Fa_Jiaxin_Research Report
2024-04-12
# List of packages
packages <- c("tidyverse", "infer", "fst", "modelsummary", "effects", "survey", "performance", "flextable", "broom", "effects", "scales", "ggridges", "viridis", "knitr", "kableExtra", "rmarkdown", "questionr")
# Install packages if they aren't installed already
new_packages <- packages[!(packages %in% installed.packages()[,"Package"])]
if(length(new_packages)) install.packages(new_packages)
# Load the packages
lapply(packages, library, character.only = TRUE)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
## Loading required package: carData
##
## lattice theme set by effectsTheme()
## See ?effectsTheme for details.
##
## Loading required package: grid
##
## Loading required package: Matrix
##
##
## Attaching package: 'Matrix'
##
##
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack
##
##
## Loading required package: survival
##
##
## Attaching package: 'survey'
##
##
## The following object is masked from 'package:graphics':
##
## dotchart
##
##
##
## Attaching package: 'flextable'
##
##
## The following object is masked from 'package:purrr':
##
## compose
##
##
##
## Attaching package: 'scales'
##
##
## The following object is masked from 'package:purrr':
##
## discard
##
##
## The following object is masked from 'package:readr':
##
## col_factor
##
##
## Loading required package: viridisLite
##
##
## Attaching package: 'viridis'
##
##
## The following object is masked from 'package:scales':
##
## viridis_pal
##
##
##
## Attaching package: 'kableExtra'
##
##
## The following objects are masked from 'package:flextable':
##
## as_image, footnote
##
##
## The following object is masked from 'package:dplyr':
##
## group_rows## [[1]]
## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [13] "grDevices" "utils" "datasets" "methods" "base"
##
## [[2]]
## [1] "infer" "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [7] "readr" "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [13] "graphics" "grDevices" "utils" "datasets" "methods" "base"
##
## [[3]]
## [1] "fst" "infer" "lubridate" "forcats" "stringr" "dplyr"
## [7] "purrr" "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [13] "stats" "graphics" "grDevices" "utils" "datasets" "methods"
## [19] "base"
##
## [[4]]
## [1] "modelsummary" "fst" "infer" "lubridate" "forcats"
## [6] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [11] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [16] "grDevices" "utils" "datasets" "methods" "base"
##
## [[5]]
## [1] "effects" "carData" "modelsummary" "fst" "infer"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[6]]
## [1] "survey" "survival" "Matrix" "grid" "effects"
## [6] "carData" "modelsummary" "fst" "infer" "lubridate"
## [11] "forcats" "stringr" "dplyr" "purrr" "readr"
## [16] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [21] "graphics" "grDevices" "utils" "datasets" "methods"
## [26] "base"
##
## [[7]]
## [1] "performance" "survey" "survival" "Matrix" "grid"
## [6] "effects" "carData" "modelsummary" "fst" "infer"
## [11] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [16] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [21] "stats" "graphics" "grDevices" "utils" "datasets"
## [26] "methods" "base"
##
## [[8]]
## [1] "flextable" "performance" "survey" "survival" "Matrix"
## [6] "grid" "effects" "carData" "modelsummary" "fst"
## [11] "infer" "lubridate" "forcats" "stringr" "dplyr"
## [16] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [21] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [26] "datasets" "methods" "base"
##
## [[9]]
## [1] "broom" "flextable" "performance" "survey" "survival"
## [6] "Matrix" "grid" "effects" "carData" "modelsummary"
## [11] "fst" "infer" "lubridate" "forcats" "stringr"
## [16] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [21] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [26] "utils" "datasets" "methods" "base"
##
## [[10]]
## [1] "broom" "flextable" "performance" "survey" "survival"
## [6] "Matrix" "grid" "effects" "carData" "modelsummary"
## [11] "fst" "infer" "lubridate" "forcats" "stringr"
## [16] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [21] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [26] "utils" "datasets" "methods" "base"
##
## [[11]]
## [1] "scales" "broom" "flextable" "performance" "survey"
## [6] "survival" "Matrix" "grid" "effects" "carData"
## [11] "modelsummary" "fst" "infer" "lubridate" "forcats"
## [16] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [21] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [26] "grDevices" "utils" "datasets" "methods" "base"
##
## [[12]]
## [1] "ggridges" "scales" "broom" "flextable" "performance"
## [6] "survey" "survival" "Matrix" "grid" "effects"
## [11] "carData" "modelsummary" "fst" "infer" "lubridate"
