Articles
<![CDATA[Empirical Bayesian Method for the Estimation of Literacy Rate at Sub-district Level Case Study: Sumenep District of East Java Province ]]>
<![CDATA[A.Tuti Rumiati]]>;
<![CDATA[Khairil Anwar Notodiputro]]>;
<![CDATA[Kusman Sadik]]>;
<![CDATA[I Wayan Mangku]]>
<![CDATA[ IPTEK The Journal for Technology and Science Vol 23, No 1 (2012) ]]>
Publisher : <![CDATA[IPTEK, LPPM, Institut Teknologi Sepuluh Nopember ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.12962/j20882033.v23i1.13
<![CDATA[This paper discusses Bayesian Method of Small Area Estimation (SAE) based on Binomial response variable. SAE method being developed to estimate parameter in small area due to insufficiency of sample. The case study is literacy rate estimation at sub-district level in Sumenep district, East Java Province. Literacy rate is measured by proportion of people who are able to read and write, from the population of 10 year-old or more. In the case study we used Social Economic Survey (Susenas)data collected by BPS. The SAE approach was applied since the Susenas data is not representative enough to estimate the parameters at sub-district level because it’s designed to estimate parameters in regional area (in scope of a district/city at minimum). In this research, the response variable being used was logit function trasformation of pi (the parameter of Binomial distribution). We applied direct and indirect approach for parameter estimation, both using Empirical Bayes approach. For direct estimation we used prior distribution of Beta distribution and Normal prior distribution for logit function (pi) and to estimate parameter by using numerical method, i.e integration Monte Carlo. For indirect approach, we used auxiliary variables which are combinations of sex and age (which is divided into five categories). Penalized Quasi Likelihood (PQL) was used to get parameter estimation of SAE model and Restricted Maximum Likelihood method (REML) for MSE estimation. Instead of Bayesian approach, we are also conducting direct estimation using classical approach in order to evaluate the quality of the estimators. This research gives some findings, those are: Bayesian approach for SAE model gives the best estimation because having the lowest MSE value compares to the other methods. For the direct estimation, Bayesian approach using Beta and logit Normal prior distribution give a very similar result to the direct estimation with classical approach since the weight of is too large, which is about 0.905. It is also found that direct estimation using Bayesian approach with the Beta prior distribution gives better MSE than using logit normal prior distribution.]]>
<![CDATA[Parameter Quantile-like dalam Pendugaan Area Kecil Melalui Pendekatan Penalized- Splines ]]>
<![CDATA[Kusman Sadik]]>
<![CDATA[ STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 8, No 1 (2008) ]]>
Publisher : <![CDATA[Program Studi Statistika Unisba ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.29313/jstat.v8i1.972
<![CDATA[Pada beberapa tahun terakhir ini, para statistisi mulai mengembangkan metodologi yang berkaitandengan pendugaan untuk daerah atau domain survei yang memiliki sampel kecil atau bahkan tidakmemiliki sampel satupun. Data yang diperoleh melalui teknik survei yang tepat akan sangat efektifdan memiliki sifat reliabilitas untuk menduga total atau rataan peubah tertentu. Sifat penduga yangdemikian dapat dicapai apabila data sampel dari survei mencakup daerah atau domain yang besar.Misalnya, beberapa survei ekonomi yang dilakukan di Indonesia berskala nasional. Pada survei yangdemikian banyaknya sampel rumah tangga untuk tiap kecamatan dalam suatu kabupaten sangatkecil (small area). Bahkan bisa terjadi suatu kecamatan tertentu tidak terpilih sebagai daerah surveisehingga sampel rumah tangga dari kecamatan tersebut tidak ada. Persoalannya adalah bagaimanamenduga parameter, misalnya tingkat kemiskinan di level kecamatan tersebut sementara sampelnyasangat kecil. Salah satu metode yang banyak dikembangkan untuk pendugaan area kecil (small areaestimation / SAE) adalah model yang berbasis pada generalized linear mixed model (GLMM).Beberapa pendekatan lain saat ini mulai didiskusikan oleh para statistisi di dunia. Salah satumetode alternatif tersebut adalah pemodelan yang didasarkan pada kuantil yang dikenal dengan MquantileP-splines. Aspek penting dari metode ini adalah adanya sifat tegar (robust) terhadappencilan (outliers) dan bebas sebaran (distribution free).]]>
