Project: Analyzing Students' Mental Health in SQL

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.

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)

DataFrameas

students

variable

-- Run this code to save the CSV file as students
SELECT * 
FROM 'students.csv';

CREATE TABLE students AS SELECT * 
FROM 'students.csv';

SELECT COUNT (*) AS total_records
FROM students;

SELECT inter_dom, COUNT (inter_dom)
FROM students
GROUP BY inter_dom;

SELECT ROUND(AVG(todep),2) AS average_phq,
	ROUND(MIN(todep),2) AS min_phq,
	ROUND(MAX(todep),2) AS max_phq,
	ROUND(AVG(tosc),2) AS average_scs,
	ROUND(MIN(tosc),2) AS min_scs,
	ROUND(MAX(tosc),2) AS max_scs,
	ROUND(AVG(toas),2) AS average_as,
	ROUND(MIN(toas),2) AS min_as,
	ROUND(MAX(toas),2) AS max_as
FROM students;

SELECT ROUND(AVG(todep),2) AS average_phq,
	ROUND(MIN(todep),2) AS min_phq,
	ROUND(MAX(todep),2) AS max_phq,
	ROUND(AVG(tosc),2) AS average_scs,
	ROUND(MIN(tosc),2) AS min_scs,
	ROUND(MAX(tosc),2) AS max_scs,
	ROUND(AVG(toas),2) AS average_as,
	ROUND(MIN(toas),2) AS min_as,
	ROUND(MAX(toas),2) AS max_as
FROM students
WHERE inter_dom='Inter';

SELECT stay,
	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
ORDER BY stay DESC;

DataFrameas

df

variable

-- Run this code to save the CSV file as students
SELECT * 
FROM 'students.csv';

CREATE TABLE df AS SELECT * 
FROM 'students.csv';

SELECT COUNT (*) AS total_records
FROM df;

SELECT inter_dom, COUNT (inter_dom)
FROM df
GROUP BY inter_dom;

SELECT
	ROUND(AVG(todep),2) AS average_phq,
	ROUND(MIN(todep),2) AS min_phq,
	ROUND(MAX(todep),2) AS max_phq,
	ROUND(AVG(tosc),2) AS average_scs,
	ROUND(MIN(tosc),2) AS min_scs,
	ROUND(MAX(tosc),2) AS max_scs,
	ROUND(AVG(toas),2) AS average_as,
	ROUND(MIN(toas),2) AS min_as,
	ROUND(MAX(toas),2) AS max_as
FROM df;

SELECT ROUND(AVG(todep),2) AS average_phq,
	ROUND(MIN(todep),2) AS min_phq,
	ROUND(MAX(todep),2) AS max_phq,
	ROUND(AVG(tosc),2) AS average_scs,
	ROUND(MIN(tosc),2) AS min_scs,
	ROUND(MAX(tosc),2) AS max_scs,
	ROUND(AVG(toas),2) AS average_as,
	ROUND(MIN(toas),2) AS min_as,
	ROUND(MAX(toas),2) AS max_as
FROM df
WHERE inter_dom='Inter';

SELECT stay,
	ROUND(AVG(todep),2) AS average_phq,
	ROUND(AVG(tosc),2) AS average_scs,
	ROUND(AVG(toas),2) AS average_as,
FROM df
WHERE inter_dom='Inter'
GROUP BY stay
ORDER BY stay DESC;