## [16] "forcats" "stringr" "dplyr" "purrr" "readr"
## [21] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [26] "graphics" "grDevices" "utils" "datasets" "methods"
## [31] "base"
##
## [[13]]
## [1] "viridis" "viridisLite" "ggridges" "scales" "broom"
## [6] "flextable" "performance" "survey" "survival" "Matrix"
## [11] "grid" "effects" "carData" "modelsummary" "fst"
## [16] "infer" "lubridate" "forcats" "stringr" "dplyr"
## [21] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [26] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [31] "datasets" "methods" "base"
##
## [[14]]
## [1] "knitr" "viridis" "viridisLite" "ggridges" "scales"
## [6] "broom" "flextable" "performance" "survey" "survival"
## [11] "Matrix" "grid" "effects" "carData" "modelsummary"
## [16] "fst" "infer" "lubridate" "forcats" "stringr"
## [21] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [26] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [31] "utils" "datasets" "methods" "base"
##
## [[15]]
## [1] "kableExtra" "knitr" "viridis" "viridisLite" "ggridges"
## [6] "scales" "broom" "flextable" "performance" "survey"
## [11] "survival" "Matrix" "grid" "effects" "carData"
## [16] "modelsummary" "fst" "infer" "lubridate" "forcats"
## [21] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [26] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [31] "grDevices" "utils" "datasets" "methods" "base"
##
## [[16]]
## [1] "rmarkdown" "kableExtra" "knitr" "viridis" "viridisLite"
## [6] "ggridges" "scales" "broom" "flextable" "performance"
## [11] "survey" "survival" "Matrix" "grid" "effects"
## [16] "carData" "modelsummary" "fst" "infer" "lubridate"
## [21] "forcats" "stringr" "dplyr" "purrr" "readr"
## [26] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [31] "graphics" "grDevices" "utils" "datasets" "methods"
## [36] "base"
##
## [[17]]
## [1] "questionr" "rmarkdown" "kableExtra" "knitr" "viridis"
## [6] "viridisLite" "ggridges" "scales" "broom" "flextable"
## [11] "performance" "survey" "survival" "Matrix" "grid"
## [16] "effects" "carData" "modelsummary" "fst" "infer"
## [21] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [26] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [31] "stats" "graphics" "grDevices" "utils" "datasets"
## [36] "methods" "base"ess <- read_fst("All-ESS-Data.fst")Introduction
Does a person’s level of education have a significant impact on job income? Some argue that it is better to study more than to accumulate more experience, and that experience is worth more than education; others argue that the level of education determines commercial value, and that the higher the level of education, the higher the employment salary. There may be a close relationship between education and income; therefore, the question of this study is to analyze what is the relationship between education and income in France?
The main current view is generally that investment in education can significantly improve the standard of living of individual residents, and in particular The impact of education on income is of great relevance. The other view, that education has little to do with income and that income is mainly related to social experience. And education is a decisive cause, both our country and families should pay attention to the development of education, improve the level of education on the one hand, help to improve their own cognitive level, expanding the perspective of understanding the world, on the other hand, also conducive to the improvement of the level of the family, and conducive to the development of the country. Meanwhile, the study of factors influencing the level of income of the population is one of the important issues that economics and sociology have been concerned with for a long time, and this study analyzes the relationship between education and income, which is of great significance in promoting social equity and economic and social development, so this research question has an important sociological significance and contribution.
Hypotheses
Reference 1 Analysis of the relationship between education level and monthly income: A case study of Kitwe County, Zambia.The data were analyzed using independent chi-square tests. (null hypothesis) was tested at the significance level. The results show that there is a significant relationship between education level and monthly income in Zambia.
Reference 2 explores how European GDP reflects income distribution, which is related to educational attainment. The relationship between GDP and personal income, and educational levels such as primary, high school and university is analyzed. As a statistical methodology, detailed tests were carried out on cases from the EU (27 countries), the UK, Germany, the Czech Republic, Slovakia and Poland.
