Employee awareness of rebound effects
Isabel Pacheco
2025-09-24
Overview of employees
plot_pie(dlabels, country)
plot_edu(dlabels, education)
plot_pie2(dlabels, division)
plot_pie(dlabels, gender)
plot_sus(dlabels, sustainability)
plot_pie2(dlabels, age) 
plot_position(dlabels, position)
plot_tenure(dlabels, tenure)
plot_size(dlabels, empno)
plot_influence(dlabels, influential)
#awareness of rebound effects
describe(d$reboundaware1)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 3391 3.94 2.09 4 3.93 2.97 1 7 6 -0.15 -1.33 0.04describeBy(d$reboundaware1, group = d$country)##
## Descriptive statistics by group
## group: 1
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 673 4.14 2.23 5 4.18 2.97 1 7 6 -0.25 -1.43 0.09
## ------------------------------------------------------------
## group: 2
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 781 3.56 2.1 4 3.46 2.97 1 7 6 0.08 -1.4 0.08
## ------------------------------------------------------------
## group: 3
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 796 3.85 2.03 4 3.83 2.97 1 7 6 -0.11 -1.32 0.07
## ------------------------------------------------------------
## group: 4
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 877 4.25 2.02 5 4.31 1.48 1 7 6 -0.33 -1.16 0.07
## ------------------------------------------------------------
## group: 5
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 264 3.81 1.86 4 3.81 1.48 1 7 6 -0.21 -1.01 0.11#strategies
describe(d$reboundaware2)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 3391 5.17 2.04 5 5.31 1.48 1 8 7 -0.4 -0.66 0.04describeBy(d$reboundaware2, group = d$country)##
## Descriptive statistics by group
## group: 1
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 673 5.47 2 6 5.68 1.48 1 8 7 -0.72 -0.25 0.08
## ------------------------------------------------------------
## group: 2
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 781 5.16 2.14 5 5.3 2.97 1 8 7 -0.35 -0.82 0.08
## ------------------------------------------------------------
## group: 3
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 796 5.15 1.99 5 5.27 1.48 1 8 7 -0.33 -0.6 0.07
## ------------------------------------------------------------
## group: 4
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 877 5.1 2 5 5.2 1.48 1 8 7 -0.35 -0.67 0.07
## ------------------------------------------------------------
## group: 5
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 264 4.77 2.05 5 4.82 1.48 1 8 7 -0.14 -0.8 0.13Awareness depending on various factors
Country
#Violin for rebound1
ggplot(d, aes(x = factor(country,
levels = 1:5,
labels = c("UK", "Germany", "NL", "Italy", "Lithuania")), y = reboundaware1, fill = factor(country))) + # Ensure 'country' is #categorical
geom_violin(trim = FALSE, alpha = 0.5) + # Violin plot with transparency
geom_boxplot(width = 0.2, outlier.shape = NA, aes(color = factor(country)), show.legend = FALSE) +
stat_summary(fun = mean, geom = "point", shape = 18, size = 3, color = "darkred") + # Mean point
scale_fill_brewer(palette = "Dark2") + # Use Dark2 color palette for fill
scale_color_brewer(palette = "Dark2") + # Use Dark2 color palette for boxplot outlines
theme_minimal() +
scale_y_continuous(
breaks = 0:8, # full scale breaks (adjust if needed)
labels = c(" ", "(1) Not at all", "(2)", "(3)", "(4)", "(5)", "(6)", "(7) To a great extent", "")
) + theme(legend.position = "none")
###recoding answers indicating "I dont know" from 8 to 0
table(d$reboundaware2)##
## 1 2 3 4 5 6 7 8
## 243 172 276 464 677 567 453 539d$reboundaware2[d$reboundaware2 == 8] <- 0
describe(d$reboundaware2)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 3391 3.9 2.35 5 4 1.48 0 7 7 -0.45 -1.09 0.04#Violin for rebound2
ggplot(d, aes(x = factor(country,
levels = 1:5,
labels = c("UK", "Germany", "NL", "Italy", "Lithuania")), y = reboundaware2, fill = factor(country))) + # Ensure 'country' is categorical
geom_violin(trim = FALSE, alpha = 0.5) + # Violin plot with transparency
geom_boxplot(width = 0.2, outlier.shape = NA, aes(color = factor(country)), show.legend = FALSE) +
stat_summary(fun = mean, geom = "point", shape = 18, size = 3, color = "darkred") + # Mean point
scale_fill_brewer(palette = "Dark2") + # Use Dark2 color palette for fill
scale_color_brewer(palette = "Dark2") + # Use Dark2 color palette for boxplot outlines
theme_minimal() +
scale_y_continuous(
breaks = 0:8, # full scale breaks (adjust if needed)
labels = c(" ", "(1) Not at all", "(2)", "(3)", "(4)", "(5)", "(6)", "(7) To a great extent", "")
) + theme(legend.position = "none")
Sector
#Violin for rebound1
ggplot(d, aes(x = industry_new, y = reboundaware1, fill = factor(industry_new))) + # Ensure 'country' is categorical
geom_violin(trim = FALSE, alpha = 0.5) + # Violin plot with transparency
geom_boxplot(width = 0.2, outlier.shape = NA, aes(color = factor(industry_new)), show.legend = FALSE) +
stat_summary(fun = mean, geom = "point", shape = 18, size = 3, color = "darkred") + # Mean point
scale_fill_brewer(palette = "Dark2") + # Use Dark2 color palette for fill
scale_color_brewer(palette = "Dark2") + # Use Dark2 color palette for boxplot outlines
theme_minimal() +
scale_y_continuous(
breaks = 0:8, # full scale breaks (adjust if needed)
labels = c(" ", "(1) Not at all", "(2)", "(3)", "(4)", "(5)", "(6)", "(7) To a great extent", "")
) + theme(legend.position = "none")
# Check sig mean differences
anova_rebound1 <- aov(reboundaware1 ~ industry_new, data = d)
summary(anova_rebound1)## Df Sum Sq Mean Sq F value Pr(>F)
## industry_new 2 80 40.15 9.257 9.79e-05 ***
## Residuals 3388 14696 4.34
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1#Violin for rebound2
ggplot(d, aes(x = industry_new, y = reboundaware2, fill = factor(industry_new))) + # Ensure 'country' is categorical
geom_violin(trim = FALSE, alpha = 0.5) + # Violin plot with transparency
geom_boxplot(width = 0.2, outlier.shape = NA, aes(color = factor(industry_new)), show.legend = FALSE) +
stat_summary(fun = mean, geom = "point", shape = 18, size = 3, color = "darkred") + # Mean point
scale_fill_brewer(palette = "Dark2") + # Use Dark2 color palette for fill
