3.255 0.236 13.769 0.000 3.255 0.828
## .mob_pn 2.266 0.214 10.576 0.000 2.266 0.684
## .mob_imp 1.699 0.193 8.784 0.000 1.699 0.568
##
## R-Square:
## Estimate
## willcarless 0.060
## willcarshare 0.172
## mob_pn 0.316
## mob_imp 0.432
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_willcarlss 0.186 0.064 2.883 0.004 0.186 0.162
## ind_willcarshr 0.284 0.072 3.959 0.000 0.284 0.252
## total_wllcrlss 0.091 0.070 1.300 0.194 0.091 0.079
## total_wllcrshr 0.265 0.070 3.785 0.000 0.265 0.235summary(lavaan::sem(model_mob, dNL, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 16 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 9 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Used Total
## Number of observations 511 1081
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 442.100
## Degrees of freedom 10
## 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) -3641.032
## Loglikelihood unrestricted model (H1) -3641.032
##
## Akaike (AIC) 7310.065
## Bayesian (BIC) 7369.374
## Sample-size adjusted Bayesian (SABIC) 7324.936
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4984
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## willcarless ~
## mob_nat (f1) -0.034 0.071 -0.483 0.629 -0.034 -0.026
## mob_imp (d1) 0.057 0.064 0.901 0.368 0.057 0.047
## mob_pn (e1) 0.469 0.060 7.784 0.000 0.469 0.378
## willcarshare ~
## mob_nat (f2) -0.015 0.064 -0.234 0.815 -0.015 -0.013
## mob_imp (d2) 0.115 0.068 1.697 0.090 0.115 0.109
## mob_pn (e2) 0.355 0.061 5.821 0.000 0.355 0.333
## mob_pn ~
## mob_nat (b) 0.243 0.066 3.694 0.000 0.243 0.225
## mob_imp (c) 0.270 0.055 4.913 0.000 0.270 0.274
## mob_imp ~
## mob_nat (a) 0.421 0.059 7.181 0.000 0.421 0.385
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless ~~
## .willcarshare 1.047 0.144 7.257 0.000 1.047 0.420
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless 2.895 0.186 15.594 0.000 2.895 0.849
## .willcarshare 2.149 0.159 13.528 0.000 2.149 0.855
## .mob_pn 1.832 0.155 11.781 0.000 1.832 0.827
## .mob_imp 1.934 0.201 9.610 0.000 1.934 0.852
##
## R-Square:
## Estimate
## willcarless 0.151
## willcarshare 0.145
## mob_pn 0.173
## mob_imp 0.148
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_willcarlss 0.191 0.041 4.622 0.000 0.191 0.143
## ind_willcarshr 0.175 0.036 4.847 0.000 0.175 0.152
## total_wllcrlss 0.157 0.063 2.504 0.012 0.157 0.117
## total_wllcrshr 0.160 0.057 2.824 0.005 0.160 0.139summary(lavaan::sem(model_mob, dUK, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 8 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 10 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Used Total
## Number of observations 459 1053
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 524.390
## Degrees of freedom 10
## 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) -3307.033
## Loglikelihood unrestricted model (H1) -3307.033
##
## Akaike (AIC) 6642.066
## Bayesian (BIC) 6699.873
## Sample-size adjusted Bayesian (SABIC) 6655.441
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4992
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## willcarless ~
## mob_nat (f1) 0.072 0.070 1.033 0.301 0.072 0.052
## mob_imp (d1) 0.066 0.066 0.998 0.318 0.066 0.055
## mob_pn (e1) 0.448 0.068 6.591 0.000 0.448 0.367
## willcarshare ~
## mob_nat (f2) 0.159 0.060 2.657 0.008 0.159 0.142
## mob_imp (d2) -0.013 0.052 -0.251 0.802 -0.013 -0.013
## mob_pn (e2) 0.372 0.055 6.702 0.000 0.372 0.378
## mob_pn ~
## mob_nat (b) 0.196 0.067 2.938 0.003 0.196 0.172
## mob_imp (c) 0.347 0.062 5.567 0.000 0.347 0.353
## mob_imp ~
## mob_nat (a) 0.567 0.051 11.085 0.000 0.567 0.487
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless ~~
## .willcarshare 1.136 0.158 7.192 0.000 1.136 0.449
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willcarless 3.181 0.192 16.534 0.000 3.181 0.826