The purpose of Reference 3 was to find the relationship between education level and parents’ income and their participation in the implementation of school education. The sample used for the study was 150 parents randomly sampled using a cluster scale. The data collection techniques used were questionnaires and documents. Data analysis techniques are descriptive statistics, correlation and regression. The results show that there is a significant correlation between parents’ education level and income.
Reference 4 focuses on religion and how it is affected by income and education levels, as well as how people from different social classes view religion today. The study shows clear differences in religious affiliation between low-income and basic educators and those with higher incomes and higher education levels.
Reference 5 uses the Gini coefficient methodology to measure income inequality in Pakistan through data available on the PSLM (Pakistan Social and Living Standards Measurement Survey), HIES (Household Income and Expenditure Survey) and MDG (Pakistan Millennium Development Goals) websites.
Based on the above literature analysis, the hypotheses of this study were formulated.
Null hypothesis H0: There is no significant relationship between education level and monthly income.
Alternative hypothesis H1: There is a significant relationship between education level and monthly income.
Interaction Hypothesis H2: Income may be significantly associated with the interaction term of gender and education.
Context
The country selected for this study is France, which has a representative education system in Europe, and its social welfare system and income distribution help us better understand the relationship between education and income. In addition, income and educational activities in France have a profound impact on society, so this research objective is in line with the general question and also contributes to our in-depth understanding of the socio-economic structure.
This study used data from the European Social Survey (ESS). The time range of data selected for this study is from December 1, 2018 to June 30, 2023. The outcome variable was income, and the predictors were education level and age. The education level variable is recoded as a numerical variable to reflect the difference in educational attainment. Age is also recoded as a numerical variable to reflect different age groups. These variables were selected based on their expected relationship with income and their importance in theoretical and empirical research.
Through the correlation statistical table, the variable information was analyzed to obtain the mean, standard deviation, median and maximum, as well as the missing situation.
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
|---|---|---|---|---|---|---|---|
edulvlb | 16 | 39 | 373.1 | 193.8 | 0.0 | 321.0 | 800.0 |
edulvla | 6 | 61 | 3.0 | 1.4 | 1.0 | 3.0 | 5.0 |
hincfel | 8 | 9 | 2.5 | 2.1 | 1.0 | 2.0 | 9.0 |
age | 726 | 90 | 48.2 | 17.7 | 15.0 | 47.2 | 94.3 |
Findings
According to the test results, the distribution of statistics is approximately normal.
The confidence interval of the test result includes 0. Therefore, the null hypothesis is rejected, the alternative hypothesis is accepted, and it is believed that there are significant differences in income under different education levels.
# A tibble: 1 × 2
lower_ci upper_ci
<dbl> <dbl>
1 -0.0781 0.0767With income as the dependent variable and education level as the independent variable, Model 1 is constructed. With income as the dependent variable and education level and age level as the independent variable, Model 2 was constructed. With income factor as the dependent variable and the interaction term of education level and age level as the independent variable, Model 3 is constructed. The statistical table for the three models is shown below.
