Exploring Higher Education in the United States: A Comprehensive Analysis

collegescore4yr = read.csv("https://www.lock5stat.com/datasets3e/CollegeScores4yr.csv")

Introduction:

  The analysis of this dataset encompasses a diverse range of questions, shedding light on various aspects of higher education institutions in the United States. From examining the distribution of undergraduate enrollment and tuition costs to delving into the impact of school locale and control on educational outcomes, these questions provide valuable insights into the intricate landscape of American higher education. Whether investigating the influence of locale on standardized test scores or understanding how faculty salaries vary across regions, each question offers a unique perspective on the educational landscape, guiding students, educators, and policymakers in their decision-making processes.

Task:

  We use chatGPT to propose 10 questions inorder to analysis this data set as follow:

Q1).What is the frequency distribution of undergraduate enrollment in the dataset?

      The histogram of undergraduate enrollment reveals a positively skewed distribution. The majority of educational institutions in our dataset have a relatively small undergraduate enrollment, as indicated by the high peak on the left side of the histogram. This suggests that a substantial number of schools cater to a more limited student population. As we move towards the right side of the histogram, we encounter progressively fewer institutions with larger undergraduate enrollments. This distribution implies that while many institutions serve a smaller number of students, there are a select few with significantly larger student bodies. This skewness in the distribution highlights the diversity in the sizes of educational institutions, with a notable concentration of smaller schools.
hist(collegescore4yr$Enrollment, 
     main="Histogram of Undergraduate Enrollment", 
     xlab="Enrollment",
     col= "blue")

Q2). How does the distribution of net tuition revenue per FTE student vary across different regions of the country?

  The horizontal box plot shows the distribution of tuition revenue per full-time equivalent (FTE) student across different regions. Each box represents a region, and its position on the y-axis corresponds to the region's name. The width of each box indicates the range of tuition revenue, with longer whiskers suggesting greater variability. The line inside each box represents the median tuition revenue for that region. This plot allows us to compare the central tendency and variability of tuition costs among regions. from the plot,we can see that the West, Northeast, and Midwest tend to have higher median tuition revenue, while the Southeast, and Territory tend to have lower average costs per FTE student.
# Filter out rows with missing or non-numeric values in TuitionFTE
collegescore4yr_cleaned <- collegescore4yr[!is.na(collegescore4yr$TuitionFTE) & is.finite(collegescore4yr$TuitionFTE), ]

# Create a horizontal box plot of TuitionFTE by Region
library(ggplot2)
ggplot(collegescore4yr_cleaned, aes(y=Region, x=TuitionFTE)) + 
  geom_boxplot() + 
  labs(title="Horizontal Box Plot of Tuition Revenue per FTE by Region", y="Region", x="Tuition Revenue per FTE")

Q3). Are schools in urban locales associated with higher admission rates compared to schools in rural locales?

  The horizontal box plot reveals that admission rates for schools in both urban and rural locales share a similar distribution pattern, with the majority falling within a range of approximately 0.50 to 0.80. This suggests that most schools, regardless of their geographic setting, admit a substantial portion of their applicants. Median admission rates for both locales also tend to fall within this range, indicating comparable central tendencies. While some outliers exist, the overall patterns suggest that the locale alone may not be the primary factor influencing admission rates. Other school-specific factors likely play significant roles in determining admission rates. These findings underscore the need for prospective students to consider a wider range of factors beyond locale when evaluating their college choices.
  
# Load necessary libraries
library(ggplot2)

# Assuming 'collegescore4yr' is your DataFrame and columns 'Locale' and 'AdmitRate' contain the locale information and admission rates.

# Create a horizontal box plot to compare admission rates by school locale
ggplot(collegescore4yr, aes(x = AdmitRate, y = Locale, fill = Locale)) +
  geom_boxplot() +
  labs(
    title = "Admission Rates by School Locale",
    x = "Admission Rate",
    y = "School Locale"
  )
## Warning: Removed 360 rows containing non-finite values (`stat_boxplot()`).

Q4). Is there a relationship between the average monthly salary for full-time faculty and the completion rate of students?

  The scatter diagram of faculty salary versus completion rate provides a visual representation of the potential relationship between average monthly faculty salaries and student program completion rates at educational institutions.