<![CDATA[Pendugaan Angka Kematian Bayi dengan Menggunakan Model Poisson Bayes Berhirarki Dua-Level ]]>
<![CDATA[Nusar Hajarisman]]>;
<![CDATA[Khairi A N]]>;
<![CDATA[Kusman Sadik]]>
<![CDATA[ MIMBAR (Jurnal Sosial dan Pembangunan) Volume 29, No. 1, Year 2013 (Accredited by Dikti) ]]>
Publisher : <![CDATA[Universitas Islam Bandung ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (117.48 KB)
|
DOI: 10.29313/mimbar.v29i1.366
<![CDATA[Official institutions of national data providers such as the BPS-Statistics Indonesia is required to produce and present the statistical information, as necessary as a form of contributory BPS region in support of regional development policy and planning. There are survey conducted by BPS capability estimation techniques are still limited, due to the resulting estimators have not been able to directly assumed for small areas. In this article we propose the hierarchical Bayesian models, especially for count data which are Poisson distributed, in small area estimation problem. The model was developed by combining concept of generalized linear model and Fay-Herriot model. The results of the development of this model is implemented to estimate the infant mortality rate in Bojonegoro district, East Java Province.]]>
<![CDATA[PEMODELAN DATA TERSENSOR KANAN MENGGUNAKAN ZERO INFLATED NEGATIVE BINOMIAL DAN HURDLE NEGATIVE BINOMIAL ]]>
<![CDATA[Kusni Rohani Rumahorbo]]>;
<![CDATA[Budi Susetyo]]>;
<![CDATA[Kusman Sadik]]>
<![CDATA[ Indonesian Journal of Statistics and Applications Vol 3 No 2 (2019) ]]>
Publisher : <![CDATA[Departemen Statistika, IPB University dengan Forum Perguruan Tinggi Statistika (FORSTAT) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.29244/ijsa.v3i2.247
<![CDATA[Health is a very important thing for humanity. One way to look at a person's health condition is through the number of unhealthy days which can also shows the productivity of the community in a region. Modeling the number of unhealthy days which are examples of count data can be done using Poisson regression. Problems that are often faced in data counts are overdispersion and excess zero. Poisson regression cannot be applied to data that experiences both of these. Zero Inflated Negative Binomial and Hurdle Negative Binomial modeling was performed on data with 2 conditions, uncensored and censored. The explanatory variables used are gender, age, marital status, education level, home ownership status and rural-urban status. According to the results of the AIC and RMSE calculation, Zero Inflated Negative Binomial on censored data showed the best performance for estimating the number of unhealthy days.]]>
<![CDATA[KAJIAN REGRESI KEKAR MENGGUNAKAN METODE PENDUGA-MM DAN KUADRAT MEDIAN TERKECIL ]]>
<![CDATA[Khusnul Khotimah]]>;
<![CDATA[Kusman Sadik]]>;
<![CDATA[Akbar Rizki]]>
<![CDATA[ Indonesian Journal of Statistics and Applications Vol 4 No 1 (2020) ]]>
Publisher : <![CDATA[Departemen Statistika, IPB University dengan Forum Perguruan Tinggi Statistika (FORSTAT) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (361.525 KB)
|
DOI: 10.29244/ijsa.v4i1.502
<![CDATA[Regression is a statistical method that is used to obtain a pattern of relations between two or more variables presented in the regression line equation. This line equation is derived from estimation using ordinary least squares (OLS). However, OLS has limitations that are highly dependent on outliers data. One solution to the outliers problem in regression analysis is to use the robust regression method. This study used the least median squares (LMS) and multi-stage method (MM) robust regression for analysis of data containing outliers. Data analysis was carried out on generation data simulation and actual data. The simulation results of regression analysis in various scenarios are concluded that the LMS and MM methods have better performance compared to the OLS on data containing outliers. MM method has the lowest average parameter estimation bias, followed by the LMS, then OLS. The LMS has the smallest average root mean squares error (RMSE) and the highest average R2 is followed by the MM then the OLS. The results of the regression analysis comparison of the three methods on Indonesian rice production data in 2017 which contains 10% outliers were concluded that the LMS is the best method. The LMS produces the smallest RMSE of 4.44 and the highest R2 that is 98%. MM's method is in the second-best position with RMSE of 6.78 and R2 of 96%. OLS method produces the largest RMSE and lowest R2 that is 23.15 and 58% respectively.]]>
