CD Skripsi
Analisis Multidimensional Scaling Dan Cluster Fuzzy C-Means Pada Data Indikator Kesejahteraan Rakyat Di Indonesia
ABSTRACT
The Covid-19 pandemic has disrupted various sectors of people's lives which have an impact on the level of people's welfare in an area. The value of PDRB, per capita expenditure, percentage of the poor, participation rate, and average schooling are some of the variables that can provide an overview of the welfare of the people in an area. Mapping and clustering can be done to determine the level of welfare of the people in Indonesia due to the Covid-19 pandemic. In this study, using the Central Bureau of Statistics data, namely indicators of the welfare of the people of provinces and regencies/cities in Indonesia. The mapping analysis was carried out using multidimensional scaling resulting in 2 groups of provinces with group 1 consisting of 30 provinces and group 2 consisting of 4 provinces and 2 groups of regencies/cities with group 1 consisting of 494 regencies/cities and group 2 consisting of 20 regencies/cities. Multidimensional scaling validation values in the form of STRES values obtained in provinces and regencies/city data are close to 0 and R square equal to 1 which means the results are very good. The grouping was carried out using fuzzy C-Means which resulted in 2 provinces clusters with cluster 1 consisting of 30 provinces and cluster 2 consisting of 4 provinces and 2 clusters of regencies/cities with cluster 1 consisting of 495 regencies/cities and cluster 2 consisting of 19 regencies/cities. Based on the comparison of each variable obtained by cluster 2, cluster 2 is more prosperous than cluster 1. Cluster validation values in the form of MPC and FSI obtained are close to 1 so that the cluster results obtained are very good.
Keywords: Welfare indicators, multidimensional scaling, fuzzy C-Means, validation of clusters.
Tidak tersedia versi lain