## .willcarshare 2.015 0.170 11.820 0.000 2.015 0.806
## .mob_pn 2.036 0.156 13.075 0.000 2.036 0.787
## .mob_imp 2.043 0.201 10.161 0.000 2.043 0.763
##
## R-Square:
## Estimate
## willcarless 0.174
## willcarshare 0.194
## mob_pn 0.213
## mob_imp 0.237
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_willcarlss 0.214 0.043 4.981 0.000 0.214 0.153
## ind_willcarshr 0.139 0.036 3.889 0.000 0.139 0.123
## total_wllcrlss 0.286 0.065 4.401 0.000 0.286 0.205
## total_wllcrshr 0.298 0.063 4.751 0.000 0.298 0.265lavaanPlot(model = fit_mob, graph_options = list(rankdir = "LR"), node_options = list(shape = "box", fontname = "Helvetica"), edge_options = list(color = "grey"), coefs = TRUE, covs = FALSE, stand = TRUE)Housing
model_build <- '
willdown ~ f1*build_nat + d1*build_imp + e1*build_pn
willshare_ki ~ f2*build_nat + d2*build_imp + e2*build_pn
build_pn ~ b*build_nat + c*build_imp
build_imp ~ a*build_nat
#indirect effect
ind_willdown := a*d1 + b*e1 + a*c*e1
ind_willshare_ki := a*d2 + b*e2 + a*c*e2
#total effect
total_willdown := f1 + a*d1 + b*e1 + a*c*e1
total_willshare_ki := f2 + a*d2 + b*e2 + a*c*e2
'
#path analysis overall
fit_build <- lavaan::sem(model_build, dEU)
#fit_build <- lavaan::sem(model_build, dEU, meanstructure = TRUE, se = "bootstrap", bootstrap = 5000)
summary(fit_build, standardized = T, fit.measures = T , rsquare = TRUE)## lavaan 0.6-20 ended normally after 9 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Used Total
## Number of observations 5632 5651
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 8169.980
## Degrees of freedom 10
## 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) -41247.249
## Loglikelihood unrestricted model (H1) -41247.249
##
## Akaike (AIC) 82522.498
## Bayesian (BIC) 82615.405
## Sample-size adjusted Bayesian (SABIC) 82570.918
##
## 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|) Std.lv Std.all
## willdown ~
## build_nat (f1) 0.052 0.020 2.676 0.007 0.052 0.043
## build_imp (d1) 0.065 0.021 3.100 0.002 0.065 0.055
## build_pn (e1) 0.429 0.017 24.864 0.000 0.429 0.376
## willshare_ki ~
## build_nat (f2) 0.051 0.017 3.050 0.002 0.051 0.050
## build_imp (d2) 0.175 0.018 9.861 0.000 0.175 0.179
## build_pn (e2) 0.228 0.015 15.494 0.000 0.228 0.238
## build_pn ~
## build_nat (b) 0.134 0.015 8.949 0.000 0.134 0.126
## build_imp (c) 0.531 0.014 36.673 0.000 0.531 0.518
## build_imp ~
## build_nat (a) 0.688 0.010 66.555 0.000 0.688 0.664
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willdown ~~
## .willshare_ki 0.354 0.038 9.251 0.000 0.354 0.124
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willdown 3.340 0.063 53.066 0.000 3.340 0.810
## .willshare_ki 2.433 0.046 53.066 0.000 2.433 0.835
## .build_pn 1.995 0.038 53.066 0.000 1.995 0.629
## .build_imp 1.692 0.032 53.066 0.000 1.692 0.560
##
## R-Square:
## Estimate
## willdown 0.190
## willshare_ki 0.165
## build_pn 0.371
## build_imp 0.440
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_willdown 0.259 0.014 18.119 0.000 0.259 0.213
## ind_willshar_k 0.235 0.012 19.770 0.000 0.235 0.230
## total_willdown 0.311 0.016 19.930 0.000 0.311 0.257
## total_wllshr_k 0.285 0.013 21.914 0.000 0.285 0.280lavaanPlot(model = fit_build, graph_options = list(rankdir = "LR"), node_options = list(shape = "box", fontname = "Helvetica"), edge_options = list(color = "grey"), coefs = TRUE, covs = FALSE, stand = TRUE)#path analysis per country
summary(lavaan::sem(model_build, dGER, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 32 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 8 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Used Total
## Number of observations 1099 1100
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 1690.110
## Degrees of freedom 10
## 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) -7904.602
## Loglikelihood unrestricted model (H1) -7904.602
##
## Akaike (AIC) 15837.205
## Bayesian (BIC) 15907.235
## Sample-size adjusted Bayesian (SABIC) 15862.768
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4968
