PENGGUNAAN REGRESI LOGISTIK BINER DAN ITERATIVE DICHOTOMISER 3 (ID3) DALAM PEMBUATAN KLASIFIKASI STATUS KERJA (Studi Kasus Penduduk Kota Surakarta Tahun 2015)

Lugas Putranti Winastiti, Agus Rusgiyono, Diah Safitri

Abstract


Discussing about the macro economy usually discuss about unemployment. Unemployment basically can not be fully eliminated. Unemployment usually symbolized with an employment status of person. In this research, two methods were used in making the classification of employment status in the population of the city of Surakarta in February 2015, the methods are binary logistic regression and Iterative Dichotomiser 3 (ID3) Algorithm. Predictor variables used in determining employment status were age, gender, status in the household, marital status, education and work training. Comparison of the training data and testing data is 60:40. Based on calculations obtained binary logistic regression variables that significantly affect the employment status are age, gender and marital status and the accuracy using testing data is 75%, while the calculations of a decision tree using iterative dichotomiser 3 algorithm the accuracy using testing data is  75%.

 

Keywords: Classification, Iterative Dichotomiser 3 Algorithm, Binary Logistic Regression


Full Text:

PDF

Refbacks

  • There are currently no refbacks.



Creative Commons License
Jurnal Gaussian by Departemen Statistika Undip is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Flag Counter