IJCSN - International Journal of Computer Science and Network, Volume 6, Issue 6, December 2017 ISSN (Online) : 2277-5420 www.IJCSN.org Impact Factor: 1.5 760 Copyright (c) 2017 International Journal of Computer Science and Network. All Rights Reserved. Small Area Estimation in Estimating Unemployment Rate in Bogor District of Sampled and Non - Sampled Areas Using A Calibration Modeling Approach 1 Siti Aprizkiyandari; 2 Anang Kurnia; 3 Indahwati 1 Departement of Statistics, Agricultural University Bogor, Indonesia 2 Departement of Statistics, Agricultural University Bogor, Indonesia 3 Departement of Statistics, Agricultural University Bogor, Indonesia Abstract – The main problem in Indonesia is unemployment. There are some various government policies to resolve unemployment, such as the availability of statistical data in unemployment. The National Labor Survey conducted by the Statistics Indonesia (BPS) only generates estimates at the national levels, whereas to carry out various government policies requires the availability of unemployment information to smaller levels. The Small Area Estimation (SAE) method is one of the solutions to estimate small area without adds sampling units. The method is borrowing strength from nearby observation sample areas. The study focused on estimating unemployment rate in Bogor sub-district level using Generalized Linear Mixed Models (GLMM) method with calibration approach. The results of the proposed method can produce the same result as published by BPS and are able to generate the result to sub-district level.. Keywords – Generalized Linear Mixed Models (GLMM), Calibration modeling approach, Clustering analysis. 1. Introduction he unemployment issue is a very important issue to be resolved by the government because one of the milestones in the process of the movement of the economy. the Country that tends to be forward will have a lot of unemployment. A wide range of Government policy ever done in tackling unemployment one of them that is available related statistics of unemployment. Statistics Indonesia (BPS) only presents data for the unemployment level area is higher e.g. national, provinces or districts, so as to lower level areas such as sub-district or village than any sample unit number small. If a direct prediction is used then it will produce a low precision. Therefore, one solution to overcome these problems is prediction method for a small area (Small Area Estimation). According to [6] defines the small area estimation as estimating an area of relatively small sample size by utilizing information from outside the area, information from within the area itself and from outside the survey. The response module will be associated with fixed-match variables and the small, random-area specific diversity. Through the estimation of small areas, the available samples will be strengthened in their role to be effective. The increase in effectiveness will increase the precision in the estimation because the default error will be small. Research on unemployment of small area estimation method has been done by many previous researchers. Study on applying of empirical best linear unbiased prediction method to small area estimation in estimating of the unemployment rate in Bogor city, the result showed by using EBLUP method generates smaller RRMSE when compared with direct estimation method by Harsanti [4]. While a study of a small area estimation method for estimating unemployment using the Bayes approach with education level, this results obtained suggest that indirect estimation is better than direct estimates by Hanike [3]. The unemployment rate at Bogor district had been increased in different ways. In 2011 until 2013 the unemployment rate in Bogor regency decreased from 10.73% to 7.87, but in 2015 the unemployment rate in Bogor District experienced a significant change that is increased to 10.01%. Therefore, the researchers are interested to observe the unemployment rate incident that occurred in Bogor regency. The difference of this study T