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## willdown ~
## build_nat (f1) -0.048 0.042 -1.133 0.257 -0.048 -0.040
## build_imp (d1) 0.145 0.049 2.956 0.003 0.145 0.123
## build_pn (e1) 0.462 0.041 11.347 0.000 0.462 0.403
## willshare_ki ~
## build_nat (f2) 0.026 0.035 0.757 0.449 0.026 0.027
## build_imp (d2) 0.221 0.041 5.378 0.000 0.221 0.229
## build_pn (e2) 0.293 0.037 7.920 0.000 0.293 0.313
## build_pn ~
## build_nat (b) 0.099 0.032 3.077 0.002 0.099 0.094
## build_imp (c) 0.566 0.034 16.652 0.000 0.566 0.548
## build_imp ~
## build_nat (a) 0.640 0.026 24.286 0.000 0.640 0.631
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willdown ~~
## .willshare_ki 0.367 0.085 4.319 0.000 0.367 0.146
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willdown 3.156 0.125 25.337 0.000 3.156 0.781
## .willshare_ki 2.010 0.132 15.232 0.000 2.010 0.746
## .build_pn 1.923 0.103 18.748 0.000 1.923 0.625
## .build_imp 1.739 0.078 22.190 0.000 1.739 0.602
##
## R-Square:
## Estimate
## willdown 0.219
## willshare_ki 0.254
## build_pn 0.375
## build_imp 0.398
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_willdown 0.306 0.031 10.016 0.000 0.306 0.255
## ind_willshar_k 0.276 0.029 9.454 0.000 0.276 0.282
## total_willdown 0.258 0.038 6.811 0.000 0.258 0.215
## total_wllshr_k 0.303 0.033 9.111 0.000 0.303 0.309summary(lavaan::sem(model_build, dIT, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 33 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 8 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Used Total
## Number of observations 1408 1409
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 1992.416
## Degrees of freedom 10
## 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) -10158.796
## Loglikelihood unrestricted model (H1) -10158.796
##
## Akaike (AIC) 20345.591
## Bayesian (BIC) 20419.090
## Sample-size adjusted Bayesian (SABIC) 20374.617
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4967
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## willdown ~
## build_nat (f1) 0.081 0.045 1.820 0.069 0.081 0.068
## build_imp (d1) 0.077 0.047 1.627 0.104 0.077 0.065
## build_pn (e1) 0.441 0.038 11.549 0.000 0.441 0.395
## willshare_ki ~
## build_nat (f2) 0.048 0.040 1.192 0.233 0.048 0.046
## build_imp (d2) 0.135 0.045 2.970 0.003 0.135 0.132
## build_pn (e2) 0.180 0.034 5.315 0.000 0.180 0.186
## build_pn ~
## build_nat (b) 0.125 0.039 3.237 0.001 0.125 0.117
## build_imp (c) 0.511 0.039 13.199 0.000 0.511 0.484
## build_imp ~
## build_nat (a) 0.702 0.024 29.476 0.000 0.702 0.693
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willdown ~~
## .willshare_ki 0.258 0.081 3.171 0.002 0.258 0.094
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willdown 2.946 0.111 26.551 0.000 2.946 0.776
## .willshare_ki 2.559 0.128 20.043 0.000 2.559 0.902
## .build_pn 2.049 0.093 21.942 0.000 2.049 0.673
## .build_imp 1.419 0.079 17.907 0.000 1.419 0.520
##
## R-Square:
## Estimate
## willdown 0.224
## willshare_ki 0.098
## build_pn 0.327
## build_imp 0.480
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_willdown 0.267 0.034 7.963 0.000 0.267 0.224
## ind_willshar_k 0.182 0.031 5.887 0.000 0.182 0.176
## total_willdown 0.349 0.034 10.186 0.000 0.349 0.292
## total_wllshr_k 0.230 0.030 7.566 0.000 0.230 0.222summary(lavaan::sem(model_build, dLIT, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 32 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 10 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Used Total
## Number of observations 1000 1008
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 1761.074
## Degrees of freedom 10
## 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) -7209.908
## Loglikelihood unrestricted model (H1) -7209.908
##
## Akaike (AIC) 14447.815
## Bayesian (BIC) 14516.524
## Sample-size adjusted Bayesian (SABIC) 14472.059
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4968
