I/O Dataset

On this page

• Data
  • Individual Variables
  • Appendix

pacman::p_load(
  rio,         
  tidyverse,   
  janitor,     
  lubridate,   
  openxlsx,    
  psych, 
  readr, 
  lubridate, 
  pander, 
  car, 
  lsr, 
  plotly
)

Data

Individual Variables

All the variables we are looking at in this dataset.

Human Nature

Human Nature Normality

hn_diff <- final_io_data$`Pre_Human Nature` - final_io_data$`Post_Human Nature`


qqPlot(hn_diff, main = "Q-Q Plot of Human Nature Differences")

[1] 82 71

Human Nature Test

t.test(final_io_data$`Pre_Human Nature`, final_io_data$`Post_Human Nature`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Human Natureand `final_io_data$`Post_Human Nature

Test statistic	df	P value	Alternative hypothesis	mean difference
-3.442	127	0.0007819 * * *	two.sided	-0.1062

cohensD(final_io_data$`Pre_Human Nature`, final_io_data$`Post_Human Nature`, method = "paired") 

[1] 0.3042466

Human Nature Graph

long_data <- stack(final_io_data[c("Pre_Human Nature", "Post_Human Nature")])
names(long_data) <- c("Human_Nature", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Human Nature", "Post_Human Nature"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Human_Nature,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("steelblue2", "steelblue4")
) %>%
  layout(
    title = "Human Nature Changes Across Semester", 
    yaxis = list(title = "Total Average Human Nature"),
    xaxis = list(title = "Timepoint")
  )

Locus of Control

Locus of Control Normality

loc_diff <- final_io_data$`Pre_L of C` - final_io_data$`Post_L of C`


qqPlot(loc_diff, main = "Q-Q Plot of Locus of Control Differences", col = "darkgreen", col.lines = "palegreen3")

[1] 20 71

Locus of Control Test

t.test(final_io_data$`Pre_L of C`, final_io_data$`Post_L of C`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_L of Cand `final_io_data$`Post_L of C

Test statistic	df	P value	Alternative hypothesis	mean difference
-0.3015	128	0.7636	two.sided	-0.02093

cohensD(final_io_data$`Pre_L of C`, final_io_data$`Post_L of C`, method = "paired") 

[1] 0.02654157

Locus of Control Graph

long_data <- stack(final_io_data[c("Pre_L of C", "Post_L of C")])
names(long_data) <- c("Locus_of_Control", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_L of C", "Post_L of C"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Locus_of_Control,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("palegreen3", "darkgreen")
) %>%
  layout(
    title = "Locus of Control Changes Across Semester", 
    yaxis = list(title = "Total Average Locus of Control"),
    xaxis = list(title = "Timepoint")
  )

Efficacy

Efficacy Normality

eff_diff <- final_io_data$`Pre_Efficacy` - final_io_data$`Post_Efficacy`

qqPlot(eff_diff, main = "Q-Q Plot of Efficacy Differences", col = "firebrick3", col.lines = "coral1")

[1] 71  8

Efficacy Test

t.test(final_io_data$`Pre_Efficacy`, final_io_data$`Post_Efficacy`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Efficacy and final_io_data$Post_Efficacy

Test statistic	df	P value	Alternative hypothesis	mean difference
0.5825	128	0.5612	two.sided	0.03566

cohensD(final_io_data$`Pre_Efficacy`, final_io_data$`Post_Efficacy`, method = "paired") 

[1] 0.05128757

Efficacy Graph

long_data <- stack(final_io_data[c("Pre_Efficacy", "Post_Efficacy")])
names(long_data) <- c("Efficacy", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Efficacy", "Post_Efficacy"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Efficacy,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("coral1", "firebrick3")
) %>%
  layout(
    title = "Efficacy Changes Across Semester", 
    yaxis = list(title = "Total Average Efficacy"),
    xaxis = list(title = "Timepoint")
  )

Challenge

Challenge Normality

chal_diff <- final_io_data$`Pre_Challenge` - final_io_data$`Post_Challenge`

qqPlot(chal_diff, main = "Q-Q Plot of Challenge Differences", col = "purple4", col.lines = "mediumpurple2")

[1] 71 90

Challenge Test

t.test(final_io_data$`Pre_Challenge`, final_io_data$`Post_Challenge`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Challenge and final_io_data$Post_Challenge