scale_color_brewer(palette = "Dark2") + # Use Dark2 color palette for boxplot outlines
theme_minimal() +
scale_y_continuous(
breaks = 0:8, # full scale breaks (adjust if needed)
labels = c(" ", "(1) Not at all", "(2)", "(3)", "(4)", "(5)", "(6)", "(7) To a great extent", "")
) + theme(legend.position = "none")
### boxplot
summary_df <- d %>%
group_by(industry_new) %>%
summarise(
mean = mean(reboundaware2, na.rm = TRUE),
sd = sd(reboundaware2, na.rm = TRUE),
n = sum(!is.na(reboundaware2)),
se = sd / sqrt(n)
)
ggplot(summary_df, aes(x = industry_new, y = mean, fill = industry_new)) +
geom_col(alpha = 0.8) +
geom_errorbar(aes(ymin = mean - se, ymax = mean + se), width = 0.2) +
scale_fill_brewer(palette = "Dark2") +
theme_minimal() +
theme(legend.position = "none") +
labs(
x = "Industry",
y = "Mean reboundaware2 (± SE)"
) +
scale_y_continuous(
breaks = 0:8,
labels = c(" ", "(1) Not at all", "(2)", "(3)", "(4)", "(5)", "(6)", "(7) To a great extent", "")
)
anova_rebound2 <- aov(reboundaware2 ~ industry_new, data = d)
summary(anova_rebound2)## Df Sum Sq Mean Sq F value Pr(>F)
## industry_new 2 79 39.65 7.19 0.000765 ***
## Residuals 3388 18685 5.51
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Awareness differences depending on country and sector
###rebound1
## country
describeBy(d$reboundaware1, group = d$country)##
## Descriptive statistics by group
## group: 1
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 673 4.14 2.23 5 4.18 2.97 1 7 6 -0.25 -1.43 0.09
## ------------------------------------------------------------
## group: 2
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 781 3.56 2.1 4 3.46 2.97 1 7 6 0.08 -1.4 0.08
## ------------------------------------------------------------
## group: 3
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 796 3.85 2.03 4 3.83 2.97 1 7 6 -0.11 -1.32 0.07
## ------------------------------------------------------------
## group: 4
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 877 4.25 2.02 5 4.31 1.48 1 7 6 -0.33 -1.16 0.07
## ------------------------------------------------------------
## group: 5
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 264 3.81 1.86 4 3.81 1.48 1 7 6 -0.21 -1.01 0.11# Check sig mean differences
anova_rebound1 <- aov(reboundaware1 ~ country, data = d)
summary(anova_rebound1)## Df Sum Sq Mean Sq F value Pr(>F)
## country 4 234 58.59 13.64 4.9e-11 ***
## Residuals 3386 14542 4.29
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1tukey_rebound1 <- TukeyHSD(anova_rebound1)
library(effectsize)##
## Attaching package: 'effectsize'## The following object is masked from 'package:psych':
##
## phieta_squared(aov(reboundaware1 ~ country, data = d))## For one-way between subjects designs, partial eta squared is equivalent
## to eta squared. Returning eta squared.## # Effect Size for ANOVA
##
## Parameter | Eta2 | 95% CI
## -------------------------------
## country | 0.02 | [0.01, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].industry
describeBy(d$reboundaware1, group = d$industry_new)##
## Descriptive statistics by group
## group: Building
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1262 3.95 2.1 4 3.94 2.97 1 7 6 -0.18 -1.36 0.06
## ------------------------------------------------------------
## group: Manufacturing
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1494 4.06 2.04 4 4.08 2.97 1 7 6 -0.23 -1.23 0.05
## ------------------------------------------------------------
## group: Mobility
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 635 3.64 2.14 4 3.55 2.97 1 7 6 0.1 -1.39 0.08summary(aov(reboundaware1 ~ industry_new, data = d))## Df Sum Sq Mean Sq F value Pr(>F)
## industry_new 2 80 40.15 9.257 9.79e-05 ***
## Residuals 3388 14696 4.34
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1tukey_bio <- TukeyHSD(aov(reboundaware1 ~ industry_new, data = d))
library(effectsize)
eta_squared(aov(reboundaware1 ~ industry_new, data = d))## For one-way between subjects designs, partial eta squared is equivalent
## to eta squared. Returning eta squared.## # Effect Size for ANOVA
##
## Parameter | Eta2 | 95% CI
## --------------------------------------
## industry_new | 5.43e-03 | [0.00, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].Company size
d$empno <- as.factor(d$empno)
describeBy(d$reboundaware1, group = d$empno)##
## Descriptive statistics by group
## group: 1
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 388 3.3 2.07 3 3.14 2.97 1 7 6 0.3 -1.26 0.11
## ------------------------------------------------------------
## group: 2
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 558 3.68 2.05 4 3.61 2.97 1 7 6 0.02 -1.34 0.09
## ------------------------------------------------------------
## group: 3
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 650 4.03 1.99 4 4.03 2.97 1 7 6 -0.23 -1.17 0.08
## ------------------------------------------------------------
## group: 4
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 525 4.37 2 5 4.47 1.48 1 7 6 -0.46 -1.03 0.09
## ------------------------------------------------------------
## group: 5
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 414 4.67 1.83 5 4.83 1.48 1 7 6 -0.71 -0.56 0.09
## ------------------------------------------------------------
## group: 6
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 856 3.73 2.21 4 3.66 2.97 1 7 6 0.05 -1.48 0.08summary(aov(reboundaware1 ~ empno, data = d))## Df Sum Sq Mean Sq F value Pr(>F)
## empno 5 561 112.2 26.72 <2e-16 ***
## Residuals 3385 14216 4.2
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1tukey_bio <- TukeyHSD(aov(reboundaware1 ~ empno, data = d))
library(effectsize)
eta_squared(aov(reboundaware1 ~ empno, data = d))## For one-way between subjects designs, partial eta squared is equivalent
## to eta squared. Returning eta squared.## # Effect Size for ANOVA
##
## Parameter | Eta2 | 95% CI
## -------------------------------
## empno | 0.04 | [0.03, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].#figure
ggplot(d, aes(x = factor(empno,
levels = 1:7,
labels = c("Less than 10", "11-50", "51-150", "151-300","301-500",
"More than 500", "Self-employed")), y = reboundaware1, fill = factor(empno))) +