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## willdown ~
## build_nat (f1) 0.052 0.050 1.034 0.301 0.052 0.046
## build_imp (d1) 0.047 0.056 0.832 0.405 0.047 0.043
## build_pn (e1) 0.398 0.046 8.641 0.000 0.398 0.366
## willshare_ki ~
## build_nat (f2) 0.064 0.049 1.294 0.196 0.064 0.063
## build_imp (d2) 0.163 0.054 3.025 0.002 0.163 0.166
## build_pn (e2) 0.244 0.048 5.097 0.000 0.244 0.248
## build_pn ~
## build_nat (b) 0.158 0.044 3.619 0.000 0.158 0.154
## build_imp (c) 0.568 0.043 13.153 0.000 0.568 0.570
## build_imp ~
## build_nat (a) 0.723 0.027 26.779 0.000 0.723 0.706
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willdown ~~
## .willshare_ki 0.506 0.103 4.935 0.000 0.506 0.179
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willdown 3.135 0.153 20.494 0.000 3.135 0.819
## .willshare_ki 2.554 0.150 17.023 0.000 2.554 0.819
## .build_pn 1.702 0.103 16.499 0.000 1.702 0.527
## .build_imp 1.630 0.109 14.942 0.000 1.630 0.502
##
## R-Square:
## Estimate
## willdown 0.181
## willshare_ki 0.181
## build_pn 0.473
## build_imp 0.498
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_willdown 0.260 0.038 6.796 0.000 0.260 0.234
## ind_willshar_k 0.256 0.038 6.802 0.000 0.256 0.255
## total_willdown 0.312 0.039 7.951 0.000 0.312 0.280
## total_wllshr_k 0.320 0.038 8.467 0.000 0.320 0.319summary(lavaan::sem(model_build, dNL, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 36 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 8 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Used Total
## Number of observations 1075 1081
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 1271.386
## Degrees of freedom 10
## 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) -7820.727
## Loglikelihood unrestricted model (H1) -7820.727
##
## Akaike (AIC) 15669.454
## Bayesian (BIC) 15739.175
## Sample-size adjusted Bayesian (SABIC) 15694.708
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4964
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## willdown ~
## build_nat (f1) 0.024 0.052 0.456 0.648 0.024 0.017
## build_imp (d1) -0.022 0.054 -0.405 0.685 -0.022 -0.017
## build_pn (e1) 0.492 0.045 10.863 0.000 0.492 0.387
## willshare_ki ~
## build_nat (f2) 0.050 0.037 1.351 0.177 0.050 0.048
## build_imp (d2) 0.112 0.041 2.701 0.007 0.112 0.114
## build_pn (e2) 0.233 0.039 5.967 0.000 0.233 0.243
## build_pn ~
## build_nat (b) 0.081 0.038 2.106 0.035 0.081 0.074
## build_imp (c) 0.518 0.041 12.541 0.000 0.518 0.508
## build_imp ~
## build_nat (a) 0.676 0.028 24.060 0.000 0.676 0.634
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willdown ~~
## .willshare_ki 0.206 0.097 2.115 0.034 0.206 0.071
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willdown 3.762 0.143 26.289 0.000 3.762 0.852
## .willshare_ki 2.208 0.160 13.773 0.000 2.208 0.879
## .build_pn 1.886 0.100 18.779 0.000 1.886 0.689
## .build_imp 1.572 0.084 18.669 0.000 1.572 0.598
##
## R-Square:
## Estimate
## willdown 0.148
## willshare_ki 0.121
## build_pn 0.311
## build_imp 0.402
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_willdown 0.197 0.036 5.484 0.000 0.197 0.143
## ind_willshar_k 0.176 0.027 6.429 0.000 0.176 0.169
## total_willdown 0.221 0.045 4.881 0.000 0.221 0.160
## total_wllshr_k 0.225 0.037 6.149 0.000 0.225 0.216summary(lavaan::sem(model_build, dUK, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 48 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 8 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Used Total
## Number of observations 1050 1053
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 1483.169
## Degrees of freedom 10
## 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) -7965.424
## Loglikelihood unrestricted model (H1) -7965.424
##
## Akaike (AIC) 15958.848
## Bayesian (BIC) 16028.239
## Sample-size adjusted Bayesian (SABIC) 15983.773
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4952