Test statistic	df	P value	Alternative hypothesis	mean difference
-1.199	127	0.2329	two.sided	-0.08906

cohensD(final_io_data$`Pre_Challenge`, final_io_data$`Post_Challenge`, method = "paired") 

[1] 0.1059479

Challenge Graph

long_data <- stack(final_io_data[c("Pre_Challenge", "Post_Challenge")])
names(long_data) <- c("Challenge", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Challenge", "Post_Challenge"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Challenge,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("mediumpurple2", "purple4")
) %>%
  layout(
    title = "Challenge Changes Across Semester", 
    yaxis = list(title = "Total Average Challenge"),
    xaxis = list(title = "Timepoint")
  )

Barriers

Barriers Normality

bar_diff <- final_io_data$`Pre_Barriers` - final_io_data$`Post_Barriers`

qqPlot(bar_diff, main = "Q-Q Plot of Barriers Differences", col = "darkorange2", col.lines = "goldenrod1")

[1] 20 82

Barriers Test

t.test(final_io_data$`Pre_Barriers`, final_io_data$`Post_Barriers`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Barriers and final_io_data$Post_Barriers

Test statistic	df	P value	Alternative hypothesis	mean difference
-0.428	128	0.6694	two.sided	-0.03322

cohensD(final_io_data$`Pre_Barriers`, final_io_data$`Post_Barriers`, method = "paired") 

[1] 0.03768324

Barriers Graph

long_data <- stack(final_io_data[c("Pre_Barriers", "Post_Barriers")])
names(long_data) <- c("Barriers", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Barriers", "Post_Barriers"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Barriers,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("goldenrod1", "darkorange2")
) %>%
  layout(
    title = "Barriers Changes Across Semester", 
    yaxis = list(title = "Total Average Barriers"),
    xaxis = list(title = "Timepoint")
  )

Social Integration

Social Integration Normality

si_diff <- final_io_data$`Pre_Social Integration` - final_io_data$`Post_Social Integration`

qqPlot(si_diff, main = "Q-Q Plot of Social Integration Differences", col = "darkslategrey", col.lines = "turquoise3")

[1] 120  87

Social Integration Test

t.test(final_io_data$`Pre_Social Integration`, final_io_data$`Post_Social Integration`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Social Integrationand `final_io_data$`Post_Social Integration

Test statistic	df	P value	Alternative hypothesis	mean difference
1.358	128	0.1767	two.sided	0.09731

cohensD(final_io_data$`Pre_Social Integration`, final_io_data$`Post_Social Integration`, method = "paired") 

[1] 0.1196026

Social Integration Graph

long_data <- stack(final_io_data[c("Pre_Social Integration", "Post_Social Integration")])
names(long_data) <- c("Social_Integration", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Social Integration", "Post_Social Integration"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Social_Integration,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("turquoise3", "darkslategrey")
) %>%
  layout(
    title = "Social Integration Changes Across Semester", 
    yaxis = list(title = "Total Average Social Integration"),
    xaxis = list(title = "Timepoint")
  )

Tech

Tech Normality

tech_diff <- final_io_data$`Pre_Tech` - final_io_data$`Post_Tech`

qqPlot(tech_diff, main = "Q-Q Plot of Tech Differences", col = "darkorchid4", col.lines = "mediumorchid2")

[1] 129  95

Tech Test

t.test(final_io_data$`Pre_Tech`, final_io_data$`Post_Tech`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Tech and final_io_data$Post_Tech

Test statistic	df	P value	Alternative hypothesis	mean difference
0.7279	128	0.468	two.sided	0.06977

cohensD(final_io_data$`Pre_Tech`, final_io_data$`Post_Tech`, method = "paired") 

[1] 0.06408512

Tech Graph

long_data <- stack(final_io_data[c("Pre_Tech", "Post_Tech")])
names(long_data) <- c("Tech", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Tech", "Post_Tech"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Tech,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("mediumorchid2", "darkorchid4")
) %>%
  layout(
    title = "Tech Changes Across Semester", 
    yaxis = list(title = "Total Average Tech"),
    xaxis = list(title = "Timepoint")
  )

Screen

Screen Normality

screen_diff <- final_io_data$`Pre_Screen` - final_io_data$`Post_Screen`

qqPlot(screen_diff, main = "Q-Q Plot of Screen Differences", col = "deepskyblue4", col.lines = "skyblue2")

