# A tibble: 10,545 × 8
country continent region decade year life_expectancy gdp_cap_ppp Score
<chr> <fct> <fct> <fct> <int> <dbl> <dbl> <dbl>
1 Albania Europe South… 1960s 1960 62.9 2660 NA
2 Algeria Africa North… 1960s 1960 47.5 6480 NA
3 Angola Africa Middl… 1960s 1960 36.0 2300 NA
4 Antigua and … Americas Carib… 1960s 1960 63.0 3630 NA
5 Argentina Americas South… 1960s 1960 65.4 10200 NA
6 Armenia Asia Weste… 1960s 1960 66.9 6670 NA
7 Aruba Americas Carib… 1960s 1960 65.7 NA NA
8 Australia Oceania Austr… 1960s 1960 70.9 16100 NA
9 Austria Europe Weste… 1960s 1960 68.8 12000 NA
10 Azerbaijan Asia Weste… 1960s 1960 61.3 5500 NA
# … with 10,535 more rows
# A tibble: 10,545 × 8
country continent region decade year life_expectancy gdp_cap_ppp Score
<chr> <fct> <fct> <fct> <int> <dbl> <dbl> <dbl>
1 Albania Europe South… 1960s 1960 62.9 2660 NA
2 Algeria Africa North… 1960s 1960 47.5 6480 NA
3 Angola Africa Middl… 1960s 1960 36.0 2300 NA
4 Antigua and … Americas Carib… 1960s 1960 63.0 3630 NA
5 Argentina Americas South… 1960s 1960 65.4 10200 NA
6 Armenia Asia Weste… 1960s 1960 66.9 6670 NA
7 Aruba Americas Carib… 1960s 1960 65.7 NA NA
8 Australia Oceania Austr… 1960s 1960 70.9 16100 NA
9 Austria Europe Weste… 1960s 1960 68.8 12000 NA
10 Azerbaijan Asia Weste… 1960s 1960 61.3 5500 NA
# … with 10,535 more rows
Introduction
This project is about basic welfare index. The provision of basic welfare is measured using standard observable human development indicators and two expert-based indicators from V-Dem that assess whether everyone in a given society has access to basic education and health care. All the indicators reflect the extent to which the basic needs of the population are being met.
Research Questions
Problems this project will explore:
Data Set
The project uses the Data Science Labs version of gapminder, with the following additional data sets from Gapminder.org:
Basic_welfare_index(IDEA)
The data set is available from Gapminder.org under a CC-BY 4.0 license.
Principal investigator
This project, Basic Welfare Index, was submitted on 12 June 2022 by Hazel, ID: 2019221022, in partial fulfillment of the requirements for ENG 3208A: Telling stories with Data, Shantou University, Spring Semester 2022
The box plot shows that from 1970s to 2010s, all the indices of continents are increasing, which means these continents made progresses from the perspective of BWI. During this period, Americas and Asia are statistically similar. The mean and median of the two continents are close. The mean index of Africa is the lowest and that of Europe keeps highest.
The result indicates that basic welfare index are related to economic development. With better economic development, the index may be higher; otherwise, it may be lower.
# A tibble: 156 × 7
term estimate std.error statistic p.value conf.low conf.high
<chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 (Intercept) -1131. 7.62 -149. 0 -1146. -1.12e+3
2 year 0.596 0.0038 156. 0 0.588 6.03e-1
3 gdp_cap_ppp 0.0001 0 12.8 0 0.0001 1 e-4
4 countryAlgeria -12.5 0.662 -18.9 0 -13.8 -1.12e+1
5 countryAngola -35.9 0.662 -54.3 0 -37.2 -3.46e+1
6 countryArgentina 0.913 0.668 1.37 0.172 -0.396 2.22e+0
7 countryArmenia -3.26 0.758 -4.31 0 -4.75 -1.78e+0
8 countryAustralia 17.1 0.695 24.6 0 15.8 1.85e+1
9 countryAustria 16.4 0.709 23.2 0 15.0 1.78e+1
10 countryAzerbaijan -16.3 0.758 -21.5 0 -17.8 -1.48e+1
# … with 146 more rows
# A tibble: 1 × 12
r.squared adj.r.squared sigma statistic p.value df logLik AIC BIC
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 0.978 0.977 3.03 1703. 0 155 -15350. 31013. 32068.