geom_violin(trim = FALSE, alpha = 0.5) + # Violin plot with transparency
geom_boxplot(width = 0.2, outlier.shape = NA, aes(color = factor(empno)), show.legend = FALSE) +
stat_summary(fun = mean, geom = "point", shape = 18, size = 3, color = "darkred") + # Mean point
scale_fill_brewer(palette = "Dark2") +
scale_color_brewer(palette = "Dark2") +
theme_minimal() +
scale_y_continuous(
breaks = 0:8, # full scale breaks (adjust if needed)
labels = c(" ", "(1) Not at all", "(2)", "(3)", "(4)", "(5)", "(6)", "(7) To a great extent", "")
) + theme(legend.position = "none")
division
describeBy(d$reboundaware1, group = d$division)##
## Descriptive statistics by group
## group: 1
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1301 3.58 2.08 4 3.49 2.97 1 7 6 0.09 -1.38 0.06
## ------------------------------------------------------------
## group: 2
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 321 4.19 2.07 5 4.24 1.48 1 7 6 -0.4 -1.16 0.12
## ------------------------------------------------------------
## group: 3
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 333 4.75 1.8 5 4.93 1.48 1 7 6 -0.67 -0.43 0.1
## ------------------------------------------------------------
## group: 4
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 411 4.02 2.04 4 4.03 2.97 1 7 6 -0.21 -1.27 0.1
## ------------------------------------------------------------
## group: 5
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 298 4.31 2.05 5 4.38 2.97 1 7 6 -0.35 -1.19 0.12
## ------------------------------------------------------------
## group: 6
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 365 4.7 1.94 5 4.88 1.48 1 7 6 -0.68 -0.7 0.1
## ------------------------------------------------------------
## group: 7
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 362 3.12 2.01 3 2.94 2.97 1 7 6 0.42 -1.16 0.11summary(aov(reboundaware1 ~ division, data = d))## Df Sum Sq Mean Sq F value Pr(>F)
## division 1 36 36.02 8.281 0.00403 **
## Residuals 3389 14741 4.35
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov(reboundaware1 ~ division, data = d))## For one-way between subjects designs, partial eta squared is equivalent
## to eta squared. Returning eta squared.## # Effect Size for ANOVA
##
## Parameter | Eta2 | 95% CI
## -----------------------------------
## division | 2.44e-03 | [0.00, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].ggplot(d, aes(x = factor(division,
levels = 1:7,
labels = c("Operations", "Finance", "Human Resources (HR)", "Marketing & Sales", "Research & Development", "Information Technology (IT)", "Other:")), y = reboundaware1, fill = factor(division))) +
geom_violin(trim = FALSE, alpha = 0.5) + # Violin plot with transparency
geom_boxplot(width = 0.2, outlier.shape = NA, aes(color = factor(division)), show.legend = FALSE) +
stat_summary(fun = mean, geom = "point", shape = 18, size = 3, color = "darkred") + # Mean point
scale_fill_brewer(palette = "Dark2") +
scale_color_brewer(palette = "Dark2") +
theme_minimal() +
scale_y_continuous(
breaks = 0:8, # full scale breaks (adjust if needed)
labels = c(" ", "(1) Not at all", "(2)", "(3)", "(4)", "(5)", "(6)", "(7) To a great extent", "")
) + theme(legend.position = "none")
position
describeBy(d$reboundaware1, group = d$position)##
## Descriptive statistics by group
## group: 1
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1358 3.36 2.14 3 3.21 2.97 1 7 6 0.26 -1.38 0.06
## ------------------------------------------------------------
## group: 2
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1267 4.27 1.95 5 4.34 1.48 1 7 6 -0.39 -1.03 0.05
## ------------------------------------------------------------
## group: 3
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 641 4.64 1.91 5 4.8 1.48 1 7 6 -0.58 -0.76 0.08
## ------------------------------------------------------------
## group: 4
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 125 3.4 1.99 4 3.3 2.97 1 7 6 0.18 -1.28 0.18summary(aov(reboundaware1 ~ position, data = d))## Df Sum Sq Mean Sq F value Pr(>F)
## position 1 498 497.9 118.2 <2e-16 ***
## Residuals 3389 14279 4.2
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov(reboundaware1 ~ position, data = d))## For one-way between subjects designs, partial eta squared is equivalent
## to eta squared. Returning eta squared.## # Effect Size for ANOVA
##
## Parameter | Eta2 | 95% CI
## -------------------------------
## position | 0.03 | [0.02, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].ggplot(d, aes(x = factor(position,
levels = 1:4,
labels = c("Team member / Employee (no management responsibilities)", "Middle management (e.g., supervising others, team lead)", "Senior or upper management", "Other")), y = reboundaware1, fill = factor(position))) +
geom_violin(trim = FALSE, alpha = 0.5) + # Violin plot with transparency
geom_boxplot(width = 0.2, outlier.shape = NA, aes(color = factor(position)), show.legend = FALSE) +
stat_summary(fun = mean, geom = "point", shape = 18, size = 3, color = "darkred") + # Mean point
scale_fill_brewer(palette = "Dark2") +
scale_color_brewer(palette = "Dark2") +
theme_minimal() +
scale_y_continuous(
breaks = 0:8, # full scale breaks (adjust if needed)
labels = c(" ", "(1) Not at all", "(2)", "(3)", "(4)", "(5)", "(6)", "(7) To a great extent", "")
) + theme(legend.position = "none")
tenure
describeBy(d$reboundaware1, group = d$tenure)##
## Descriptive statistics by group
## group: 1
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 150 3.1 2.05 3 2.9 2.97 1 7 6 0.46 -1.13 0.17
## ------------------------------------------------------------
## group: 2
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 509 3.87 2.11 4 3.84 2.97 1 7 6 -0.1 -1.41 0.09
## ------------------------------------------------------------
## group: 3
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 687 4.18 1.96 5 4.23 1.48 1 7 6 -0.37 -1.04 0.07
## ------------------------------------------------------------
## group: 4
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 689 4.44 2.02 5 4.55 1.48 1 7 6 -0.46 -1.02 0.08
## ------------------------------------------------------------
## group: 5
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 479 4.2 2.08 5 4.24 1.48 1 7 6 -0.29 -1.21 0.09
