Kajian Penentuan Klasifikasi Desa di Indonesia

Abstract

Classification of “kelurahan” and rural area into urban/rural class basically meant to form a layer (stratum) were used in the survey sampling techniques. With the status of urban and rural areas, the sample can represent the entire population correctly. Proper selection of variables could distinguish village into urban and rural class. Logistik regression is one of regressions method where the response variable is categorical data. Binary logistik regression was used when the response variable consists of two categories. This method can also be used for data classification. Bootstrap, is known as one of the data simulation method, intended to simplify the inferential statistikal analysis but produces a more robust analysis. The purpose of this study was to do some studies in selection of the most influential variables in determining the classification of villages in Indonesia with a mix method of bootstrap and binary logistik regression. The data used in this case is data Potensi Desa (PODES) 2011 which conducted by Badan Pusat Statistik with consist of 15 predictor variable. The results showed that reduction of eleven variables (X1-X11) in determining the classification of villages in Indonesia into five variables able to produce models that are just as good as previous model. The model with the addition of four new predictor variables were able to raise the level of accuracy of the classification. The use of bootstrap method in variables selection was proved better than variables selection that only see partial test results alone.