daTE 7/10/2025
IANLEE
2025-10-07
R Markdown
rm(list = ls())#LOAD LIBRARIES
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(psych)
library(ggplot2)##
## Attaching package: 'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alphalibrary(readxl)data1<-read_excel("C:/Users/USER/OneDrive/Documents/jkia_delayed_payments_survey_150_filtered.....new.xlsx")# Create Composite Scores
data1 <- data1 %>%
mutate(
compliance_score = rowMeans(select(., Compliance_Report_Work,
Compliance_Follow_Instructions,
Compliance_Fear_Job_Loss), na.rm = TRUE),
morale_score = rowMeans(select(., Morale_Job_Satisfaction,
Morale_Stress_Anxiety,
Morale_Motivation,
Morale_Seek_Other_Employment), na.rm = TRUE),
productivity_score = rowMeans(select(., Productivity_Quality,
Productivity_Pace,
Productivity_Sick_Days), na.rm = TRUE)
)# 4. Descriptive Statistics
summary_stats <- data1 %>%
summarise(
mean_compliance = mean(compliance_score, na.rm = TRUE),
mean_morale = mean(morale_score, na.rm = TRUE),
mean_productivity = mean(productivity_score, na.rm = TRUE)
)#Reliability Checks (Cronbach's alpha)
psych::alpha(dplyr::select(data1, Compliance_Report_Work,
Compliance_Follow_Instructions,
Compliance_Fear_Job_Loss))## Warning in psych::alpha(dplyr::select(data1, Compliance_Report_Work, Compliance_Follow_Instructions, : Some items were negatively correlated with the first principal component and probably
## should be reversed.
## To do this, run the function again with the 'check.keys=TRUE' option## Some items ( Compliance_Follow_Instructions ) were negatively correlated with the first principal component and
## probably should be reversed.
## To do this, run the function again with the 'check.keys=TRUE' option## Warning in sqrt(Vtc): NaNs produced##
## Reliability analysis
## Call: psych::alpha(x = dplyr::select(data1, Compliance_Report_Work,
## Compliance_Follow_Instructions, Compliance_Fear_Job_Loss))
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## -0.064 -0.065 -0.037 -0.021 -0.061 0.15 3 0.82 -0.013
##
## 95% confidence boundaries
## lower alpha upper
## Feldt -0.40 -0.06 0.20
## Duhachek -0.36 -0.06 0.23
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N
## Compliance_Report_Work -0.200 -0.200 -0.091 -0.091 -0.167
## Compliance_Follow_Instructions 0.078 0.079 0.041 0.041 0.085
## Compliance_Fear_Job_Loss -0.026 -0.026 -0.013 -0.013 -0.025
## alpha se var.r med.r
## Compliance_Report_Work 0.20 NA -0.091
## Compliance_Follow_Instructions 0.15 NA 0.041
## Compliance_Fear_Job_Loss 0.17 NA -0.013
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## Compliance_Report_Work 150 0.62 0.61 NaN 0.020 3.1 1.5
## Compliance_Follow_Instructions 150 0.53 0.53 NaN -0.070 3.0 1.5
## Compliance_Fear_Job_Loss 150 0.55 0.56 NaN -0.035 2.9 1.4
##
## Non missing response frequency for each item
## 1 2 3 4 5 miss
## Compliance_Report_Work 0.21 0.18 0.19 0.17 0.25 0
## Compliance_Follow_Instructions 0.22 0.18 0.19 0.20 0.21 0
## Compliance_Fear_Job_Loss 0.21 0.23 0.17 0.22 0.18 0psych::alpha(dplyr::select(data1, Morale_Job_Satisfaction,
Morale_Stress_Anxiety,
Morale_Motivation,
Morale_Seek_Other_Employment))## Warning in psych::alpha(dplyr::select(data1, Morale_Job_Satisfaction, Morale_Stress_Anxiety, : Some items were negatively correlated with the first principal component and probably
## should be reversed.
## To do this, run the function again with the 'check.keys=TRUE' option## Some items ( Morale_Job_Satisfaction Morale_Seek_Other_Employment ) were negatively correlated with the first principal component and