## ------------------------------------------------------------
## group: 6
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 346 3.69 2.09 4 3.62 2.97 1 7 6 0.04 -1.42 0.11
## ------------------------------------------------------------
## group: 7
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 531 3.23 2.06 3 3.08 2.97 1 7 6 0.31 -1.35 0.09summary(aov(reboundaware1 ~ tenure, data = d))## Df Sum Sq Mean Sq F value Pr(>F)
## tenure 1 77 77.19 17.8 2.52e-05 ***
## Residuals 3389 14699 4.34
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1eta_squared(aov(reboundaware1 ~ tenure, data = d))## For one-way between subjects designs, partial eta squared is equivalent
## to eta squared. Returning eta squared.## # Effect Size for ANOVA
##
## Parameter | Eta2 | 95% CI
## -----------------------------------
## tenure | 5.22e-03 | [0.00, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].#figure
ggplot(d, aes(x = factor(tenure,
levels = 1:7,
labels = c("Less than 12 months", "1-3 years", "4-6 years", "7-10 years", "11-15 years", "15-20 years", "More than 20 years")), y = reboundaware1, fill = factor(tenure))) +
geom_violin(trim = FALSE, alpha = 0.5) + # Violin plot with transparency
geom_boxplot(width = 0.2, outlier.shape = NA, aes(color = factor(tenure)), show.legend = FALSE) +
stat_summary(fun = mean, geom = "point", shape = 18, size = 3, color = "darkred") + # Mean point
scale_fill_brewer(palette = "Dark2") +
scale_color_brewer(palette = "Dark2") +
theme_minimal() +
scale_y_continuous(
breaks = 0:8, # full scale breaks (adjust if needed)
labels = c(" ", "(1) Not at all", "(2)", "(3)", "(4)", "(5)", "(6)", "(7) To a great extent", "")
) + theme(legend.position = "none")
Sustainability as part of job description
describeBy(d$reboundaware1, group = d$sustainability)##
## Descriptive statistics by group
## group: 1
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 601 2.05 1.6 1 1.72 0 1 7 6 1.44 0.97 0.07
## ------------------------------------------------------------
## group: 2
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 537 3.12 1.96 3 2.97 2.97 1 7 6 0.42 -1.15 0.08
## ------------------------------------------------------------
## group: 3
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 915 3.98 1.85 4 4.01 1.48 1 7 6 -0.24 -1.04 0.06
## ------------------------------------------------------------
## group: 4
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 857 4.8 1.67 5 4.97 1.48 1 7 6 -0.78 -0.06 0.06
## ------------------------------------------------------------
## group: 5
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 481 5.63 1.54 6 5.9 1.48 1 7 6 -1.34 1.43 0.07summary(lm(reboundaware1 ~ sustainability, data = d))##
## Call:
## lm(formula = reboundaware1 ~ sustainability, data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.6963 -1.1463 0.0787 1.1912 4.8537
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.25875 0.07575 16.62 <2e-16 ***
## sustainability 0.88750 0.02302 38.56 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.741 on 3389 degrees of freedom
## Multiple R-squared: 0.3049, Adjusted R-squared: 0.3047
## F-statistic: 1487 on 1 and 3389 DF, p-value: < 2.2e-16eta_squared(lm(reboundaware1 ~ sustainability, data = d))## For one-way between subjects designs, partial eta squared is equivalent
## to eta squared. Returning eta squared.## # Effect Size for ANOVA
##
## Parameter | Eta2 | 95% CI
## ------------------------------------
## sustainability | 0.30 | [0.28, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].#figure
ggplot(d, aes(x = factor(sustainability,
levels = 1:5,
labels = c("Not at all", "Hardly", "Somewhat", "Fairly", "Very much")), y = reboundaware1, fill = factor(sustainability))) +
geom_violin(trim = FALSE, alpha = 0.5) +
geom_boxplot(width = 0.2, outlier.shape = NA, aes(color = factor(sustainability)), show.legend = FALSE) +
stat_summary(fun = mean, geom = "point", shape = 18, size = 3, color = "darkred") + # Mean point
scale_fill_brewer(palette = "Dark2") +
scale_color_brewer(palette = "Dark2") +
theme_minimal() +
scale_y_continuous(
breaks = 0:8, # full scale breaks (adjust if needed)
labels = c(" ", "(1) Not at all", "(2)", "(3)", "(4)", "(5)", "(6)", "(7) To a great extent", "")
) + theme(legend.position = "none")
Correlation matrix
library(corrplot)## corrplot 0.95 loadedd$position[d$position == 4] <- NA
d$gender <- as.factor(d$gender)
d$country_base <- as.factor(d$country_base)
d$division <- as.factor(d$division)
d$industry_new <- as.factor(d$industry_new)
d$empno <- as.numeric(d$empno)
d$tenure <- as.numeric(d$tenure)
d$position <- as.numeric(d$position)
#overall table
var <- d[, c("age","gender", "education", "country_base",
"sustainability", "position", "division", "tenure",
"industry_new", "empno",
"bio_val", "ego_val", "pa", "ccb_ar",
"se", "ar1_employee", "ar3_employee", "ar4_employee",
"sn", "ar1_org", "ar3_org", "ar4_org", "cer",
"wpeb3", "ar5_org", "cer3",
"reboundaware1")]
var_num <- var[, sapply(var, is.numeric)] # only numerical variables
cor_matrix <- cor(var_num, use = "complete.obs")
corrplot(cor_matrix, method = "color", type = "lower", col = brewer.pal(n = 10, name = "RdYlBu"), addCoef.col = "black", tl.col = "black", tl.srt = 45,diag = FALSE) 
apaTables::apa.cor.table(
var_num,
filename = "Table_Correlations.doc",
table.number = 1,
show.conf.interval = TRUE
)##