[1]  52 105

Screen Test

t.test(final_io_data$`Pre_Screen`, final_io_data$`Post_Screen`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Screen and final_io_data$Post_Screen

Test statistic	df	P value	Alternative hypothesis	mean difference
-2.255	128	0.02584 *	two.sided	-21.76

cohensD(final_io_data$`Pre_Screen`, final_io_data$`Post_Screen`, method = "paired") 

[1] 0.1985328

Screen Graph

long_data <- stack(final_io_data[c("Pre_Screen", "Post_Screen")])
names(long_data) <- c("Screen", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Screen", "Post_Screen"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Screen,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("skyblue2", "deepskyblue4")
) %>%
  layout(
    title = "Screen Changes Across Semester", 
    yaxis = list(title = "Total Average Screen"),
    xaxis = list(title = "Timepoint")
  )

Job Satisfaction

Job Satisfaction Normality

js_diff <- final_io_data$`Pre_Job Satisfaction` - final_io_data$`Post_Job Satisfaction`

qqPlot(js_diff, main = "Q-Q Plot of Job Satisfaction Differences", col = "darkolivegreen", col.lines = "chartreuse3")

[1] 92 55

Job Satisfaction Test

t.test(final_io_data$`Pre_Job Satisfaction`, final_io_data$`Post_Job Satisfaction`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Job Satisfactionand `final_io_data$`Post_Job Satisfaction

Test statistic	df	P value	Alternative hypothesis	mean difference
1.308	77	0.1947	two.sided	0.1795

cohensD(final_io_data$`Pre_Job Satisfaction`, final_io_data$`Post_Job Satisfaction`, method = "paired") 

[1] 0.1481349

Job Satisfaction Graph

long_data <- stack(final_io_data[c("Pre_Job Satisfaction", "Post_Job Satisfaction")])
names(long_data) <- c("Job_Satisfaction", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Job Satisfaction", "Post_Job Satisfaction"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Job_Satisfaction,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("chartreuse3", "darkolivegreen")
) %>%
  layout(
    title = "Job Satisfaction Changes Across Semester", 
    yaxis = list(title = "Total Average Job Satisfaction"),
    xaxis = list(title = "Timepoint")
  )

Affective Committment

Affective Committment Normality

ac_diff <- final_io_data$Pre_Affective - final_io_data$Post_Affective

qqPlot(ac_diff, main = "Q-Q Plot of Affective Committment Differences", col = "darkred", col.lines = "indianred1")

[1] 92 51

Affective Committment Test

t.test(final_io_data$Pre_Affective, final_io_data$Post_Affective, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Affective and final_io_data$Post_Affective

Test statistic	df	P value	Alternative hypothesis	mean difference
-2.554	77	0.01263 *	two.sided	-0.2651

cohensD(final_io_data$Pre_Affective, final_io_data$Post_Affective, method = "paired") 

[1] 0.2891605

Affective Committment Graph

long_data <- stack(final_io_data[c("Pre_Affective", "Post_Affective")])
names(long_data) <- c("Affective_Committment", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Affective", "Post_Affective"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Affective_Committment,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("indianred1", "darkred")
) %>%
  layout(
    title = "Affective Committment Changes Across Semester", 
    yaxis = list(title = "Total Average Affective Committment"),
    xaxis = list(title = "Timepoint")
  )

Normative Committment

Normative Committment Normality

nc_diff <- final_io_data$Pre_Normative - final_io_data$Post_Normative

qqPlot(nc_diff, main = "Q-Q Plot of Normative Committment Differences", col = "violetred4", col.lines = "plum2")

[1] 57 74

Normative Committment Test

t.test(final_io_data$Pre_Normative, final_io_data$Post_Normative, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Normative and final_io_data$Post_Normative

Test statistic	df	P value	Alternative hypothesis	mean difference
0.5147	77	0.6082	two.sided	0.07564

cohensD(final_io_data$Pre_Normative, final_io_data$Post_Normative, method = "paired") 

[1] 0.05828294

Normative Committment Graph

long_data <- stack(final_io_data[c("Pre_Normative", "Post_Normative")])
names(long_data) <- c("Normative_Committment", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Normative", "Post_Normative"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Normative_Committment,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("plum2", "violetred4")
) %>%
  layout(
    title = "Normative Committment Changes Across Semester", 
    yaxis = list(title = "Total Average Normative Committment"),
    xaxis = list(title = "Timepoint")
  )