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## willdown ~
## build_nat (f1) 0.119 0.049 2.418 0.016 0.119 0.096
## build_imp (d1) 0.107 0.051 2.093 0.036 0.107 0.093
## build_pn (e1) 0.364 0.043 8.391 0.000 0.364 0.326
## willshare_ki ~
## build_nat (f2) 0.101 0.039 2.603 0.009 0.101 0.094
## build_imp (d2) 0.213 0.044 4.786 0.000 0.213 0.214
## build_pn (e2) 0.200 0.037 5.377 0.000 0.200 0.207
## build_pn ~
## build_nat (b) 0.197 0.041 4.762 0.000 0.197 0.178
## build_imp (c) 0.477 0.038 12.444 0.000 0.477 0.464
## build_imp ~
## build_nat (a) 0.684 0.028 24.113 0.000 0.684 0.635
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willdown ~~
## .willshare_ki 0.499 0.099 5.046 0.000 0.499 0.159
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .willdown 3.612 0.137 26.296 0.000 3.612 0.800
## .willshare_ki 2.716 0.150 18.134 0.000 2.716 0.807
## .build_pn 2.342 0.110 21.215 0.000 2.342 0.649
## .build_imp 2.039 0.110 18.587 0.000 2.039 0.597
##
## R-Square:
## Estimate
## willdown 0.200
## willshare_ki 0.193
## build_pn 0.351
## build_imp 0.403
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_willdown 0.264 0.036 7.323 0.000 0.264 0.213
## ind_willshar_k 0.250 0.031 8.115 0.000 0.250 0.234
## total_willdown 0.382 0.038 9.963 0.000 0.382 0.309
## total_wllshr_k 0.351 0.036 9.873 0.000 0.351 0.328CCB
#path analysis overall
model_ccb <- '
gov ~ f1*ccb_nat + d1*ccb_imp + e1*ccb_pn
busi ~ f2*ccb_nat + d2*ccb_imp + e2*ccb_pn
cit ~ f3*ccb_nat + d3*ccb_imp + e3*ccb_pn
ccb_pn ~ b*ccb_nat + c*ccb_imp
ccb_imp ~ a*ccb_nat
#indirect effect
ind_gov := a*d1 + b*e1 + a*c*e1
ind_busi := a*d2 + b*e2 + a*c*e2
ind_cit := a*d3 + b*e3 + a*c*e3
#total effect
total_gov := f1 + a*d1 + b*e1 + a*c*e1
total_busi := f2 + a*d2 + b*e2 + a*c*e2
total_cit := f3 + a*d3 + b*e3 + a*c*e3
'
fit_ccb <- lavaan::sem(model_ccb, dEU)
#fit_ccb <- lavaan::sem(model_ccb, dEU, se = "bootstrap", bootstrap = 5000)
summary(fit_ccb, standardized = T, fit.measures = T , rsquare = TRUE)## lavaan 0.6-20 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 5651
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 22036.700
## Degrees of freedom 15
## 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) -45140.092
## Loglikelihood unrestricted model (H1) -45140.092
##
## Akaike (AIC) 90320.183
## Bayesian (BIC) 90452.975
## Sample-size adjusted Bayesian (SABIC) 90389.421
##
## 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|) Std.lv Std.all
## gov ~
## ccb_nat (f1) 0.114 0.017 6.889 0.000 0.114 0.100
## ccb_imp (d1) 0.306 0.018 17.084 0.000 0.306 0.283
## ccb_pn (e1) 0.373 0.014 26.126 0.000 0.373 0.360
## busi ~
## ccb_nat (f2) 0.136 0.016 8.437 0.000 0.136 0.120
## ccb_imp (d2) 0.307 0.018 17.513 0.000 0.307 0.286
## ccb_pn (e2) 0.360 0.014 25.763 0.000 0.360 0.351
## cit ~
## ccb_nat (f3) 0.128 0.015 8.278 0.000 0.128 0.114
## ccb_imp (d3) 0.251 0.017 15.002 0.000 0.251 0.236
## ccb_pn (e3) 0.446 0.013 33.340 0.000 0.446 0.437
## ccb_pn ~
## ccb_nat (b) 0.135 0.015 8.848 0.000 0.135 0.122
## ccb_imp (c) 0.624 0.014 43.213 0.000 0.624 0.598
## ccb_imp ~
## ccb_nat (a) 0.762 0.010 77.972 0.000 0.762 0.720
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .gov ~~
## .busi 0.967 0.027 35.477 0.000 0.967 0.535
## .cit 0.674 0.025 27.310 0.000 0.674 0.390
## .busi ~~
## .cit 0.845 0.025 33.615 0.000 0.845 0.500
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .gov 1.848 0.035 53.155 0.000 1.848 0.560
## .busi 1.767 0.033 53.155 0.000 1.767 0.546
## .cit 1.617 0.030 53.155 0.000 1.617 0.506
## .ccb_pn 1.600 0.030 53.155 0.000 1.600 0.522
## .ccb_imp 1.358 0.026 53.155 0.000 1.358 0.482
##
## R-Square:
## Estimate
## gov 0.440
## busi 0.454
## cit 0.494
## ccb_pn 0.478
## ccb_imp 0.518
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_gov 0.461 0.014 33.720 0.000 0.461 0.403