  From the scatter diagram, we can observe a general trend where, as faculty salaries increase, there appears to be a tendency for higher completion rates. This is suggested by the overall positive slope of the points on the plot, indicating that institutions with higher faculty salaries often have higher completion rates.
  
plot(collegescore4yr$FacSalary, collegescore4yr$CompRate, xlab="Average Monthly Salary", ylab="Completion Rate",
     main="Scatter Diagram of Faculty Salary vs. Completion Rate")

Q5). What is the distribution of tuition costs for in-state students?

  The histogram reveals a negatively skewed histogram of in-state tuition costs among educational institutions indicates that a larger proportion of institutions within the dataset tend to charge higher in-state tuition fees. This distribution suggests that there is greater variability in tuition costs, with the majority of institutions leaning toward higher fees. However, there are still some institutions offering more affordable in-state tuition rates, although they represent a minority in the dataset. This histogram provides a clear visual representation of the distribution of tuition fees, highlighting the spectrum of pricing options available to in-state students at different higher education institutions.
  
hist(collegescore4yr$TuitionIn, 
     main="Distribution of Tuition Costs for In-State Students",
     xlab="In-State Tuition Costs",
     ylab="Frequency",
     col="blue")

Q6). How does the average debt for students who complete their program vary among schools in different locales (City, Rural, Suburb, Town)?

  In this analysis, we can see that in city and suburb tend to have higher Dept than Rural and Town.  The variation in mean student debt among locales reflects the economic and educational landscape of these areas. City and Suburb locales offer a diverse but often higher-cost array of educational options, while Rural and Town locales prioritize affordability, resulting in lower mean student debt levels for residents in these areas.
collegescore4yr_cleaned <- collegescore4yr[!is.na(collegescore4yr$Debt) & is.finite(collegescore4yr$Debt), ]

# Load the ggplot2 library for creating plots
library(ggplot2)

# Create a horizontal box plot of average debt by locale with cleaned data
ggplot(collegescore4yr_cleaned, aes(x=Debt, y=Locale, fill=Locale)) +
  geom_boxplot() +
  labs(title="Average Debt by Locale",
       x="Average Debt",
       y="Locale",
       fill="Locale") +
  scale_fill_discrete(name="Locale")

Q7). How does school locale (City, Rural, Suburb, Town) impact the percentage of students receiving Pell grants?

  From the  box plot, it illustrates that across various school locales (City, Rural, Suburb, Town), there is a remarkable similarity in the distribution of Pell grant percentages. The medians tend to fall within a consistent range of approximately 25% to 50%, indicating that, on average, a significant portion of students across locales qualify for Pell grants due to financial need. The uniformity in variability, as seen in the interquartile ranges, suggests a consistent distribution pattern regardless of geographic settings. While this reveals a shared central tendency in Pell grant percentages, it's important to consider the specific contextual factors influencing these percentages, as well as the potential implications for financial aid policies and equity in education.
library(ggplot2)

collegescore4yr_cleaned <- collegescore4yr[!is.na(collegescore4yr$Pell) & is.finite(collegescore4yr$Pell), ]
# Create a box plot to compare Pell grant percentages by school locale
ggplot(collegescore4yr_cleaned, aes(x = Pell, y = Locale, fill = Locale)) +
  geom_boxplot() +
  labs(
    title = "Impact of School Locale on Pell Grant Percentages",
    x = "Percentage of Students Receiving Pell Grants",
    y = "School Locale"
  )

Q8). Are there significant differences in the average SAT scores (AvgSAT) among schools located in different types of locales (City, Rural, Suburb, Town)?

  From the horizontal box plot, it becomes evident that there are distinct differences in average SAT scores (AvgSAT) among schools located in different types of locales. Specifically, schools in urban locales, categorized as "City," exhibit the highest mean average SAT scores, indicating that students in urban areas tend to perform exceptionally well on SAT exams. Following closely behind are schools situated in "Suburb" locales, displaying the second-highest average SAT scores, suggesting that suburban environments also foster strong academic performance. In contrast, schools in "Town" locales rank third in terms of average SAT scores, while those in "Rural" areas have the lowest mean SAT scores. This analysis underscores the influence of locale on students' standardized test performance, highlighting the importance of considering locale when evaluating academic outcomes.
# Load necessary libraries
library(ggplot2)

# Assuming 'collegescore4yr' is your DataFrame and columns 'Locale' and 'AvgSAT' contain locale information and average SAT scores.

