Depression in College Students

knitr::include_graphics("C:/Users/jman1/OneDrive/Documents/DepressedCollege.jpg")

Image Source: https://www.nami.org/depression-disorders/what-are-the-warning-signs-of-depression-in-college-students/

Introduction

For my topic, I chose to look into depression in students and other related factors like students academic pressure, study satisfaction, age and more. The data comes from Kaggle. For my cleaning, I simply use rename from dplyr to simply rename some of the columns for better readability. The data was collected through a series of willing anonymous participants of wide-ranging demographics throughout January and June 2023. I chose this topic because I wanted to see for myself how my certain behaviors could be affecting my academic performance. I also thought it would be interesting to see how I could potentially change these behaviors or inform others on how to change these behaviors for potenially better academic performance. The topic also just seemed interesting as I’ve always been into psychology and the development of different psychological traits (like depression). For background, I just read through the wikipedia page of depression some to better understand if any correlations between depression and academic behaviors were already found.

Citation: Wikipedia contributors. (2024, December 16). Depression (mood). Wikipedia. https://en.wikipedia.org/wiki/Depression_(mood)

library(tidyverse) #Load libraries & dataset
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(plotly)
## 
## Attaching package: 'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:stats':
## 
##     filter
## 
## The following object is masked from 'package:graphics':
## 
##     layout
library(reshape2)
## 
## Attaching package: 'reshape2'
## 
## The following object is masked from 'package:tidyr':
## 
##     smiths
studentDepression <- read_csv("DepressionData.csv")
## Rows: 502 Columns: 11
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (6): Gender, Sleep Duration, Dietary Habits, Have you ever had suicidal ...
## dbl (5): Age, Academic Pressure, Study Satisfaction, Study Hours, Financial ...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
studentDepression <- studentDepression %>% #Rename columns for better readability and accesss
  rename(Study_Satisfaction = `Study Satisfaction`)
studentDepression <- studentDepression %>%
  rename(Academic_Pressure = `Academic Pressure`)
studentDepression <- studentDepression %>%
  rename(Sleep_Duration = `Sleep Duration`)
studentDepression <- studentDepression %>%
  rename(Study_Hours = `Study Hours`)
studentDepression <- studentDepression %>%
  rename(Financial_Stress = `Financial Stress`)
model <- lm(Study_Satisfaction ~ Academic_Pressure + Study_Hours, studentDepression) # Linear model
summary(model) #Summarize model
## 
## Call:
## lm(formula = Study_Satisfaction ~ Academic_Pressure + Study_Hours, 
##     data = studentDepression)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -2.2965 -1.0838 -0.0581  1.0145  2.1417 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)        3.396401   0.175419  19.362   <2e-16 ***
## Academic_Pressure -0.099905   0.044066  -2.267   0.0238 *  
## Study_Hours       -0.003215   0.016367  -0.196   0.8443    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.369 on 499 degrees of freedom
## Multiple R-squared:  0.01039,    Adjusted R-squared:  0.006427 
## F-statistic:  2.62 on 2 and 499 DF,  p-value: 0.07378
plot(model) # Plot the model

The low adjusted R-squared value of around 0.64% indicates that study satisfaction, surprisingly to me, isn’t actually very much if at all related to the academic pressure one faces or their study hours. The p-value of around 7.4% further indicates that this isn’t a statistically significant result. The equation model is as follows: Study Satisfaction = 3.3964 - 0.0999 * Academic Pressure - 0.0032 * Study Hours.
box_plot <- ggplot(studentDepression, aes(x = Gender, y = Study_Satisfaction, fill = Depression)) + # Create interactive box plot
  geom_boxplot(outlier.color = "red", outlier.shape = 16) +
  labs(
    title = "Study Satisfaction by Gender and Depression Status",
    x = "Gender",
    y = "Study Satisfaction (1-10 Scale)",
    fill = "Depression",
    caption = "Data Source: https://www.kaggle.com/datasets/ikynahidwin/depression-student-dataset"
  ) +
  scale_fill_manual(values = c("#FF9999", "#66B2FF")) +
  theme_classic()
box_plot

interactive_box_plot <- ggplotly(box_plot)
interactive_box_plot
This box plot visualization shows that study satisfaction of depressed males is somewhat higher than that for females, although interesting, for non-depressed males and females, this gap in study satisfaction disappears.
bar_chart <- ggplot(studentDepression, aes(x = `Dietary Habits`, fill = `Have you ever had suicidal thoughts ?`)) + #Create bar chart 
  geom_bar(position = "fill") +
  labs(
    title = "Proportion of Suicidal Thoughts by Dietary Habits",
    x = "Dietary Habits",
    y = "Proportion",
    fill = "Suicidal Thoughts",
    caption = "Data Source: https://www.kaggle.com/datasets/ikynahidwin/depression-student-dataset"
  ) +
  scale_fill_manual(values = c("#F8766D", "#00BFC4")) +
  theme_light()

bar_chart

This bar chart shows that for students with unhealthy dietary habits, suicidal thoughts tend to be slightly more prevalent compared to those with healthy dietary habits. This goes to show that a good diet is one factor of many that can potentially ward off depressive attitudes.
density_plot <- ggplot(studentDepression, aes(x = Sleep_Duration, fill = Depression)) + #Create interactive density plot
  geom_density(alpha = 0.6) +
  labs(
    title = "Sleep Duration by Depression Status",
    x = "Sleep Duration (Hours)",
    y = "Density",
    fill = "Depression Status",
    caption = "Data Source: https://www.kaggle.com/datasets/ikynahidwin/depression-student-dataset"
  ) +
  scale_fill_manual(values = c("#8DA0CB", "#FC8D62")) +
  theme_bw() +
  theme(
    plot.title = element_text(hjust = 0.5, size = 14, face = "bold"),
    axis.text = element_text(size = 10),
    axis.title = element_text(size = 12),
    legend.title = element_text(size = 12)
  )

interactive_density_plot <- ggplotly(density_plot)
interactive_density_plot
This density plot simply shows that college students most often get very few hours of sleep. This is likely an unfortunate by-product of the demanding college student workload, although this lack of sleep, as seen earlier can cause complications in student’s mental health as well as decreased academic performance.