## ind_busi 0.453 0.013 33.914 0.000 0.453 0.400
## ind_cit 0.464 0.013 35.076 0.000 0.464 0.411
## total_gov 0.575 0.013 43.670 0.000 0.575 0.502
## total_busi 0.590 0.013 45.814 0.000 0.590 0.520
## total_cit 0.592 0.013 46.370 0.000 0.592 0.525lavaanPlot(model = fit_ccb, graph_options = list(rankdir = "LR"), node_options = list(shape = "box", fontname = "Helvetica"), edge_options = list(color = "grey"), coefs = TRUE, covs = FALSE, stand = TRUE)#path analysis per country with serial mediation
summary(lavaan::sem(model_ccb, dGER, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 15 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 21 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 1100
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 4478.209
## Degrees of freedom 15
## 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) -8749.763
## Loglikelihood unrestricted model (H1) -8749.763
##
## Akaike (AIC) 17539.526
## Bayesian (BIC) 17639.588
## Sample-size adjusted Bayesian (SABIC) 17576.063
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4985
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## gov ~
## ccb_nat (f1) 0.080 0.035 2.289 0.022 0.080 0.069
## ccb_imp (d1) 0.329 0.047 7.051 0.000 0.329 0.300
## ccb_pn (e1) 0.431 0.039 11.128 0.000 0.431 0.413
## busi ~
## ccb_nat (f2) 0.103 0.031 3.314 0.001 0.103 0.091
## ccb_imp (d2) 0.363 0.041 8.861 0.000 0.363 0.342
## ccb_pn (e2) 0.373 0.035 10.714 0.000 0.373 0.369
## cit ~
## ccb_nat (f3) 0.042 0.029 1.464 0.143 0.042 0.038
## ccb_imp (d3) 0.281 0.040 7.039 0.000 0.281 0.266
## ccb_pn (e3) 0.522 0.033 15.681 0.000 0.522 0.519
## ccb_pn ~
## ccb_nat (b) 0.029 0.034 0.848 0.397 0.029 0.025
## ccb_imp (c) 0.731 0.030 24.345 0.000 0.731 0.696
## ccb_imp ~
## ccb_nat (a) 0.677 0.029 23.054 0.000 0.677 0.636
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .gov ~~
## .busi 0.760 0.078 9.771 0.000 0.760 0.458
## .cit 0.510 0.065 7.864 0.000 0.510 0.328
## .busi ~~
## .cit 0.811 0.067 12.138 0.000 0.811 0.549
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .gov 1.750 0.105 16.644 0.000 1.750 0.506
## .busi 1.576 0.084 18.717 0.000 1.576 0.487
## .cit 1.384 0.070 19.790 0.000 1.384 0.431
## .ccb_pn 1.563 0.084 18.541 0.000 1.563 0.493
## .ccb_imp 1.711 0.096 17.856 0.000 1.711 0.596
##
## R-Square:
## Estimate
## gov 0.494
## busi 0.513
## cit 0.569
## ccb_pn 0.507
## ccb_imp 0.404
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_gov 0.449 0.031 14.305 0.000 0.449 0.384
## ind_busi 0.441 0.028 15.704 0.000 0.441 0.390
## ind_cit 0.464 0.029 15.752 0.000 0.464 0.412
## total_gov 0.529 0.035 15.084 0.000 0.529 0.452
## total_busi 0.544 0.033 16.347 0.000 0.544 0.481
## total_cit 0.506 0.034 14.843 0.000 0.506 0.449summary(lavaan::sem(model_ccb, dIT, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 28 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 1409
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 4704.565
## Degrees of freedom 15
## 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) -11279.278
## Loglikelihood unrestricted model (H1) -11279.278
##
## Akaike (AIC) 22598.556
## Bayesian (BIC) 22703.569
## Sample-size adjusted Bayesian (SABIC) 22640.036
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4972
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## gov ~
## ccb_nat (f1) 0.142 0.040 3.526 0.000 0.142 0.123
## ccb_imp (d1) 0.243 0.043 5.599 0.000 0.243 0.219
## ccb_pn (e1) 0.371 0.034 10.783 0.000 0.371 0.358
## busi ~
## ccb_nat (f2) 0.209 0.042 4.977 0.000 0.209 0.184
## ccb_imp (d2) 0.199 0.044 4.520 0.000 0.199 0.182
## ccb_pn (e2) 0.346 0.034 10.154 0.000 0.346 0.338
## cit ~
## ccb_nat (f3) 0.139 0.038 3.661 0.000 0.139 0.123
## ccb_imp (d3) 0.150 0.041 3.708 0.000 0.150 0.139
## ccb_pn (e3) 0.479 0.032 14.873 0.000 0.479 0.472
## ccb_pn ~
## ccb_nat (b) 0.212 0.038 5.529 0.000 0.212 0.190
## ccb_imp (c) 0.529 0.036 14.882 0.000 0.529 0.495
## ccb_imp ~
## ccb_nat (a) 0.739 0.021 35.510 0.000 0.739 0.709
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .gov ~~