Continuance Committment

Continuance Committment Normality

cc_diff <- final_io_data$Pre_Continuance - final_io_data$Post_Continuance

qqPlot(cc_diff, main = "Q-Q Plot of Continuance Committment Differences", col = "sienna3", col.lines = "sandybrown")

[1] 88 30

Continuance Committment Test

t.test(final_io_data$Pre_Continuance, final_io_data$Post_Continuance, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Continuance and final_io_data$Post_Continuance

Test statistic	df	P value	Alternative hypothesis	mean difference
0.8802	77	0.3815	two.sided	0.1092

cohensD(final_io_data$Pre_Continuance, final_io_data$Post_Continuance, method = "paired") 

[1] 0.09966727

Continuance Committment Graph

long_data <- stack(final_io_data[c("Pre_Continuance", "Post_Continuance")])
names(long_data) <- c("Continuance_Committment", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Continuance", "Post_Continuance"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Continuance_Committment,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("sandybrown", "sienna3")
) %>%
  layout(
    title = "Continuance Committment Changes Across Semester", 
    yaxis = list(title = "Total Average Continuance Committment"),
    xaxis = list(title = "Timepoint")
  )

Engagement

Engagement Normality

eng_diff <- final_io_data$`Pre_Engagement` - final_io_data$`Post_Engagement`

qqPlot(eng_diff, main = "Q-Q Plot of Engagement Differences", col = "darkcyan", col.lines = "lightseagreen")

[1]  55 104

Engagement Test

t.test(final_io_data$`Pre_Engagement`, final_io_data$`Post_Engagement`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Engagement and final_io_data$Post_Engagement

Test statistic	df	P value	Alternative hypothesis	mean difference
0.07458	76	0.9407	two.sided	0.007937

cohensD(final_io_data$`Pre_Engagement`, final_io_data$`Post_Engagement`, method = "paired") 

[1] 0.008499205

Engagement Graph

long_data <- stack(final_io_data[c("Pre_Engagement", "Post_Engagement")])
names(long_data) <- c("Engagement", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Engagement", "Post_Engagement"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Engagement,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("lightseagreen", "darkcyan")
) %>%
  layout(
    title = "Engagement Changes Across Semester", 
    yaxis = list(title = "Total Average Engagement"),
    xaxis = list(title = "Timepoint")
  )

Safety

Safety Normality

safety_diff <- final_io_data$`Pre_Safety` - final_io_data$`Post_Safety`

qqPlot(safety_diff, main = "Q-Q Plot of Safety Differences", col = "cadetblue4", col.lines = "cadetblue2")

[1]  64 106

Safety Test

t.test(final_io_data$`Pre_Safety`, final_io_data$`Post_Safety`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Safety and final_io_data$Post_Safety

Test statistic	df	P value	Alternative hypothesis	mean difference
0.2566	77	0.7981	two.sided	0.02137

cohensD(final_io_data$`Pre_Safety`, final_io_data$`Post_Safety`, method = "paired") 

[1] 0.02905968

Safety Graph

long_data <- stack(final_io_data[c("Pre_Safety", "Post_Safety")])
names(long_data) <- c("Safety", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Safety", "Post_Safety"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Safety,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("cadetblue2", "cadetblue4")
) %>%
  layout(
    title = "Safety Changes Across Semester", 
    yaxis = list(title = "Total Average Safety"),
    xaxis = list(title = "Timepoint")
  )

CWB

CWB Normality

cwb_diff <- final_io_data$`Pre_CWB` - final_io_data$`Post_CWB`

qqPlot(cwb_diff, main = "Q-Q Plot of CWB Differences", col = "rosybrown4", col.lines = "rosybrown2")

[1]  20 106

CWB Test

t.test(final_io_data$`Pre_CWB`, final_io_data$`Post_CWB`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_CWB and final_io_data$Post_CWB

Test statistic	df	P value	Alternative hypothesis	mean difference
-1.649	77	0.1032	two.sided	-0.07051

cohensD(final_io_data$`Pre_CWB`, final_io_data$`Post_CWB`, method = "paired") 