##
## Table 1
##
## Means, standard deviations, and correlations with confidence intervals
##
##
## Variable M SD 1 2 3 4
## 1. age 3.49 1.33
##
## 2. education 4.90 1.70 -.14**
## [-.17, -.11]
##
## 3. sustainability 3.02 1.30 -.25** .17**
## [-.28, -.22] [.14, .21]
##
## 4. position 1.78 0.75 -.05** .31** .34**
## [-.09, -.02] [.28, .34] [.31, .37]
##
## 5. tenure 4.18 1.77 .52** -.05** -.07** .08**
## [.50, .55] [-.08, -.02] [-.10, -.04] [.04, .11]
##
## 6. empno 3.76 1.72 -.07** .18** .10** .05**
## [-.11, -.04] [.15, .21] [.07, .14] [.01, .08]
##
## 7. bio_val 5.13 1.63 .03 .09** .23** .09**
## [-.01, .06] [.06, .13] [.19, .26] [.06, .13]
##
## 8. ego_val 4.22 1.75 -.21** .16** .41** .17**
## [-.24, -.18] [.12, .19] [.39, .44] [.14, .20]
##
## 9. pa 5.33 1.47 .02 .04** .12** .04*
## [-.02, .05] [.01, .08] [.08, .15] [.01, .07]
##
## 10. ccb_ar 4.72 1.65 -.11** .10** .37** .14**
## [-.14, -.08] [.07, .14] [.34, .40] [.11, .17]
##
## 11. se 5.04 1.41 -.08** .12** .46** .22**
## [-.11, -.04] [.09, .16] [.44, .49] [.19, .25]
##
## 12. ar1_employee 5.14 1.56 -.00 .08** .30** .14**
## [-.04, .03] [.04, .11] [.26, .33] [.11, .18]
##
## 13. ar3_employee 5.17 1.54 -.02 .06** .30** .13**
## [-.05, .02] [.03, .10] [.27, .33] [.10, .16]
##
## 14. ar4_employee 5.24 1.49 .01 .07** .30** .11**
## [-.03, .04] [.04, .10] [.27, .33] [.08, .15]
##
## 15. sn 5.05 1.45 -.07** .10** .48** .21**
## [-.10, -.04] [.07, .13] [.45, .50] [.18, .25]
##
## 16. ar1_org 5.40 1.41 .00 .08** .21** .09**
## [-.03, .04] [.05, .11] [.18, .24] [.06, .12]
##
## 17. ar3_org 5.44 1.39 .01 .07** .23** .08**
## [-.03, .04] [.04, .11] [.19, .26] [.04, .11]
##
## 18. ar4_org 5.37 1.42 .01 .08** .26** .10**
## [-.03, .04] [.05, .11] [.23, .29] [.06, .13]
##
## 19. cer 5.14 1.42 -.02 .11** .43** .18**
## [-.05, .01] [.08, .14] [.40, .46] [.15, .21]
##
## 20. wpeb3 4.63 1.75 -.11** .15** .53** .26**
## [-.15, -.08] [.11, .18] [.50, .55] [.23, .30]
##
## 21. ar5_org 5.13 1.39 -.04* .07** .36** .14**
## [-.07, -.00] [.04, .11] [.34, .39] [.10, .17]
##
## 22. cer3 5.03 1.55 -.04* .11** .43** .17**
## [-.07, -.00] [.08, .14] [.40, .45] [.14, .20]
##
## 23. reboundaware1 3.94 2.09 -.26** .15** .55** .24**
## [-.30, -.23] [.12, .18] [.53, .58] [.21, .28]
##
## 5 6 7 8 9 10
##
##
##
##
##
##
##
##
##
##
##
##
##
##
## .06**
## [.03, .10]
##
## .05** .08**
## [.01, .08] [.05, .11]
##
## -.06** .11** .42**
## [-.10, -.03] [.07, .14] [.40, .45]
##
## .04* .06** .45** .26**
## [.01, .08] [.03, .10] [.42, .47] [.23, .30]
##
## -.01 .08** .43** .40** .40**
## [-.04, .02] [.05, .12] [.40, .46] [.37, .43] [.37, .43]
##
## .02 .07** .51** .48** .34** .49**
## [-.02, .05] [.04, .10] [.48, .53] [.45, .50] [.31, .37] [.46, .51]
##
## .06** .07** .46** .36** .29** .41**
## [.02, .09] [.04, .11] [.43, .48] [.34, .39] [.26, .32] [.38, .44]
##
## .04* .06** .40** .37** .28** .36**
## [.01, .07] [.02, .09] [.37, .43] [.34, .40] [.25, .31] [.33, .39]
##
## .05** .08** .48** .39** .31** .38**
## [.01, .08] [.05, .11] [.45, .50] [.36, .41] [.28, .34] [.36, .41]
##
## .04* .06** .49** .47** .34** .50**
## [.01, .07] [.03, .10] [.46, .51] [.44, .50] [.31, .37] [.47, .52]
##
## .04* .15** .42** .28** .27** .32**
## [.01, .08] [.11, .18] [.39, .45] [.25, .31] [.24, .30] [.28, .35]
##
## .06** .15** .44** .31** .31** .32**
## [.03, .10] [.12, .19] [.41, .46] [.28, .34] [.28, .34] [.29, .35]
##
## .06** .14** .43** .34** .28** .34**
## [.02, .09] [.11, .17] [.41, .46] [.31, .37] [.25, .31] [.31, .37]
##
## .05** .17** .40** .41** .26** .37**
## [.02, .08] [.14, .21] [.37, .43] [.39, .44] [.23, .29] [.34, .40]
##
## -.01 .07** .39** .46** .26** .46**
## [-.04, .03] [.04, .10] [.36, .42] [.44, .49] [.22, .29] [.44, .49]
##
## .05** .15** .36** .35** .22** .31**
## [.02, .09] [.12, .18] [.33, .39] [.32, .38] [.18, .25] [.28, .34]
##
## .05** .20** .35** .40** .23** .33**
## [.02, .09] [.17, .23] [.32, .38] [.37, .42] [.19, .26] [.30, .36]
##
## -.07** .08** .17** .44** .19** .43**
## [-.11, -.04] [.04, .11] [.14, .21] [.41, .47] [.16, .23] [.40, .45]
##
## 11 12 13 14 15 16 17
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
## .52**
## [.50, .55]
##
## .52** .64**
## [.50, .54] [.62, .66]
##
## .54** .64** .67**
## [.52, .57] [.62, .66] [.65, .69]
##
## .78** .49** .48** .50**
## [.77, .79] [.46, .51] [.45, .50] [.48, .53]
##
## .41** .61** .48** .50** .39**
## [.39, .44] [.59, .63] [.45, .51] [.48, .53] [.37, .42]
##
## .45** .53** .63** .55** .41** .60**
## [.42, .48] [.51, .55] [.61, .65] [.52, .57] [.38, .44] [.58, .62]
##
## .46** .54** .53** .68** .44** .60** .61**
## [.43, .49] [.51, .56] [.50, .55] [.66, .70] [.42, .47] [.57, .62] [.58, .63]
##
## .61** .42** .40** .43** .62** .41** .40**
## [.59, .63] [.40, .45] [.37, .43] [.40, .46] [.60, .64] [.39, .44] [.37, .42]
##
## .66** .42** .41** .43** .67** .31** .34**
## [.64, .68] [.39, .45] [.38, .44] [.40, .46] [.65, .69] [.28, .34] [.31, .37]
##
## .51** .47** .47** .49** .51** .50** .50**
## [.49, .54] [.45, .50] [.44, .49] [.46, .52] [.48, .53] [.48, .53] [.47, .52]
##
## .57** .39** .35** .39** .57** .37** .36**
## [.54, .59] [.36, .42] [.32, .38] [.37, .42] [.54, .59] [.34, .40] [.33, .39]
##
## .42** .25** .27** .25** .43** .13** .17**
## [.40, .45] [.21, .28] [.24, .30] [.22, .29] [.41, .46] [.09, .16] [.13, .20]
##
## 18 19 20 21 22
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
## .46**
## [.43, .48]
##
## .37** .55**
## [.34, .40] [.52, .57]
##
## .53** .58** .44**
## [.51, .56] [.56, .60] [.42, .47]
##
## .42** .79** .53** .54**
## [.39, .45] [.78, .80] [.51, .55] [.51, .56]
##
## .19** .33** .48** .27** .34**
## [.16, .22] [.30, .36] [.45, .50] [.24, .31] [.31, .37]
##
##
## Note. M and SD are used to represent mean and standard deviation, respectively.
## Values in square brackets indicate the 95% confidence interval.
## The confidence interval is a plausible range of population correlations
## that could have caused the sample correlation (Cumming, 2014).
## * indicates p < .05. ** indicates p < .01.
## #correlation figure with focus on reboundaware1
target <- "reboundaware1"
df_plot <- map_dfr(
setdiff(names(var_num), target),
function(v) {
ct <- cor.test(
var_num[[v]],
var_num[[target]],
method = "pearson",
use = "pairwise.complete.obs"
)
tibble(
variable = v,
r = unname(ct$estimate),
lower = ct$conf.int[1],
upper = ct$conf.int[2],
p = ct$p.value
)
}
)
library(ggplot2)
ggplot(df_plot, aes(x = r, y = reorder(variable, r))) +
geom_vline(xintercept = 0, linetype = "dashed", color = "grey60") +
geom_errorbarh(aes(xmin = lower, xmax = upper), height = .2) +
geom_point(size = 3) +
labs(
x = "Correlation with Rebound Awareness (r)",
y = NULL
) +
theme_classic(base_size = 12)## Warning: `geom_errobarh()` was deprecated in ggplot2 4.0.0.
## ℹ Please use the `orientation` argument of `geom_errorbar()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## `height` was translated to `width`.