## .busi 1.061 0.073 14.510 0.000 1.061 0.572
## .cit 0.621 0.073 8.524 0.000 0.621 0.353
## .busi ~~
## .cit 0.720 0.075 9.553 0.000 0.720 0.414
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .gov 1.880 0.087 21.704 0.000 1.880 0.624
## .busi 1.833 0.079 23.128 0.000 1.833 0.627
## .cit 1.651 0.083 19.904 0.000 1.651 0.573
## .ccb_pn 1.637 0.083 19.684 0.000 1.637 0.585
## .ccb_imp 1.217 0.069 17.627 0.000 1.217 0.497
##
## R-Square:
## Estimate
## gov 0.376
## busi 0.373
## cit 0.427
## ccb_pn 0.415
## ccb_imp 0.503
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_gov 0.404 0.032 12.550 0.000 0.404 0.349
## ind_busi 0.356 0.033 10.619 0.000 0.356 0.312
## ind_cit 0.400 0.032 12.517 0.000 0.400 0.354
## total_gov 0.546 0.030 18.281 0.000 0.546 0.472
## total_busi 0.565 0.029 19.651 0.000 0.565 0.496
## total_cit 0.539 0.029 18.556 0.000 0.539 0.477summary(lavaan::sem(model_ccb, dLIT, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 25 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 21 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 1008
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 3436.158
## Degrees of freedom 15
## 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) -8136.304
## Loglikelihood unrestricted model (H1) -8136.304
##
## Akaike (AIC) 16312.607
## Bayesian (BIC) 16410.922
## Sample-size adjusted Bayesian (SABIC) 16347.400
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4975
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## gov ~
## ccb_nat (f1) 0.157 0.043 3.645 0.000 0.157 0.146
## ccb_imp (d1) 0.287 0.048 5.986 0.000 0.287 0.278
## ccb_pn (e1) 0.315 0.044 7.097 0.000 0.315 0.306
## busi ~
## ccb_nat (f2) 0.146 0.056 2.622 0.009 0.146 0.135
## ccb_imp (d2) 0.227 0.057 3.973 0.000 0.227 0.219
## ccb_pn (e2) 0.329 0.047 6.994 0.000 0.329 0.319
## cit ~
## ccb_nat (f3) 0.236 0.047 4.975 0.000 0.236 0.230
## ccb_imp (d3) 0.180 0.050 3.620 0.000 0.180 0.182
## ccb_pn (e3) 0.293 0.042 6.959 0.000 0.293 0.299
## ccb_pn ~
## ccb_nat (b) 0.182 0.050 3.673 0.000 0.182 0.174
## ccb_imp (c) 0.507 0.046 11.064 0.000 0.507 0.504
## ccb_imp ~
## ccb_nat (a) 0.771 0.025 31.437 0.000 0.771 0.741
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .gov ~~
## .busi 1.046 0.088 11.943 0.000 1.046 0.549
## .cit 0.729 0.084 8.670 0.000 0.729 0.415
## .busi ~~
## .cit 0.848 0.096 8.848 0.000 0.848 0.458
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .gov 1.807 0.099 18.294 0.000 1.807 0.592
## .busi 2.008 0.112 17.943 0.000 2.008 0.653
## .cit 1.706 0.101 16.928 0.000 1.706 0.617
## .ccb_pn 1.692 0.112 15.165 0.000 1.692 0.586
## .ccb_imp 1.283 0.094 13.638 0.000 1.283 0.450
##
## R-Square:
## Estimate
## gov 0.408
## busi 0.347
## cit 0.383
## ccb_pn 0.414
## ccb_imp 0.550
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_gov 0.402 0.035 11.489 0.000 0.402 0.373
## ind_busi 0.364 0.044 8.206 0.000 0.364 0.337
## ind_cit 0.306 0.036 8.446 0.000 0.306 0.299
## total_gov 0.559 0.033 16.727 0.000 0.559 0.519
## total_busi 0.510 0.037 13.798 0.000 0.510 0.472
## total_cit 0.542 0.033 16.253 0.000 0.542 0.529summary(lavaan::sem(model_ccb, dNL, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 22 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 23 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 1081
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 5236.710
## Degrees of freedom 15
## 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) -7660.281
## Loglikelihood unrestricted model (H1) -7660.281
##
## Akaike (AIC) 15360.562
## Bayesian (BIC) 15460.275
## Sample-size adjusted Bayesian (SABIC) 15396.751
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4978
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## gov ~