[1] 0.1867107

CWB Graph

long_data <- stack(final_io_data[c("Pre_CWB", "Post_CWB")])
names(long_data) <- c("CWB", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_CWB", "Post_CWB"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~CWB,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("rosybrown2", "rosybrown4")
) %>%
  layout(
    title = "CWB Changes Across Semester", 
    yaxis = list(title = "Total Average CWB"),
    xaxis = list(title = "Timepoint")
  )

Job Search

Job Search Normality

jobsearch_diff <- final_io_data$`Pre_Job Search` - final_io_data$`Post_Job Search`

qqPlot(jobsearch_diff, main = "Q-Q Plot of Job Search Differences", col = "darkgoldenrod3", col.lines = "khaki3")

[1] 32 55

Job Search Test

t.test(final_io_data$`Pre_Job Search`, final_io_data$`Post_Job Search`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Job Searchand `final_io_data$`Post_Job Search

Test statistic	df	P value	Alternative hypothesis	mean difference
-3.656	77	0.0004662 * * *	two.sided	-0.4712

cohensD(final_io_data$`Pre_Job Search`, final_io_data$`Post_Job Search`, method = "paired") 

[1] 0.4139586

Job Search Graph

long_data <- stack(final_io_data[c("Pre_Job Search", "Post_Job Search")])
names(long_data) <- c("Job_Search", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Job Search", "Post_Job Search"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Job_Search,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("khaki3", "darkgoldenrod3")
) %>%
  layout(
    title = "Job Search Changes Across Semester", 
    yaxis = list(title = "Total Average Job Search"),
    xaxis = list(title = "Timepoint")
  )

Appendix

Depressive Symptoms

Depressive Symptoms Normality

cesd_diff <- final_io_data$`Pre_CESD` - final_io_data$`Post_CESD`

qqPlot(na.omit(cesd_diff), main = "Q-Q Plot of CESD Differences", col = "midnightblue", col.lines = "lightslateblue")

[1] 64 84

Depressive Symptoms Test

t.test(final_io_data$`Pre_CESD`, final_io_data$`Post_CESD`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_CESD and final_io_data$Post_CESD

Test statistic	df	P value	Alternative hypothesis	mean difference
-2.731	128	0.007215 * *	two.sided	-0.1194

cohensD(final_io_data$`Pre_CESD`, final_io_data$`Post_CESD`, method = "paired") 

[1] 0.2404124

Depressive Symptoms Graph

long_data <- stack(final_io_data[c("Pre_CESD", "Post_CESD")])
names(long_data) <- c("CESD", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_CESD", "Post_CESD"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~CESD,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("lightslateblue", "midnightblue")
) %>%
  layout(
    title = "CESD Changes Across Semester", 
    yaxis = list(title = "Total Average CESD"),
    xaxis = list(title = "Timepoint")
  )

Happiness

Happiness Normality

happiness_diff <- final_io_data$Pre_Happiness - final_io_data$Post_Happiness


qqPlot(happiness_diff, main = "Q-Q Plot of Happiness Differences")

[1]  3 20

Happiness Test

t.test(final_io_data$Pre_Happiness, final_io_data$Post_Happiness, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Happiness and final_io_data$Post_Happiness

Test statistic	df	P value	Alternative hypothesis	mean difference
2.507	127	0.01344 *	two.sided	0.1866

cohensD(final_io_data$Pre_Happiness, final_io_data$Post_Happiness, method = "paired") 

[1] 0.2215755

Happiness Graph

long_data <- stack(final_io_data[c("Pre_Happiness", "Post_Happiness")])
names(long_data) <- c("Happiness", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Happiness", "Post_Happiness"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Happiness,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("olivedrab3", "olivedrab4")
) %>%
  layout(
    title = "Happiness Changes Across Semester", 
    yaxis = list(title = "Total Average Happiness"),
    xaxis = list(title = "Timepoint")
  )

Differential

Differential Normality

diff_var_diff <- final_io_data$`Pre_Differential` - final_io_data$`Post_Differential`

qqPlot(na.omit(diff_var_diff), main = "Q-Q Plot of Differential Differences", col = "darkmagenta", col.lines = "plum3")

[1] 82  3

Differential Test

t.test(final_io_data$`Pre_Differential`, final_io_data$`Post_Differential`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Differential and final_io_data$Post_Differential

Test statistic	df	P value	Alternative hypothesis	mean difference
0.3957	128	0.693	two.sided	0.01249

cohensD(final_io_data$`Pre_Differential`, final_io_data$`Post_Differential`, method = "paired") 