# Create a horizontal box plot to compare AvgSAT scores by school locale
ggplot(collegescore4yr, aes(x = AvgSAT, y = Locale, fill = Locale)) +
  geom_boxplot() +
  labs(
    title = "Average SAT Scores by School Locale",
    x = "Average SAT Scores",
    y = "School Locale"
  ) +
  theme(axis.text.y = element_text(hjust = 1))  # Adjust y-axis labels for better readability
## Warning: Removed 735 rows containing non-finite values (`stat_boxplot()`).

Q9). What is the distribution of instructional spending per FTE student?

  Examining the horizontal box plot, it becomes evident that there are significant disparities in the distribution of average monthly faculty salaries for full-time faculty members across diverse regions of the country. The Northeast region emerges as the clear leader, boasting the highest mean average monthly faculty salary compared to all other regions. This suggests that educational institutions in the Northeast prioritize competitive compensation for their full-time faculty, potentially reflecting a combination of factors like cost of living and demand for quality educators. Following closely is the West region, which occupies the second position in terms of mean faculty salary, indicating a robust compensation structure for full-time faculty. Meanwhile, the Midwest and Southeast regions share the third position with relatively moderate mean faculty salaries, signifying a balance between regional factors and compensation. Lastly, the Territory region stands out with the lowest mean average monthly faculty salary, potentially reflecting unique economic conditions or educational priorities in this area. This nuanced analysis underscores the significance of regional differences in faculty salaries and provides valuable insights for educators and institutions navigating the landscape of higher education.
# Load necessary libraries
library(ggplot2)

# Assuming 'collegescore4yr' is your DataFrame and columns 'Region' and 'FacSalary' contain region information and faculty salaries.

# Create a horizontal box plot to compare faculty salaries by region
ggplot(collegescore4yr, aes(x = FacSalary, y = Region, fill = Region)) +
  geom_boxplot() +
  labs(
    title = "Faculty Salaries by Region",
    x = "Average Monthly Faculty Salary",
    y = "Region"
  ) +
  theme(axis.text.y = element_text(hjust = 1))  # Adjust y-axis labels for better readability
## Warning: Removed 54 rows containing non-finite values (`stat_boxplot()`).

Q10). How do tuition costs differ among different regions, and are there regions where tuition fees tend to be higher or lower on average?

The horizontal box plot provides insightful observations about the variation in in-state tuition fees across different regions. Notably, the Northwest and Midwest regions exhibit the highest mean tuition fees on average, suggesting that schools in these areas tend to charge more for in-state students. In contrast, the Southeast and West regions display comparatively lower average tuition fees, making them potentially more affordable options. It's particularly noteworthy that the Territory region stands out with the lowest tuition fees, signifying a region where education may be more cost-effective for in-state students. This analysis underscores the regional disparities in tuition costs, offering valuable insights for prospective students and policymakers alike.
# Load necessary libraries
library(ggplot2)

# Assuming 'collegescore4yr' is your DataFrame and columns 'Region' and 'TuitionIn' contain region information and in-state tuition fees.

# Create a horizontal box plot to compare in-state tuition fees by region
ggplot(collegescore4yr, aes(x = TuitionIn, y = Region, fill = Region)) +
  geom_boxplot() +
  labs(
    title = "In-State Tuition Fees by Region",
    x = "In-State Tuition Fees",
    y = "Region"
  ) +
  theme(axis.text.y = element_text(hjust = 1))  # Adjust y-axis labels for better readability
## Warning: Removed 94 rows containing non-finite values (`stat_boxplot()`).

Summary:

   The questions analyzed in this dataset reveal a multifaceted view of higher education in the United States. The frequency distribution of undergraduate enrollment highlights the diversity in institutional sizes, with many schools serving smaller student populations. Tuition costs, both for in-state students and across regions, vary significantly, impacting the affordability of higher education. The influence of locale on academic outcomes is evident, with urban schools tending to have higher SAT scores and rural schools often carrying lower student debt. Faculty salaries exhibit regional disparities, with the Northeast leading in compensation, and tuition fees differ among regions, with the Northwest and Midwest generally charging higher fees. These insights provide a comprehensive understanding of the complexities within the U.S. higher education landscape, informing decisions at both individual and institutional levels.