<![CDATA[Simulation Study of Robust Geographically Weighted Empirical Best Linear Unbiased Predictor on Small Area Estimation: Simulasi Metode Prediksi Tak Bias Linier Terbaik Empiris Terboboti Geografis Kekar pada Pendugaan Area Kecil ]]>
<![CDATA[Naima Rakhsyanda]]>;
<![CDATA[Kusman Sadik]]>;
<![CDATA[Indahwati Indahwati]]>
<![CDATA[ Indonesian Journal of Statistics and Applications Vol 5 No 1 (2021) ]]>
Publisher : <![CDATA[Departemen Statistika, IPB University dengan Forum Perguruan Tinggi Statistika (FORSTAT) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.29244/ijsa.v5i1p50-60
<![CDATA[Small area estimation can be used to predict the population parameter with small sample sizes. For some cases, the population units that are close spatially may be more related than units that are further apart. The use of spatial information like geographic coordinates are studied in this research. Outlier contaminations can affect small area estimations. This study was conducted using simulation methods on generated data with six scenarios. The scenarios are the combination of spatial effects (spatial stationary and spatial non-stationary) with outlier contamination (no outlier, symmetric outliers, and non-symmetric outliers). The purpose of this study was to compare the geographically weighted empirical best linear unbiased predictor (GWEBLUP) and robust GWEBLUP (RGWEBLUP) with direct estimator, EBLUP, and REBLUP using simulation data. The performance of the predictors is evaluated using relative root mean squared error (RRMSE). The simulation results showed that geographically weighted predictors have the smallest RRMSE values for scenarios with spatial non-stationary, therefore offer a better prediction. For scenarios with outliers, robust predictors with smaller RRMSE values offer more efficiency than non-robust predictors.]]>
<![CDATA[Generalized Multilevel Linear Model dengan Pendekatan Bayesian untuk Pemodelan Data Pengeluaran Perkapita Rumah Tangga ]]>
<![CDATA[Azka Ubaidillah]]>;
<![CDATA[Anang Kurnia]]>;
<![CDATA[Kusman Sadik]]>
<![CDATA[ Jurnal Aplikasi Statistika & Komputasi Statistik Vol 9 No 1 (2017): Journal of Statistical Application and Computational Statistics ]]>
Publisher : <![CDATA[Pusat Penelitian dan Pengabdian Masyarakat Politeknik Statistika STIS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (704.924 KB)
|
DOI: 10.34123/jurnalasks.v9i1.91
<![CDATA[Household per capita expenditure data is one of the important information as an approach to measure the level of prosperity in an area. Such data is needed by the government, both at the central and regional levels in formulating, implementing and evaluating the implementation of development programs. This research is aimed at modeling the household per capita expenditure data which takes into account the specificity of BPS data which has a hierarchical structure, and data distribution pattern which has the right skewed characteristic. The modeling is done by using the three parameters of Log-normal distribution (LN3P) and the three parameters of Log-logistics (LL3P) with a single level (unilevel) and two levels (multilevel) structure. The parameter estimation process is done by Markov Chain Monte Carlo (MCMC) method and Gibbs Sampling algorithm. The results showed that on the unilevel model, the LL3P model is better than the LN3P model. While in multilevel model, LN3P model is better than LL3P model. The results also show that the best model for modeling household per capita expenditure data is the LN3P multilevel model with the smallest Deviance Information Criterion (DIC) value.]]>
<![CDATA[PENANGANAN OVERDISPERSI PADA PEMODELAN DATA CACAH DENGAN RESPON NOL BERLEBIH (ZERO-INFLATED) ]]>
<![CDATA[Viarti Eminita]]>;
