Analyzing Students' Mental Health
Project Description
Does going to university in a different country affect your mental health? A Japanese international university surveyed its students in 2018 and published a study the following year that was approved by several ethical and regulatory boards.
The study found that international students have a higher risk of mental health difficulties than the general population, and that social connectedness (belonging to a social group) and acculturative stress (stress associated with joining a new culture) are predictive of depression.
Explore the students data using PostgreSQL to find out if you would come to a similar conclusion for international students and see if the length of stay is a contributing factor.
Here is a data description of the columns you may find helpful.
Data Description
| Field Name | Description |
|---|---|
inter_dom | Types of students (international or domestic) |
japanese_cate | Japanese language proficiency |
english_cate | English language proficiency |
academic | Current academic level (undergraduate or graduate) |
age | Current age of student |
stay | Current length of stay in years |
todep | Total score of depression (PHQ-9 test) |
tosc | Total score of social connectedness (SCS test) |
toas | Total score of acculturative stress (ASISS test) |
Implementation
Dataset
-- Run this code to view the data in students
SELECT *
FROM students;There are 272 rows with non-null values in this dataset, representing 272 students/survery participants. This dataset contains information on: the student type (international/domestic), language proficiency (Japanese & English), academic level (undergraduate/graduate), current age, current length of stay in years, and scores for depression, social connectedness, and acculturative tests. These will be used to answer the following questions:
- Do international students have a higher risk of mental health difficulties than the general population?
- Are social connectedness (belonging to a social group) and acculturative stress (stress associated with joining a new culture) predictive of depression?
Solution
-- Start coding here...
SELECT stay, COUNT(inter_dom) AS count_int, ROUND(AVG(todep),2) AS average_phq, ROUND(AVG(tosc),2) AS average_scs, ROUND(AVG(toas),2) AS average_as
FROM students
WHERE inter_dom = 'Inter'
GROUP BY stay -- forgot this one but it makes sense because in order to sort the results by length of stay with aggregate functions functioning, you need to first group it by something to get the total count of students with their avg scores
ORDER BY stay DESC
LIMIT 9;-- Start coding here...
SELECT stay, COUNT(inter_dom) AS count_dom, ROUND(AVG(todep),2) AS average_phq, ROUND(AVG(tosc),2) AS average_scs, ROUND(AVG(toas),2) AS average_as
FROM students
WHERE inter_dom = 'Dom'
GROUP BY stay -- forgot this one but it makes sense because in order to sort the results by length of stay with aggregate functions functioning, you need to first group it by something to get the total count of students with their avg scores
ORDER BY stay DESC
LIMIT 9;Description of Code
FROM the students dataset, WHERE the entry represents an "Inter"national student, GROUPed BY the length of stay in years, SELECTing the stay, COUNT of international students, AVG of the depression test, AVG of the social connectedness test, and AVG of the acculturative stress test columns, and ORDERing BY the length of stay in years by longest to shortest, limiting to 9 entries.
Description of Output
9 rows and 6 columns of output:
- column 1: index of entries/rows starting with 0 to 8 for 9 total rows
- column 2:
stayrepresents the length of the stay in years, ordered from largest to smallest value, which is 10 years to 1 year - column 3:
count_intrepresents the count of International students that correspond to the stay length in that row - column 4:
avg_phqrepresents the avg score on the depression test (todep/PHQ test) of all students in that row - column 5:
avg_scsrepresents the avg score on the social connectedness test (tosc/SCS test) of all students in that row - column 6:
avg_asrepresents the avg score on the acculturative stress test (toas/ASISS test) of all students in that row
For example, in row index 0, there is 1 student who had a stay of 10 years, and had an avg PHQ of 13, SCS of 32, and AS of 50. In row index 8, there are 95 students who had a stay of 1 year, and had a PHQ of 7.48, SCS of 38.11, and AS of 72.8
Findings
The longest stay in the dataset for an International student was 10 years and the shortest was 1 year. The lowest count of students was 1 student and the highest count was 95 students. The highest PHQ/depression score was 13 and the lowest was 0. The highest SCS/social connectedness score was 48 and the lowest was 32. The highest AS/acculturative stress score was 91 and the lowest was 50.
Based on the results, higher avg PHQ scores relates to higher avg AS scores and the lower avg SCS scores. Additionally, international students appear to have a higher risk of depression than domestic students. Although, I would argue that the dataset is skewed/biased towards international students and has more data points related to international students. I would also argue that the SCS and AS scores are not as predictive of PHQ as the study initially found. This is because the SCS scores across the board in the results stay within the 30s range, while the SCS range in the dataset is between 8-48. The AS scores are more varied but still do not go up to the highest value in the dataset, which is 145. The PHQ scores in the results don't go higher than 13, while in the dataset, they go up to 25. In order to address these inconsistencies/issues in the data and its results and to make the results clearer to better answer the questions, I would recommend more data be collected on more students, with an equal amount of international and domestic students accounted for in the data.
In conclusion, international students appear to have a higher risk of mental health difficulties than the general population, and social connectedness and acculturative stress appear to be predictive of depression. However, there could be more data points to better support these findings.