Correlational network
library(qgraph)
qgraph(cor_matrix,
layout = "spring", # Layout algorithm
vsize = 7, # Size of the nodes
esize = 20, # Edge size scaling
minimum = 0.2, # Show edges only if correlation > 0.2
cut = 0.5, # Threshold for line width
labels = colnames(vars), # Use variable names as labels
color = "#74ADD1",
edge.color = "#313695",
edge.labels = TRUE
) 
Regression
All variables together
#complete cases
d_cc <- d[complete.cases(d[, c(
"age","gender","education","country_base",
"sustainability","position","division","tenure",
"industry_new","empno",
"bio_val","ego_val","pa","ccb_ar",
"se","ar1_employee", "ar3_employee","ar4_employee",
"sn","ar1_org","ar3_org","ar4_org", "cer",
"ar5_employee", "wpeb3", "ar5_org", "cer3",
"reboundaware1"
)]), ]
#model with factors on all levels: 45% explained variance
model <- lm(reboundaware1 ~ age + gender + education + country_base +
sustainability + position + division + tenure +
industry_new + empno +
bio_val + ego_val + pa + ccb_ar +
se + ar1_employee + ar3_employee + ar4_employee +
sn + ar1_org + ar3_org + ar4_org + cer +
ar5_employee + wpeb3 + ar5_org + cer3, data = d)
summary(model, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ age + gender + education + country_base +
## sustainability + position + division + tenure + industry_new +
## empno + bio_val + ego_val + pa + ccb_ar + se + ar1_employee +
## ar3_employee + ar4_employee + sn + ar1_org + ar3_org + ar4_org +
## cer + ar5_employee + wpeb3 + ar5_org + cer3, data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.1257 -0.9978 0.0767 1.0137 6.2182
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.556729 0.211327 2.634 0.008468 **
## age -0.175772 0.025692 -6.841 9.34e-12 ***
## gender2 0.029614 0.060403 0.490 0.623979
## gender3 0.355431 0.306526 1.160 0.246320
## gender4 0.812381 0.325376 2.497 0.012583 *
## education 0.005888 0.017825 0.330 0.741171
## country_base2 -0.058026 0.088317 -0.657 0.511217
## country_base3 -0.223906 0.085654 -2.614 0.008988 **
## country_base4 0.276086 0.085638 3.224 0.001277 **
## country_base5 0.069149 0.119446 0.579 0.562689
## sustainability 0.453163 0.027730 16.342 < 2e-16 ***
## position 0.091343 0.041215 2.216 0.026743 *
## division2 0.220882 0.098813 2.235 0.025462 *
## division3 0.449806 0.098581 4.563 5.24e-06 ***
## division4 0.096835 0.089585 1.081 0.279805
## division5 0.244360 0.101822 2.400 0.016458 *
## division6 0.226082 0.097105 2.328 0.019961 *
## division7 -0.259766 0.098794 -2.629 0.008595 **
## tenure 0.013222 0.018646 0.709 0.478301
## industry_newManufacturing 0.026338 0.062871 0.419 0.675307
## industry_newMobility -0.191399 0.079758 -2.400 0.016463 *
## empno 0.021419 0.017860 1.199 0.230505
## bio_val -0.183839 0.022571 -8.145 5.37e-16 ***
## ego_val 0.207374 0.019864 10.439 < 2e-16 ***
## pa 0.083912 0.021754 3.857 0.000117 ***
## ccb_ar 0.230622 0.021006 10.979 < 2e-16 ***
## se 0.055974 0.035111 1.594 0.110990
## ar1_employee -0.003755 0.027648 -0.136 0.891990
## ar3_employee 0.056451 0.027942 2.020 0.043431 *
## ar4_employee 0.006474 0.030753 0.211 0.833271
## sn 0.071731 0.033880 2.117 0.034320 *
## ar1_org -0.097183 0.027907 -3.482 0.000504 ***
## ar3_org -0.054771 0.029394 -1.863 0.062503 .
## ar4_org -0.056492 0.029881 -1.891 0.058768 .
## cer -0.034994 0.034340 -1.019 0.308263
## ar5_employee -0.003955 0.028567 -0.138 0.889900
## wpeb3 0.155184 0.023618 6.570 5.82e-11 ***
## ar5_org 0.023455 0.028515 0.823 0.410819
## cer3 0.052630 0.029533 1.782 0.074830 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.533 on 3227 degrees of freedom
## (125 observations deleted due to missingness)
## Multiple R-squared: 0.4676, Adjusted R-squared: 0.4613
## F-statistic: 74.58 on 38 and 3227 DF, p-value: < 2.2e-16#figure
library(broom)
library(dplyr)
df_coef <- parameters::model_parameters(
model,
standardize = "refit", # gets standardized β
ci = 0.95 # 95% confidence interval
) |>
filter(Parameter != "(Intercept)") # remove intercept
ggplot(df_coef, aes(x = Coefficient, y = reorder(Parameter, Coefficient))) +
geom_vline(xintercept = 0, linetype = "dashed", color = "grey60") +
geom_errorbarh(aes(xmin = CI_low, xmax = CI_high), width = .2) +
geom_point(size = 3) +
labs(
x = "Standardized Regression Coefficient (β)",
y = NULL
) +
theme_classic(base_size = 12)
#model with only numeric variables
model_num <- lm(reboundaware1 ~ age +
sustainability + position + tenure +
empno +
bio_val + ego_val + pa + ccb_ar +
se + ar1_employee + ar3_employee + ar4_employee +
sn + ar1_org + ar3_org + ar4_org + cer +
ar5_employee + wpeb3 + ar5_org + cer3, data = d_cc)
summary(model_num, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ age + sustainability + position +
## tenure + empno + bio_val + ego_val + pa + ccb_ar + se + ar1_employee +
## ar3_employee + ar4_employee + sn + ar1_org + ar3_org + ar4_org +
## cer + ar5_employee + wpeb3 + ar5_org + cer3, data = d_cc)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.2874 -1.0126 0.0762 1.0124 6.1929
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.5378955 0.1783667 3.016 0.00258 **
## age -0.1799285 0.0257701 -6.982 3.51e-12 ***
## sustainability 0.4750341 0.0276476 17.182 < 2e-16 ***
## position 0.1092979 0.0391181 2.794 0.00524 **
## tenure 0.0254946 0.0185385 1.375 0.16916
## empno 0.0072699 0.0167079 0.435 0.66350
## bio_val -0.1773399 0.0225569 -7.862 5.11e-15 ***
## ego_val 0.2115955 0.0199282 10.618 < 2e-16 ***
## pa 0.0860208 0.0217791 3.950 7.99e-05 ***
## ccb_ar 0.2328217 0.0210786 11.045 < 2e-16 ***
## se 0.0841418 0.0352706 2.386 0.01711 *
## ar1_employee -0.0062851 0.0279320 -0.225 0.82198
## ar3_employee 0.0565064 0.0283269 1.995 0.04615 *
## ar4_employee 0.0159392 0.0310909 0.513 0.60822
## sn 0.0829718 0.0337818 2.456 0.01410 *
## ar1_org -0.1118054 0.0282222 -3.962 7.60e-05 ***
## ar3_org -0.0605345 0.0297210 -2.037 0.04176 *
## ar4_org -0.0597132 0.0302520 -1.974 0.04848 *
## cer -0.0566394 0.0346682 -1.634 0.10241
## ar5_employee -0.0006989 0.0288088 -0.024 0.98065
## wpeb3 0.1487484 0.0237712 6.258 4.42e-10 ***
## ar5_org 0.0280952 0.0288205 0.975 0.32971
## cer3 0.0504548 0.0298699 1.689 0.09129 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.555 on 3243 degrees of freedom
## Multiple R-squared: 0.4493, Adjusted R-squared: 0.4455
## F-statistic: 120.2 on 22 and 3243 DF, p-value: < 2.2e-16df_coef_num <- parameters::model_parameters(
model_num,
standardize = "refit", # gets standardized β
ci = 0.95 # 95% confidence interval
) |>
filter(Parameter != "(Intercept)") # remove intercept
ggplot(df_coef_num, aes(x = Coefficient, y = reorder(Parameter, Coefficient))) +
geom_vline(xintercept = 0, linetype = "dashed", color = "grey60") +