# … with 3 more variables: deviance <dbl>, df.residual <int>, nobs <int>
The plot shows that, at our 95% CI, we do NOT have a meaningful difference between United Kingdom & China or United Kingdom & Brazil, between Nigeria & China or Nigeria & Brazil, between China & Australia or Brazil & Australia, and between United Kingdom & Australia or China & Brazil. Otherwise, for our two other comparisions, we reject the NULL hypothesis. We have statistical results which indicate meaningful differences between the countries being compared.
The linear model shows that all of the 5 countries keep increasing, which matches the global trend. We also find that the indices of Australia and United Kingdom that are developed countries is the highest, that of China and Brazil that are developing countries is in the middle, and that of Nigeria that is less developed countries is the lowest. Thus, economy is a factor that strongly influences basic welfare index.
However, from 1970s to 1980s, this correlation does not happen between China and Nigeria, which is that China’s Per Capita GDP (PPP) is lower than Nigeria, but the index of China is higher than Nigeria. We conjecture that one of the reasons is that at that time China was experiencing disasters both from human and the nature, leading to economic depression.
In this chart, the adjusted R-squared value for the linear model: 0.977401 which shows that the relationship between economy and BWI is close. It is a positive correlation.
By these results, our assumption is verified. There are a strong and positive correlation between basic welfare and economic development. Those whose economic development are better have better performances in the indices.
However, in the linear model, we have found some unusual data in China and Nigeria, which implies that there are other factors influencing basic welfare index.
# A tibble: 156 × 7
term estimate std.error statistic p.value conf.low conf.high
<chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 (Intercept) -882. 7.38 -120. 0 -897. -868.
2 year 0.447 0.004 112. 0 0.439 0.455
3 life_expectancy 0.653 0.0112 58.4 0 0.631 0.674
4 countryAlgeria -9.48 0.537 -17.7 0 -10.5 -8.43
5 countryAngola -21.4 0.593 -36.0 0 -22.5 -20.2
6 countryArgentina 2.71 0.535 5.06 0 1.66 3.76
7 countryArmenia -0.340 0.615 -0.554 0.580 -1.55 0.864
8 countryAustralia 17.1 0.537 31.9 0 16.1 18.2
9 countryAustria 17.9 0.536 33.5 0 16.9 19.0
10 countryAzerbaijan -10.8 0.619 -17.5 0 -12.0 -9.60
# … with 146 more rows
# A tibble: 1 × 12
r.squared adj.r.squared sigma statistic p.value df logLik AIC BIC
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 0.986 0.985 2.45 2628. 0 155 -14050. 28414. 29469.
# … with 3 more variables: deviance <dbl>, df.residual <int>, nobs <int>
The plot shows that at our 95% CI, we do NOT have a meaningful difference between United Kingdom & China or United Kingdom & Brazil, between Nigeria & China or Nigeria & Brazil, between China & Australia or Brazil & Australia, and between United Kingdom & Australia or China & Brazil. Otherwise, for our two other comparisions, we reject the NULL hypothesis. We have statistical results which indicate meaningful differences between the countries being compared. Thus, the difference of life expectancy exists between different countries being compared.
The linear model shows that a linear positive correlation exists in these five countries. With the increasing life expectancy, BWI keeps increasing. In addition, similar to the result between per capita GDP(ppp) and BWI, the five countries are divided into three categories, Australia and United Kingdom, China and Brazil, and Nigeria, indicating different levels of life expectancy in different kinds of countries. According to data, countries with high life expectancy, such as Australia, perform better in basic welfare index. Thus, life expectancy is also the factor that influences BWI.
This project explored the relationship between basic welfare and economy, life expectancy, and also how the latter two influence basic welfare index. We found that with higher level of economy and healthy, the basic welfare index is higher, which means the better living standard. Therefore, basic welfare index is beneficial to figure out the development of a country.