The Effect of Income Level on Life Expectancy: the Case of China, Japan, and South Korea

set up

import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns import plotly.express as px import plotly.graph_objects as go #chart_studio.tools.set_credentials_file(username='econdata777', api_key='ADDhere') import statsmodels.api as sm import statsmodels.formula.api as smf import warnings #warnings.filterwarnings('ignore')

Introduction

For all people, health comes first. A healthy body is the foundation of individual development while a healthy population is the cornerstone of a country's prosperity (ZHANG, 2019). Life expectancy is one of the important indicators used to evaluate the quality of life of a country's population, as well as the level of health of its citizens.

Entering the 21 century, China's rapid economic development has led to a significant improvement in the living standards of people and an increase in income levels, and as a result, more and more people are paying attention to physical and mental health (ZHOU, G). Japan and Korea, as developed countries in East Asia, are both high-income countries with the highest life expectancy in the world.

Therefore, this program intends to study the development of national income per capita(GNI per capita) and life expectancy in China, Japan, and South Korea during the decade 2010-2019, and the status of the impact of income level on life expectancy.

Method & Data

Firstly, the development of GNI per capita and life expectancy in China, Japan and Korea during 2010-2019 is shown through data visualization.

Secondly, the regression relationship between GNI per capita and life expectancy is explored by regression function.

Here is a simple regression model by statsmodels library:

y=β0+β1(x)+ε

y=life expenctancy while x=GDI per capita. β1 is the coefficient and ε is the error term.

Import data from Global Data Lab (Published in 7 June 2021)

df=pd.read_csv("/work/SHDI-SGDI-Total 5.0.csv") df

Descriptive Statistics

Data Description

data_description=pd.read_csv("/work/SHDI-SGDI-5.0-Vardescription.csv") data_description

Select data & variables

df_well = df[['country','region','iso_code','pop','level','year','lgnic','lifexp' ]] df_well

Select China, Japan, South Korea

df3_well= df_well[df_well.country.isin(['China','Japan','South Korea'])] df3_well

Select data from 2010-2019

df3_wellt = df3_well[(df3_well['year'] >= 2010) & (df['year'] <= 2019)] df3_wellt

df3_wellt.describe()

Data on Regional Level

df3_wellts=df3_wellt[df3_wellt.level !='National'] df3_wellts

Data of China, Japan, South Korean seperately

dfC_wellts= df3_wellts[df3_wellts.country.isin(['China'])] dfC_wellts

dfJ_wellts= df3_wellts[df3_wellts.country.isin(['Japan'])] dfJ_wellts

dfS_wellts= df3_wellts[df3_wellts.country.isin(['South Korea'])] dfS_wellts

Exploratory Data Analysis

Line Plot on Regional Level of China

px.line(dfC_wellts, x = 'year', y='lgnic', hover_name= 'lgnic', color= 'region' )

Choropleth Map on National Level

px.choropleth( df_well, locations="iso_code", color="lifexp", hover_name="country", animation_frame="year", color_continuous_scale=px.colors.sequential.Plasma, projection="natural earth") #choropleth-maps

Strip Chart on Regional Level

px.strip(df3_wellts, x = 'lgnic', y = 'country', range_x= [8, 11], color = 'country', hover_name= 'region', hover_data = ['lgnic'], animation_frame= 'year' )

Box Plot on Regional Level

px.box(df3_wellts, x = 'lifexp', y = 'country', range_x= [65, 88], color = 'country', hover_name= 'region', hover_data = ['lifexp'], animation_frame= 'year' )

Regression Analysis

Three East Asian Countries as a Whole

smf.ols(formula='lifexp~lgnic', data=df3_wellts.query("year == 2019")).fit().summary()

China

smf.ols(formula='lifexp~lgnic', data=dfC_wellts.query("year == 2019")).fit().summary()

Conclusion

The 2019's data show that income levels in China, Japan and Korea as a whole play a positive role in life expectancy, where if China's average GNI increases by 1 unit(1000 US dollars), Chinese life expectancy will increases by 4.7642 years.

References

https://deepnote.com/@carlos-mendez/PYTHON-Plotly-Express-3e900d54-8143-405b-8be2-266157d4ec75).

https://globaldatalab.org/shdi/download_files/

https://plotly.com/python/treemaps/

https://deepnote.com/workspace/class-statistics-and-data-science-195b828d-b4d8-4c59-9732-0da5ee3725f5/project/c02-Simple-reg-c379f625-4a76-454f-ad75-9d11f5efe4cd/%2Fnotebook.ipynb

ZHANG,J (2019). Impact of residence's income on health- Empirical Analysis Based on CFPS (Master's thesis, JIANGXI UNIVERSITY OF FINANCE AND ECONOMICS).

ZHOU,G; FAN,G, & SHEN, G. (2014). The Income Disparity, the Social Capital and Health: A Case Study Based on China Family Panel Studies. Management World, (7), 12-21.

.css-15w88e5{color:var(--chakra-colors-fg-neutral-primary);font-weight:inherit;letter-spacing:-0.09px;}The Effect of Income Level on Life Expectancy: the Case of China, Japan, and South Korea