geom_errorbarh(aes(xmin = CI_low, xmax = CI_high), width = .2) +
geom_point(size = 3) +
labs(
x = "Standardized Regression Coefficient (β)",
y = NULL
) +
theme_classic(base_size = 12)
Explained variance per level
Model individual factors
model_ind <- lm(reboundaware1 ~ age + gender + education + country_base + bio_val + ego_val + pa + ccb_ar, data = d)
summary(model_ind, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ age + gender + education + country_base +
## bio_val + ego_val + pa + ccb_ar, data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.1210 -1.1902 0.1715 1.2096 6.0792
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.74562 0.19411 8.993 < 2e-16 ***
## age -0.25723 0.02344 -10.973 < 2e-16 ***
## gender2 -0.08353 0.06422 -1.301 0.193454
## gender3 0.77742 0.34018 2.285 0.022356 *
## gender4 1.39713 0.36052 3.875 0.000108 ***
## education 0.06563 0.01813 3.621 0.000298 ***
## country_base2 -0.43769 0.09328 -4.692 2.81e-06 ***
## country_base3 -0.27162 0.09249 -2.937 0.003338 **
## country_base4 0.25310 0.09011 2.809 0.005001 **
## country_base5 -0.29580 0.12509 -2.365 0.018098 *
## bio_val -0.15991 0.02277 -7.023 2.61e-12 ***
## ego_val 0.38137 0.01997 19.096 < 2e-16 ***
## pa 0.05080 0.02344 2.167 0.030292 *
## ccb_ar 0.39092 0.02127 18.377 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.714 on 3377 degrees of freedom
## Multiple R-squared: 0.3284, Adjusted R-squared: 0.3258
## F-statistic: 127 on 13 and 3377 DF, p-value: < 2.2e-16Model job/role-level factors
model_job <- lm(reboundaware1 ~ sustainability + position + division + tenure + se + ar1_employee + ar3_employee + ar4_employee + ar5_employee + wpeb3, data = d)
summary(model_job, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ sustainability + position + division +
## tenure + se + ar1_employee + ar3_employee + ar4_employee +
## ar5_employee + wpeb3, data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.3730 -1.0775 0.0795 1.1408 6.1666
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.17905 0.15092 1.186 0.235578
## sustainability 0.59426 0.02762 21.512 < 2e-16 ***
## position 0.06747 0.04177 1.615 0.106399
## division2 0.43447 0.10365 4.192 2.84e-05 ***
## division3 0.72860 0.10294 7.078 1.78e-12 ***
## division4 0.29312 0.09434 3.107 0.001906 **
## division5 0.38170 0.10696 3.569 0.000364 ***
## division6 0.45855 0.10068 4.554 5.45e-06 ***
## division7 -0.27406 0.10405 -2.634 0.008483 **
## tenure -0.05707 0.01661 -3.436 0.000598 ***
## se 0.15319 0.03122 4.908 9.68e-07 ***
## ar1_employee -0.03058 0.02765 -1.106 0.268820
## ar3_employee 0.04887 0.02788 1.753 0.079769 .
## ar4_employee -0.02523 0.02963 -0.851 0.394570
## ar5_employee 0.01309 0.02878 0.455 0.649190
## wpeb3 0.23276 0.02361 9.860 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.641 on 3250 degrees of freedom
## (125 observations deleted due to missingness)
## Multiple R-squared: 0.3856, Adjusted R-squared: 0.3827
## F-statistic: 136 on 15 and 3250 DF, p-value: < 2.2e-16Model for organizational-level factors
model_org <- lm(reboundaware1 ~ industry_new + empno + sn + ar1_org + ar3_org + ar4_org + ar5_org + cer + cer3, data = d)
summary(model_org, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ industry_new + empno + sn + ar1_org +
## ar3_org + ar4_org + ar5_org + cer + cer3, data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.5627 -1.3959 0.2756 1.5093 5.6234
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.652797 0.166440 3.922 8.95e-05 ***
## industry_newManufacturing 0.047722 0.073644 0.648 0.517020
## industry_newMobility -0.179934 0.093403 -1.926 0.054135 .
## empno 0.043240 0.019904 2.172 0.029897 *
## sn 0.522906 0.029670 17.624 < 2e-16 ***
## ar1_org -0.146201 0.031072 -4.705 2.64e-06 ***
## ar3_org -0.016053 0.031937 -0.503 0.615246
## ar4_org -0.011032 0.031847 -0.346 0.729063
## ar5_org 0.108177 0.031758 3.406 0.000666 ***
## cer 0.009227 0.040055 0.230 0.817819
## cer3 0.165785 0.034399 4.819 1.50e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.857 on 3380 degrees of freedom
## Multiple R-squared: 0.2113, Adjusted R-squared: 0.209
## F-statistic: 90.55 on 10 and 3380 DF, p-value: < 2.2e-16#Explained variance per column
##Model structural factors
model_struc <- lm(reboundaware1 ~ age + gender + education + country_base +
sustainability + position + division + tenure +
industry_new + empno, data = d)
summary(model_struc, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ age + gender + education + country_base +
## sustainability + position + division + tenure + industry_new +
## empno, data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.9953 -1.1873 -0.0002 1.2334 5.5394
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.63487 0.19157 8.534 < 2e-16 ***
## age -0.22823 0.02765 -8.255 < 2e-16 ***
## gender2 0.04100 0.06581 0.623 0.533283
## gender3 0.39278 0.33459 1.174 0.240515
## gender4 0.72227 0.35517 2.034 0.042074 *
## education 0.02109 0.01944 1.085 0.278095
## country_base2 0.06489 0.09431 0.688 0.491488
## country_base3 -0.20878 0.09169 -2.277 0.022845 *
## country_base4 0.32764 0.09248 3.543 0.000402 ***
## country_base5 0.13820 0.12791 1.080 0.280026
## sustainability 0.76601 0.02563 29.893 < 2e-16 ***
## position 0.14708 0.04494 3.273 0.001075 **
## division2 0.35726 0.10780 3.314 0.000929 ***
## division3 0.64186 0.10727 5.983 2.42e-09 ***
## division4 0.26427 0.09767 2.706 0.006850 **
## division5 0.32589 0.11097 2.937 0.003338 **
## division6 0.34183 0.10598 3.225 0.001271 **
## division7 -0.30589 0.10788 -2.835 0.004606 **
## tenure 0.02505 0.02035 1.231 0.218582
## industry_newManufacturing 0.01657 0.06846 0.242 0.808748
## industry_newMobility -0.21188 0.08688 -2.439 0.014787 *
## empno 0.02691 0.01912 1.407 0.159513
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.681 on 3244 degrees of freedom
## (125 observations deleted due to missingness)
## Multiple R-squared: 0.3569, Adjusted R-squared: 0.3527
## F-statistic: 85.73 on 21 and 3244 DF, p-value: < 2.2e-16##Model perceptual factors
model_percep <- lm(reboundaware1 ~ bio_val + ego_val + pa + ccb_ar +
se + ar1_employee + ar3_employee + ar4_employee +
sn + ar1_org + ar3_org + ar4_org + cer +
ar5_employee + wpeb3 + ar5_org + cer3, data = d)
summary(model_percep, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ bio_val + ego_val + pa + ccb_ar +
## se + ar1_employee + ar3_employee + ar4_employee + sn + ar1_org +
## ar3_org + ar4_org + cer + ar5_employee + wpeb3 + ar5_org +
## cer3, data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.1097 -1.1362 0.1821 1.1703 5.7379
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.415879 0.154698 2.688 0.007216 **