## probably should be reversed.
## To do this, run the function again with the 'check.keys=TRUE' option## Warning in sqrt(Vtc): NaNs produced##
## Reliability analysis
## Call: psych::alpha(x = dplyr::select(data1, Morale_Job_Satisfaction,
## Morale_Stress_Anxiety, Morale_Motivation, Morale_Seek_Other_Employment))
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## -0.072 -0.074 -0.042 -0.017 -0.069 0.14 3 0.69 -0.025
##
## 95% confidence boundaries
## lower alpha upper
## Feldt -0.38 -0.07 0.18
## Duhachek -0.35 -0.07 0.21
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N
## Morale_Job_Satisfaction 0.00074 0.0030 0.0105 0.00099 0.0030
## Morale_Stress_Anxiety -0.00637 -0.0078 -0.0024 -0.00259 -0.0077
## Morale_Motivation -0.14926 -0.1501 -0.0877 -0.04548 -0.1305
## Morale_Seek_Other_Employment -0.06754 -0.0711 -0.0350 -0.02264 -0.0664
## alpha se var.r med.r
## Morale_Job_Satisfaction 0.14 0.0064 0.00091
## Morale_Stress_Anxiety 0.14 0.0021 0.00091
## Morale_Motivation 0.16 0.0057 -0.07887
## Morale_Seek_Other_Employment 0.15 0.0086 -0.04999
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## Morale_Job_Satisfaction 150 0.44 0.46 NaN -0.061 2.8 1.4
## Morale_Stress_Anxiety 150 0.46 0.46 NaN -0.056 3.0 1.4
## Morale_Motivation 150 0.53 0.53 NaN 0.020 2.9 1.4
## Morale_Seek_Other_Employment 150 0.51 0.49 NaN -0.023 3.1 1.5
##
## Non missing response frequency for each item
## 1 2 3 4 5 miss
## Morale_Job_Satisfaction 0.22 0.25 0.21 0.17 0.15 0
## Morale_Stress_Anxiety 0.17 0.25 0.17 0.19 0.21 0
## Morale_Motivation 0.23 0.17 0.22 0.21 0.17 0
## Morale_Seek_Other_Employment 0.19 0.21 0.16 0.21 0.24 0psych::alpha(dplyr::select(data1, Productivity_Quality,
Productivity_Pace,
Productivity_Sick_Days))##
## Reliability analysis
## Call: psych::alpha(x = dplyr::select(data1, Productivity_Quality, Productivity_Pace,
## Productivity_Sick_Days))
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.21 0.21 0.15 0.081 0.26 0.11 2.9 0.89 0.088
##
## 95% confidence boundaries
## lower alpha upper
## Feldt -0.04 0.21 0.41
## Duhachek -0.01 0.21 0.43
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se
## Productivity_Quality 0.162 0.162 0.088 0.088 0.193 0.14
## Productivity_Pace 0.241 0.241 0.137 0.137 0.318 0.12
## Productivity_Sick_Days 0.034 0.034 0.018 0.018 0.036 0.16
## var.r med.r
## Productivity_Quality NA 0.088
## Productivity_Pace NA 0.137
## Productivity_Sick_Days NA 0.018
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## Productivity_Quality 150 0.63 0.62 0.24 0.11 3.0 1.4
## Productivity_Pace 150 0.58 0.59 0.15 0.07 2.7 1.4
## Productivity_Sick_Days 150 0.66 0.66 0.34 0.16 2.9 1.5
##
## Non missing response frequency for each item
## 1 2 3 4 5 miss
## Productivity_Quality 0.21 0.21 0.15 0.22 0.21 0
## Productivity_Pace 0.23 0.28 0.16 0.17 0.15 0
## Productivity_Sick_Days 0.21 0.21 0.22 0.13 0.23 0colnames(data1)## [1] "Gender" "Age Group"
## [3] "Education Level" "Employment Type"
## [5] "Department" "Length of Service"
## [7] "Delayed Payment Frequency" "Average Delay"
## [9] "Main Reason for Delay" "Compliance_Report_Work"
## [11] "Compliance_Follow_Instructions" "Compliance_Fear_Job_Loss"
## [13] "Morale_Job_Satisfaction" "Morale_Stress_Anxiety"
## [15] "Morale_Motivation" "Morale_Seek_Other_Employment"
## [17] "Productivity_Quality" "Productivity_Pace"
## [19] "Productivity_Sick_Days" "Coping Mechanisms"
## [21] "Additional Comments" "compliance_score"
## [23] "morale_score" "productivity_score"# Convert delay frequency and average delay into ordered numeric scales
data1 <- data1 %>%
mutate(
delay_freq_num = case_when(
`Delayed Payment Frequency` == "Never" ~ 0,
`Delayed Payment Frequency` == "Once" ~ 1,
`Delayed Payment Frequency` == "2–3 times" ~ 2,
`Delayed Payment Frequency` == "More than 3 times" ~ 3,
TRUE ~ NA_real_
),
delay_duration_num = case_when(
`Average Delay` == "Less than 1 week" ~ 1,
`Average Delay` == "1–2 weeks" ~ 2,
`Average Delay` == "3–4 weeks" ~ 3,
`Average Delay` == "More than a month" ~ 4,
TRUE ~ NA_real_