[1] 0.03483614

Differential Graph

long_data <- stack(final_io_data[c("Pre_Differential", "Post_Differential")])
names(long_data) <- c("Differential", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Differential", "Post_Differential"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Differential,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("plum3", "darkmagenta")
) %>%
  layout(
    title = "Differential Changes Across Semester", 
    yaxis = list(title = "Total Average Differential"),
    xaxis = list(title = "Timepoint")
  )

Life Satisfaction

SWLS Normality

swls_diff <- final_io_data$`Pre_SWLS` - final_io_data$`Post_SWLS`

qqPlot(na.omit(swls_diff), main = "Q-Q Plot of SWLS Differences", col = "seagreen", col.lines = "palegreen")

[1] 83  3

SWLS Test

t.test(final_io_data$`Pre_SWLS`, final_io_data$`Post_SWLS`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_SWLS and final_io_data$Post_SWLS

Test statistic	df	P value	Alternative hypothesis	mean difference
-0.6717	127	0.503	two.sided	-0.05352

cohensD(final_io_data$`Pre_SWLS`, final_io_data$`Post_SWLS`, method = "paired") 

[1] 0.05936783

SWLS Graph

long_data <- stack(final_io_data[c("Pre_SWLS", "Post_SWLS")])
names(long_data) <- c("SWLS", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_SWLS", "Post_SWLS"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~SWLS,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("palegreen", "seagreen")
) %>%
  layout(
    title = "SWLS Changes Across Semester", 
    yaxis = list(title = "Total Average SWLS"),
    xaxis = list(title = "Timepoint")
  )

Stress

Stress Normality

stress_diff <- final_io_data$`Pre_Stress` - final_io_data$`Post_Stress`

qqPlot(na.omit(stress_diff), main = "Q-Q Plot of Stress Differences", col = "firebrick4", col.lines = "lightcoral")

[1] 71 86

Stress Test

t.test(final_io_data$`Pre_Stress`, final_io_data$`Post_Stress`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Stress and final_io_data$Post_Stress

Test statistic	df	P value	Alternative hypothesis	mean difference
-0.4162	128	0.6779	two.sided	-0.01993

cohensD(final_io_data$`Pre_Stress`, final_io_data$`Post_Stress`, method = "paired") 

[1] 0.03664871

Stress Graph

long_data <- stack(final_io_data[c("Pre_Stress", "Post_Stress")])
names(long_data) <- c("Stress", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Stress", "Post_Stress"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Stress,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("lightcoral", "firebrick4")
) %>%
  layout(
    title = "Stress Changes Across Semester", 
    yaxis = list(title = "Total Average Stress"),
    xaxis = list(title = "Timepoint")
  )

Anxiety

Anxiety Normality

anx_diff <- final_io_data$`Pre_Anxiety` - final_io_data$`Post_Anxiety`

qqPlot(na.omit(anx_diff), main = "Q-Q Plot of Anxiety Differences", col = "darkorange3", col.lines = "moccasin")

[1] 86 33

Anxiety Test

t.test(final_io_data$`Pre_Anxiety`, final_io_data$`Post_Anxiety`, paired = TRUE) |> 
  pander()

Paired t-test: final_io_data$Pre_Anxiety and final_io_data$Post_Anxiety

Test statistic	df	P value	Alternative hypothesis	mean difference
-0.1627	128	0.871	two.sided	-0.007752

cohensD(final_io_data$`Pre_Anxiety`, final_io_data$`Post_Anxiety`, method = "paired") 

[1] 0.01432335

Anxiety Graph

long_data <- stack(final_io_data[c("Pre_Anxiety", "Post_Anxiety")])
names(long_data) <- c("Anxiety", "Timepoint")

long_data$Timepoint <- factor(
  long_data$Timepoint, 
  levels = c("Pre_Anxiety", "Post_Anxiety"),
  labels = c("Pre", "Post")
)

plot_ly(
  data = long_data, 
  y = ~Anxiety,
  x = ~Timepoint,
  type = "box", 
  color = ~Timepoint,
  colors = c("moccasin", "darkorange3")
) %>%
  layout(
    title = "Anxiety Changes Across Semester", 
    yaxis = list(title = "Total Average Anxiety"),
    xaxis = list(title = "Timepoint")
  )