| (1) | (2) | (3) | |
|---|---|---|---|
| (Intercept) | −1.1 (0.0)*** | −1.3 (0.1)*** | −1.0 (0.2)*** |
| educ.baBA or more | 1.3 (0.0)*** | 1.1 (0.1)*** | 0.5 (0.3)+ |
| AdulthoodLater | 0.0 (0.1) | −0.3 (0.2) | |
| educ.baBA or more × AdulthoodLater | 0.8 (0.3)** | ||
| Num.Obs. | 15674 | 1896 | 1896 |
| AIC | 18606.3 | 2183.0 | 2178.4 |
| BIC | 18621.6 | 2199.7 | 2200.6 |
| Log.Lik. | −9301.140 | −1088.516 | −1085.202 |
| RMSE | 0.45 | 0.44 | 0.44 |
- We fitted a logistic model (estimated using ML) to predict feelincome with educ.ba (formula: feelincome
- educ.ba). The model’s explanatory power is weak (Tjur’s R2 = 0.07). The model’s intercept, corresponding to educ.ba = No BA, is at -1.08 (95% CI [-1.12, -1.03], p < .001).Within this model:
\[ \log\left[ \frac { \widehat{P( \operatorname{feelincome} )} }{ 1 - \widehat{P( \operatorname{feelincome} )} } \right] = -1.08 + 1.27(\operatorname{educ.ba}_{\operatorname{BA\ or\ more}}) \]
We fitted a logistic model (estimated using ML) to predict feelincome with educ.ba and Adulthood (formula: feelincome ~ educ.ba + Adulthood). The model’s explanatory power is weak (Tjur’s R2 = 0.06). The model’s intercept, corresponding to educ.ba = No BA and Adulthood = Early, is at -1.26 (95% CI [-1.55, -0.98], p < .001). Within this model:
\[ \log\left[ \frac { \widehat{P( \operatorname{feelincome} )} }{ 1 - \widehat{P( \operatorname{feelincome} )} } \right] = -1.26 + 1.14(\operatorname{educ.ba}_{\operatorname{BA\ or\ more}}) + 0.02(\operatorname{Adulthood}_{\operatorname{Later}}) \]
We fitted a logistic model (estimated using ML) to predict feelincome with educ.ba and Adulthood (formula: feelincome ~ educ.ba * Adulthood). The model’s explanatory power is weak (Tjur’s R2 = 0.06). The model’s intercept, corresponding to educ.ba = No BA and Adulthood = Early, is at -0.99 (95% CI [-1.33, -0.66], p < .001). Within this model:
\[ \log\left[ \frac { \widehat{P( \operatorname{feelincome} )} }{ 1 - \widehat{P( \operatorname{feelincome} )} } \right] = -0.99 + 0.52(\operatorname{educ.ba}_{\operatorname{BA\ or\ more}}) - 0.3(\operatorname{Adulthood}_{\operatorname{Later}}) + 0.75(\operatorname{educ.ba}_{\operatorname{BA\ or\ more}} \times \operatorname{Adulthood}_{\operatorname{Later}}) \]
Discussion & Conclusion
The results of the study support the alternative hypothesis H1 that education factors are significantly related to income. The three regression models show that there is an obvious correlation between education level and individual income. This conclusion is consistent with those in the references and further strengthens the relationship between education and income.
Compared to the literature, the findings of this study are consistent with observations in the existing literature, which has highlighted the impact of education level on personal income. Past research has shown that more educated individuals tend to have higher levels of income, possibly because people with more education have easier access to high-paying jobs and are more likely to advance to senior positions.
The results of the study provide further support for the discussion on the relationship between education and income, which has important implications for understanding income distribution issues in the social economy.
In the broader social context, the findings of this study also remind that education is not only a key factor in individual development, but also an important driver of socio-economic development. There are also some limitations in the study, which may be affected by sample selection bias or variable measurement errors. Comparative studies of different countries or regions are also an interesting direction to explore the relationship between education and income in different cultural contexts.
Sources
Banda Gerald & Tailoka Frank Patson.(2018).An Investigation on the Relationship between the Level of Education and Monthly Income: A Case of Kitwe District of Zambia.American Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS)(1),106-117.
Antonyová, Anna,Antony, Peter,Soewito, Benfano,Abdullah, Abd Halid Bin & Nagapan, Sasitharan.(2018).Reflection of Gross Domestic Product into the Income Values According to the Attained Level of Education in Europe.Advanced Science Letters(12),9261-9265(5).
Bambang Budi Wiyono,Ach. Rasyad & Nasrun Nasrun.(2018).The Influence of Education Level and Income of the Parents on Their Participation towards the Implementation of Education at Schools.(eds.).
Alexandra Georgiana PARASCA.(2015).THE INFLUENCE OF INCOME AND EDUCATION LEVEL ON ISSUES OF RELIGION IN ROMANIA.CES Working Papers(1),147-155.
Seema Rehman & Muhammad Zaki Rashidi.(2017).The relationship between education and income inequality (the case of Pakistan).International Journal of Accounting and Economics Studies(1),55-62.
Appendix: External link and Division of labor statement
This research was completed by myself, including the whole research process, literature review, data statistics, model construction, research summary and so on.