)
)cor_matrix <- cor(select(data1, delay_freq_num, delay_duration_num,
compliance_score, morale_score, productivity_score),
use = "pairwise.complete.obs")
print(cor_matrix)## delay_freq_num delay_duration_num compliance_score
## delay_freq_num 1.00000000 0.07307102 0.141696120
## delay_duration_num 0.07307102 1.00000000 0.066559437
## compliance_score 0.14169612 0.06655944 1.000000000
## morale_score -0.08793300 0.01267160 0.039344076
## productivity_score -0.06395307 0.10647704 -0.009568297
## morale_score productivity_score
## delay_freq_num -0.08793300 -0.063953075
## delay_duration_num 0.01267160 0.106477037
## compliance_score 0.03934408 -0.009568297
## morale_score 1.00000000 0.067319329
## productivity_score 0.06731933 1.000000000# 8. Regression Models
model_compliance <- lm(compliance_score ~ delay_freq_num + delay_duration_num, data = data1)
model_morale <- lm(morale_score ~ delay_freq_num + delay_duration_num, data = data1)
model_product <- lm(productivity_score ~ delay_freq_num + delay_duration_num, data = data1)summary(model_compliance)##
## Call:
## lm(formula = compliance_score ~ delay_freq_num + delay_duration_num,
## data = data1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.2062 -0.4907 0.2004 0.6070 1.9711
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.81813 0.30184 9.336 3.07e-15 ***
## delay_freq_num 0.06424 0.10066 0.638 0.525
## delay_duration_num 0.04883 0.07919 0.617 0.539
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8605 on 99 degrees of freedom
## (48 observations deleted due to missingness)
## Multiple R-squared: 0.008509, Adjusted R-squared: -0.01152
## F-statistic: 0.4248 on 2 and 99 DF, p-value: 0.6551summary(model_morale)##
## Call:
## lm(formula = morale_score ~ delay_freq_num + delay_duration_num,
## data = data1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.41719 -0.42080 0.08464 0.51966 1.58281
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.898024 0.240319 12.059 <2e-16 ***
## delay_freq_num -0.004531 0.080145 -0.057 0.955
## delay_duration_num 0.008189 0.063048 0.130 0.897
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6851 on 99 degrees of freedom
## (48 observations deleted due to missingness)
## Multiple R-squared: 0.0001928, Adjusted R-squared: -0.02001
## F-statistic: 0.009548 on 2 and 99 DF, p-value: 0.9905summary(model_product)##
## Call:
## lm(formula = productivity_score ~ delay_freq_num + delay_duration_num,
## data = data1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.6311 -0.5909 -0.1064 0.6391 2.0987
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.99497 0.30676 9.763 3.59e-16 ***
## delay_freq_num -0.15881 0.10230 -1.552 0.124
## delay_duration_num 0.09568 0.08048 1.189 0.237
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8745 on 99 degrees of freedom
## (48 observations deleted due to missingness)
## Multiple R-squared: 0.03483, Adjusted R-squared: 0.01533
## F-statistic: 1.786 on 2 and 99 DF, p-value: 0.1729# 9. Visualization Example
ggplot(data1, aes(x = factor(delay_freq_num), y = morale_score)) +
geom_boxplot() +
labs(x = "Delay Frequency (0=Never, 3=More than 3 times)",
y = "Morale Score",
title = "Morale vs. Delay Frequency")
model_interaction <- lm(productivity_score ~ delay_freq_num * delay_duration_num, data = data1)
summary(model_interaction)##
## Call:
## lm(formula = productivity_score ~ delay_freq_num * delay_duration_num,
## data = data1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.6238 -0.6013 -0.1011 0.6417 2.0965
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.219320 0.662890 4.856 4.53e-06 ***
## delay_freq_num -0.256883 0.276395 -0.929 0.355
## delay_duration_num 0.008588 0.241767 0.036 0.972
## delay_freq_num:delay_duration_num 0.037638 0.098467 0.382 0.703
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8783 on 98 degrees of freedom
## (48 observations deleted due to missingness)
## Multiple R-squared: 0.03627, Adjusted R-squared: 0.006764
## F-statistic: 1.229 on 3 and 98 DF, p-value: 0.3032