Exploring Life Quality Index via Education Level and Population Density

Abstract

The subjective nature of quality of life, makes it complex to measure the quality of life. Among them, finding a few key criteria that affect the quality of life in cities will be the main purpose. In this study, a linear regression model was used to predict the numerical relationship between population density, bachelor's degree rate and education Gini index, and further Akaike information criterion (AIC) and Bayesian information criterion (BIC) were selected to validate and adjust the model, and finally F-test was used to compare the initial model with the adjusted model. In addition, the random forest algorithm was used to classify the quality of life of each city by population density as well as education level to identify the common characteristics of cities with high physical quality of life index. Three classification decision trees created using different combinations of population density, bachelor's degree rate and education Gini index were used, followed by additional multiple decision trees generated by the random forest algorithm. The final results of the receiver operator characteristic curve (ROC) curves and confusion matrix of the two sets of decision trees were observed and evaluated to stratify the cities. The experimental results show that population density has a negative effect on quality of life, while bachelor's degree rate has a positive effect. Although the three indicators of population density, bachelor's degree rate and education Gini index cannot effectively distinguish the four levels, they can effectively distinguish which cities are not the first level. it shows that cities that achieve high education level and low population density are not necessarily the cities with the highest quality of life, but those that do not are definitely not.