Mathematics

Permanent URI for this collection

https://repository.unri.ac.id/handle/123456789/94

Browse

Browsing Mathematics by Subject "Akaike Information Criterion (AIC)"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    ANALISIS SPASIAL TINGKAT KESEJAHTERAAN DI INDONESIA MENGGUNAKAN GEOGRAPHICALLY WEIGHTED LOGISTIC REGRESSION
    (Elfitra, 2022-02) Reskia, Amanda; Harison, Harison
    Geographically Weighted Logistic Regression (GWLR) is a method of combining Geographically Weighted Regression (GWR) with logistic regression which is applied to spatial data. The purpose of this research to determine model on community welfare using GWLR and find factors that influence the possibility of increasing the welfare status of each Province in Indonesia 2019. The variables used are total manpower, rate of GRDP, PMWand LFPR. In the response variable, the level of welfare as measured by the human development index (HDI) is in the binary category, namely 0 and 1 following the Bernoulli distribution. The results showed that the GWLR model with the Adaptive Gaussian Kernel function was better than the logistic regression model with the smallest Akaike Information Criterion (AIC) of 37.97.
  • No Thumbnail Available
    Item
    ANALISIS SPASIAL TINGKAT KESEJAHTERAAN DI INDONESIA MENGGUNAKAN GEOGRAPHICALLY WEIGHTED LOGISTIC REGRESSION
    (Elfitra, 2022-03) Reskia, Amanda; Harison, Harison
    Geographically Weighted Logistic Regression (GWLR) is a method of combining Geographically Weighted Regression (GWR) with logistic regression which is applied to spatial data. The purpose of this research to determine model on community welfare using GWLR and find factors that influence the possibility of increasing the welfare status of each Province in Indonesia 2019. The variables used are total manpower, rate of GRDP, PMWand LFPR. In the response variable, the level of welfare as measured by the human development index (HDI) is in the binary category, namely 0 and 1 following the Bernoulli distribution. The results showed that the GWLR model with the Adaptive Gaussian Kernel function was better than the logistic regression model with the smallest Akaike Information Criterion (AIC) of 37.97.