<![CDATA[Anang Kurnia]]>;
<![CDATA[Kusman Sadik]]>
<![CDATA[ FIBONACCI: Jurnal Pendidikan Matematika dan Matematika Vol 5, No 1 (2019): FIBONACCI: Jurnal Pendidikan Matematika dan Matematika ]]>
Publisher : <![CDATA[Fakultas Ilmu Pendidikan Universitas Muhammadiyah Jakarta ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1688.07 KB)
|
DOI: 10.24853/fbc.5.1.71-80
<![CDATA[Overdispersi pada data cacah yang disebabkan karena kasus nol berlebih tidak dapat ditangani dengan metode model linier umum biasa seperti Poisson dan Binomial Negatif. Penanganan overdispersi karena nol berlebih dapat dilakukan dengan menggunakan model Zero-Inflated. Zero-Inflated Poisson (ZIP) dan Zero-Inflated Binomial Negatif (ZIBN) telah diyakini performanya dalam menangani masalah ini. Selain menangani masalah tersebut kedua model ini juga dapat memberikan informasi mengenai penyebab nol berlebih pada data respon. Performa ke Empat model tersebut dibandingkan dalam menduga model dari jumlah anak yang tidak sekolah dalam keluarga di Provinsi Jawa Barat pada tahun 2017. Berdasarkan nilai dari ukuran Pearson Chi-Squares, Likelihood Ratio Chi-Square, dan Akaike Information Crieteria (AIC). Pearson Chi-Squares, model ZIP lebih baik dibandingkan ZIBN dan model lainnya, walaupun berbeda sedikit dengan ZIBN.]]>
<![CDATA[BISAKAH MEMPEROLEH STATISTIK INDEKS HARGA KONSUMEN TINGKAT PROVINSI DI INDONESIA DENGAN KETELITIAN YANG LEBIH BAIK? ]]>
<![CDATA[Andi Okta Fengki]]>;
<![CDATA[Khairil Anwar Notodiputro]]>;
<![CDATA[Kusman Sadik]]>
<![CDATA[ Seminar Nasional Official Statistics Vol 2019 No 1 (2019): Seminar Nasional Official Statistics 2019 ]]>
Publisher : <![CDATA[Politeknik Statistika STIS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (660.165 KB)
|
DOI: 10.34123/semnasoffstat.v2019i1.178
<![CDATA[Statistik indeks harga konsumen (IHK) atau consumer price index (CPI) juga dibutuhkan pada tingkat provinsi di era desentralisasi saat ini. Ketika IHK ingin diduga pada tingkat provinsi, permasalahan ukuran contoh kecil (small area) muncul karena survei untuk menghasilkan IHK ini di Indonesia dirancang untuk tingkat nasional. Akan tetapi, informasi dari statistik IHK 82 kota dapat membantu untuk menduga IHK provinsi. Metode pendugaan area kecil atau small area estimation (SAE) dapat diterapkan sebagai solusi untuk meningkatkan ketelitian hasil pendugaan langsung. Pada penelitian ini IHK provinsi diduga menggunakan model Fay-Herriot (FH). Hasilnya menunjukan bahwa model FH dapat menghasilkan statistik IHK provinsi dengan ketelitian yang lebih baik dari pendugaan langsung. Hal ini ditunjukan dengan nilai average relative root mean square error (ARRMSE) penduga FH IHK provinsi yang lebih kecil dari penduga langsungnya.]]>
<![CDATA[Pengelompokan dan Peramalan Deret Waktu pada Produksi Bawang Merah Tingkat Provinsi di Indonesia ]]>
<![CDATA[Rifqi Aulya Rahman]]>;
<![CDATA[Farit Mochamad Afendi]]>;
<![CDATA[Widhiyanti Nugraheni]]>;
<![CDATA[Kusman Sadik]]>;
<![CDATA[Akbar Rizki]]>
<![CDATA[ Seminar Nasional Official Statistics Vol 2021 No 1 (2021): Seminar Nasional Official Statistics 2021 ]]>
Publisher : <![CDATA[Politeknik Statistika STIS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (697.411 KB)
|
DOI: 10.34123/semnasoffstat.v2021i1.910
<![CDATA[Shallots are strategic vegetable commodity state that can affect the national economy. Shallots production increases every year that in line with domestic household consumption. Every province in Indonesia has a different level of shallot production, both in terms of cycles and harvest amount. Clustering provinces with similar production patterns can help government policies. This research aims to determine cluster time series and to evaluate the shallot production forecast in several provinces in Indonesia. There are three of optimal clusters which have a characteristic pattern in time series and their production. Time series at provincial level and cluster level, then it is modelled based on Autoregressive Integrated Moving Average (ARIMA) and Seasonal ARIMA (SARIMA). The evaluation of cluster level is compared to the provincial level and is concluded that clustering makes forecasting efficiently. This is based on average of Mean Absolute Percentage Error (MAPE) that is smaller that provincial level.]]>