## bio_val -0.226963 0.023491 -9.662 < 2e-16 ***
## ego_val 0.299358 0.020162 14.848 < 2e-16 ***
## pa 0.038821 0.022785 1.704 0.088515 .
## ccb_ar 0.287259 0.021960 13.081 < 2e-16 ***
## se 0.126532 0.036824 3.436 0.000597 ***
## ar1_employee -0.009971 0.029340 -0.340 0.734003
## ar3_employee 0.088721 0.029795 2.978 0.002924 **
## ar4_employee -0.005103 0.032607 -0.156 0.875656
## sn 0.119102 0.035210 3.383 0.000726 ***
## ar1_org -0.121640 0.029806 -4.081 4.59e-05 ***
## ar3_org -0.077174 0.031348 -2.462 0.013871 *
## ar4_org -0.053303 0.031731 -1.680 0.093079 .
## cer -0.056971 0.036360 -1.567 0.117242
## ar5_employee -0.016294 0.030232 -0.539 0.589945
## wpeb3 0.243892 0.024231 10.065 < 2e-16 ***
## ar5_org 0.070173 0.030226 2.322 0.020312 *
## cer3 0.098661 0.031181 3.164 0.001569 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.671 on 3373 degrees of freedom
## Multiple R-squared: 0.3629, Adjusted R-squared: 0.3597
## F-statistic: 113 on 17 and 3373 DF, p-value: < 2.2e-16#Explained variance per block
##Individual - structural
model_ind_struc <- lm(reboundaware1 ~ age + gender + education + country_base, data = d)
summary(model_ind_struc, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ age + gender + education + country_base,
## data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.9522 -1.7857 0.2689 1.5563 4.9089
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.73126 0.17539 26.975 < 2e-16 ***
## age -0.40915 0.02626 -15.580 < 2e-16 ***
## gender2 -0.08091 0.07390 -1.095 0.273637
## gender3 0.97567 0.39155 2.492 0.012757 *
## gender4 1.48834 0.41561 3.581 0.000347 ***
## education 0.14272 0.02073 6.886 6.81e-12 ***
## country_base2 -0.32791 0.10632 -3.084 0.002058 **
## country_base3 -0.21990 0.10553 -2.084 0.037259 *
## country_base4 0.35000 0.10312 3.394 0.000696 ***
## country_base5 -0.23079 0.14341 -1.609 0.107658
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.978 on 3381 degrees of freedom
## Multiple R-squared: 0.105, Adjusted R-squared: 0.1026
## F-statistic: 44.06 on 9 and 3381 DF, p-value: < 2.2e-16##Individual - perceptual
model_ind_percep <- lm(reboundaware1 ~ bio_val + ego_val + pa + ccb_ar, data = d)
summary(model_ind_percep, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ bio_val + ego_val + pa + ccb_ar,
## data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.9970 -1.2403 0.2235 1.2490 5.6216
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.84246 0.13154 6.405 1.72e-10 ***
## bio_val -0.16960 0.02289 -7.411 1.58e-13 ***
## ego_val 0.43056 0.02000 21.524 < 2e-16 ***
## pa 0.03982 0.02395 1.663 0.0965 .
## ccb_ar 0.41135 0.02183 18.840 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.772 on 3386 degrees of freedom
## Multiple R-squared: 0.2804, Adjusted R-squared: 0.2795
## F-statistic: 329.8 on 4 and 3386 DF, p-value: < 2.2e-16##Job/role - structural
model_job_struc <- lm(reboundaware1 ~ sustainability + position + division + tenure, data = d)
summary(model_job_struc, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ sustainability + position + division +
## tenure, data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.0516 -1.1710 -0.0009 1.2569 5.1774
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.18951 0.12037 9.882 < 2e-16 ***
## sustainability 0.82243 0.02494 32.978 < 2e-16 ***
## position 0.13547 0.04320 3.136 0.001728 **
## division2 0.46047 0.10771 4.275 1.97e-05 ***
## division3 0.77552 0.10696 7.250 5.17e-13 ***
## division4 0.35127 0.09797 3.585 0.000341 ***
## division5 0.39911 0.11103 3.595 0.000330 ***
## division6 0.48271 0.10464 4.613 4.12e-06 ***
## division7 -0.29235 0.10826 -2.700 0.006961 **
## tenure -0.04640 0.01722 -2.695 0.007067 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.709 on 3256 degrees of freedom
## (125 observations deleted due to missingness)
## Multiple R-squared: 0.3328, Adjusted R-squared: 0.3309
## F-statistic: 180.4 on 9 and 3256 DF, p-value: < 2.2e-16##Job/role - perceptual
model_job_percep <- lm(reboundaware1 ~ se + ar1_employee + ar3_employee + ar4_employee + ar5_employee + wpeb3, data = d)
summary(model_job_percep, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ se + ar1_employee + ar3_employee +
## ar4_employee + ar5_employee + wpeb3, data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.7164 -1.3350 0.2194 1.4260 5.7689
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.51858 0.13650 3.799 0.000148 ***
## se 0.27808 0.03312 8.396 < 2e-16 ***
## ar1_employee -0.03339 0.02959 -1.128 0.259272
## ar3_employee 0.08091 0.03006 2.692 0.007141 **
## ar4_employee -0.03498 0.03192 -1.096 0.273221
## ar5_employee 0.01020 0.03094 0.330 0.741725
## wpeb3 0.41174 0.02392 17.215 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.81 on 3384 degrees of freedom
## Multiple R-squared: 0.2494, Adjusted R-squared: 0.2481
## F-statistic: 187.4 on 6 and 3384 DF, p-value: < 2.2e-16##Organizational - structural
model_org_struc <- lm(reboundaware1 ~ industry_new + empno, data = d)
summary(model_org_struc, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ industry_new + empno, data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2603 -2.0512 0.2625 1.8442 3.7001
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.626851 0.089432 40.554 < 2e-16 ***
## industry_newManufacturing 0.006124 0.082094 0.075 0.941
## industry_newMobility -0.431508 0.103778 -4.158 3.29e-05 ***
## empno 0.104562 0.021635 4.833 1.41e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.076 on 3387 degrees of freedom
## Multiple R-squared: 0.01225, Adjusted R-squared: 0.01137
## F-statistic: 14 on 3 and 3387 DF, p-value: 4.553e-09##Organizational - perceptual
model_org_percep <- lm(reboundaware1 ~ sn + ar1_org + ar3_org + ar4_org + cer + ar5_org + cer3, data = d)
summary(model_org_percep, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)##
## Call:
## lm(formula = reboundaware1 ~ sn + ar1_org + ar3_org + ar4_org +
## cer + ar5_org + cer3, data = d)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.6713 -1.3935 0.2914 1.5106 5.6474
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.700207 0.158682 4.413 1.05e-05 ***
## sn 0.518718 0.029512 17.576 < 2e-16 ***
## ar1_org -0.141259 0.031072 -4.546 5.65e-06 ***
## ar3_org -0.012868 0.031866 -0.404 0.68638
## ar4_org -0.009893 0.031878 -0.310 0.75633
## cer 0.014462 0.040070 0.361 0.71818
## ar5_org 0.109572 0.031773 3.449 0.00057 ***
## cer3 0.173654 0.034243 5.071 4.17e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.859 on 3383 degrees of freedom
## Multiple R-squared: 0.2087, Adjusted R-squared: 0.2071
## F-statistic: 127.5 on 7 and 3383 DF, p-value: < 2.2e-16