## ccb_nat (f1) 0.110 0.048 2.286 0.022 0.110 0.099
## ccb_imp (d1) 0.331 0.054 6.120 0.000 0.331 0.317
## ccb_pn (e1) 0.309 0.039 7.867 0.000 0.309 0.315
## busi ~
## ccb_nat (f2) 0.075 0.044 1.683 0.092 0.075 0.068
## ccb_imp (d2) 0.399 0.050 8.040 0.000 0.399 0.386
## ccb_pn (e2) 0.307 0.037 8.384 0.000 0.307 0.315
## cit ~
## ccb_nat (f3) 0.086 0.043 1.984 0.047 0.086 0.077
## ccb_imp (d3) 0.409 0.049 8.402 0.000 0.409 0.393
## ccb_pn (e3) 0.329 0.036 9.162 0.000 0.329 0.336
## ccb_pn ~
## ccb_nat (b) 0.141 0.041 3.427 0.001 0.141 0.124
## ccb_imp (c) 0.678 0.037 18.209 0.000 0.678 0.638
## ccb_imp ~
## ccb_nat (a) 0.803 0.022 36.742 0.000 0.803 0.752
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .gov ~~
## .busi 1.003 0.061 16.530 0.000 1.003 0.716
## .cit 0.732 0.055 13.237 0.000 0.732 0.545
## .busi ~~
## .cit 0.728 0.054 13.379 0.000 0.728 0.576
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .gov 1.489 0.078 19.204 0.000 1.489 0.559
## .busi 1.319 0.063 21.083 0.000 1.319 0.504
## .cit 1.210 0.067 17.988 0.000 1.210 0.456
## .ccb_pn 1.265 0.072 17.593 0.000 1.265 0.458
## .ccb_imp 1.062 0.079 13.369 0.000 1.062 0.434
##
## R-Square:
## Estimate
## gov 0.441
## busi 0.496
## cit 0.544
## ccb_pn 0.542
## ccb_imp 0.566
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_gov 0.478 0.042 11.450 0.000 0.478 0.429
## ind_busi 0.531 0.039 13.772 0.000 0.531 0.481
## ind_cit 0.554 0.039 14.273 0.000 0.554 0.499
## total_gov 0.588 0.031 19.073 0.000 0.588 0.528
## total_busi 0.605 0.029 20.913 0.000 0.605 0.549
## total_cit 0.640 0.027 23.494 0.000 0.640 0.576summary(lavaan::sem(model_ccb, dUK, se = "bootstrap", bootstrap = 5000), standardized = T, fit.measures = T , rsquare = TRUE)## Warning: lavaan->lav_model_nvcov_bootstrap():
## 20 bootstrap runs failed or did not converge.## lavaan 0.6-20 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 1053
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 4255.509
## Degrees of freedom 15
## 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) -8681.212
## Loglikelihood unrestricted model (H1) -8681.212
##
## Akaike (AIC) 17402.423
## Bayesian (BIC) 17501.611
## Sample-size adjusted Bayesian (SABIC) 17438.088
##
## 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 Bootstrap
## Number of requested bootstrap draws 5000
## Number of successful bootstrap draws 4980
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## gov ~
## ccb_nat (f1) 0.054 0.044 1.219 0.223 0.054 0.046
## ccb_imp (d1) 0.335 0.050 6.651 0.000 0.335 0.307
## ccb_pn (e1) 0.391 0.043 9.061 0.000 0.391 0.377
## busi ~
## ccb_nat (f2) 0.102 0.045 2.300 0.021 0.102 0.088
## ccb_imp (d2) 0.334 0.048 7.027 0.000 0.334 0.307
## ccb_pn (e2) 0.402 0.038 10.728 0.000 0.402 0.390
## cit ~
## ccb_nat (f3) 0.156 0.043 3.605 0.000 0.156 0.137
## ccb_imp (d3) 0.189 0.050 3.803 0.000 0.189 0.177
## ccb_pn (e3) 0.492 0.038 12.972 0.000 0.492 0.488
## ccb_pn ~
## ccb_nat (b) 0.156 0.041 3.769 0.000 0.156 0.138
## ccb_imp (c) 0.642 0.038 16.905 0.000 0.642 0.608
## ccb_imp ~
## ccb_nat (a) 0.792 0.023 34.485 0.000 0.792 0.742
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .gov ~~
## .busi 0.749 0.086 8.663 0.000 0.749 0.380
## .cit 0.561 0.084 6.668 0.000 0.561 0.297
## .busi ~~
## .cit 0.904 0.085 10.643 0.000 0.904 0.510
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .gov 2.096 0.112 18.635 0.000 2.096 0.555
## .busi 1.849 0.103 17.999 0.000 1.849 0.494
## .cit 1.695 0.097 17.422 0.000 1.695 0.473
## .ccb_pn 1.714 0.100 17.223 0.000 1.714 0.486
## .ccb_imp 1.424 0.090 15.761 0.000 1.424 0.449
##
## R-Square:
## Estimate
## gov 0.445
## busi 0.506
## cit 0.527
## ccb_pn 0.514
## ccb_imp 0.551
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ind_gov 0.525 0.036 14.463 0.000 0.525 0.451
## ind_busi 0.531 0.039 13.727 0.000 0.531 0.458
## ind_cit 0.476 0.039 12.355 0.000 0.476 0.420
## total_gov 0.578 0.034 17.159 0.000 0.578 0.497
## total_busi 0.634 0.032 19.802 0.000 0.634 0.547
## total_cit 0.632 0.030 21.179 0.000 0.632 0.557