cover
Filter by Year

Analysis
Indonesian Journal of Statistics and Its Applications
Indonesian Journal of Statistics and Its Applications (eISSN:2599-0802): diterbitkan berkala 2 (dua) kali dalam setahun yang memuat tulisan ilmiah yang berhubungan dengan bidang statistika dan aplikasinya. Artikel yang dimuat berupa hasil penelitian bidang statistika dan aplikasinya dengan topik (tapi tidak terbatas): rancangan dan analisis percobaan, metodologi survey dan analisis, riset operasi, data mining, pemodelan statistika, komputasi statistika, time series dan ekonometrika, serta pendidikan statistika.
Articles
10
Articles
POISSON REGRESSION OF DAMAGE PRODUCT SALES USING MCMC

Marliana, Reny Rian, Padmadisastra, Septiadi

Indonesian Journal of Statistics and Applications Vol 2 No 1 (2018)
Publisher : Departemen Statistika, IPB dengan Forum Perguruan Tinggi Statistika (FORSTAT)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (1038.238 KB)

Abstract

In this paper a model for the number of “damage” product sales is studied. The product sales are run into underreporting counts, caused by a delay on input process of the system called sales cycle. The goal of the study is to estimate the parameters of the regression model of product sales on an explanatory variable. It is the actual number of product sales. The model used is a mixture of the Poisson and the Binomial distributions. The parameters of the regression model are estimated by a Bayesian approach and Markov Chain Monte Carlo simulation using Gibbs sampling algorithm. The results of estimation clearly showed a gap between undamage product sales and the actual number. The gap is the number of damaged product sales.

ALTERNATIF PENGGEROMBOLAN DATA DERET WAKTU DENGAN KONDISI TERDAPAT DATA KOSONG

Yanti, Yusma, Rahardiantoro, Septian

Indonesian Journal of Statistics and Applications Vol 2 No 1 (2018)
Publisher : Departemen Statistika, IPB dengan Forum Perguruan Tinggi Statistika (FORSTAT)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (600.849 KB)

Abstract

Panel data describes a condition in which there are many observations with each observation observed periodically over a period of time. The observation clustering context based on this data is known as Clustering of Time Series Data. Many methods are developed based on fluctuating time series data conditions. However, missing data causes problems in this analysis. Missing data is the unavailability of data value on an observation because there is no information related to it. This study attempts to provide an alternative method of clustering observations on data with time series containing missing data by utilizing correlation matrices converted into Euclid distance matrices which are subsequently applied by the hierarchical clustering method. The simulation process was done to see the goodness of alternative method with common method used in data with 0%, 10%, 20% and 40% missing data condition. The result was obtained that the accuracy of the observation bundling on the proposed alternative method is always better than the commonly used method. Furthermore, the implementation was done on the annual gini ratio data of each province in Indonesia in 2007 to 2017 which contained missing data in North Kalimantan Province. There were 2 clusters of province with different characteristics.

FAKTOR-FAKTOR YANG MEMENGARUHI UNMET NEED KB DI PROVINSI BENGKULU TAHUN 2015 DENGAN PEMODELAN REGRESI LOGISTIK BINER

Rai, Abyan, Ramadhan, Reza Rizky

Indonesian Journal of Statistics and Applications Vol 2 No 1 (2018)
Publisher : Departemen Statistika, IPB dengan Forum Perguruan Tinggi Statistika (FORSTAT)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (488.424 KB)

Abstract

Indonesia failed to reach the target to reduce the percentage of unmet need KB in 2015.  Province of Bengkulu which has almost 20% of family planning services from government, has a high unmet need percentage. The purpose of this research is to determine the factors that affect status of unmet need KB of women aged 15-49 years in Bengkulu 2015. Data in this study obtained from Susenas 2015. The result showed that 21,34% of women aged 15-49 years in Bengkulu in 2015 was unmet need KB and 78,65% was not unmet need KB. Using binary logistic regression, the result showed that the age of women, number of surviving children, education of women aged 15-49 years, and type of residence have a significant effect on status of unmet need KB. Socialization of family planning program on Bengkulu is needed to reduce the percentage of unmet need KB of women aged 15-49 years on Bengkulu. Further research is suggested to use other independent variables and see spatial correlation in Province of Bengkulu.

REGRESI POISSON BIVARIAT DENGAN KOVARIAN MERUPAKAN FUNGSI DARI VARIABEL BEBAS

Kurniawan, Untung

Indonesian Journal of Statistics and Applications Vol 2 No 1 (2018)
Publisher : Departemen Statistika, IPB dengan Forum Perguruan Tinggi Statistika (FORSTAT)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (560.385 KB)

Abstract

Poisson regression is a regression model which often used to analyze the count data. In this study, poisson regression has been used bivariate poisson regression where the regression is a method which is used to model a pair of correlated count data with multiple predictor variables. The model is used covariance which has a function of the independent variable. The purposes of this study is obtain parameter estimates, test statistics of bivariate poisson regression, and determine the factors that influence of infant mortality and maternal mortality. The data is used from the infant mortality and maternal mortality in Central Java 2015. Based on the result, the parameter estimation of poisson bivariate regression model using maximum likelihood (MLE) method. The results obtained from the parameter estimation are not close form so it needs to be done by Newton-Raphson iteration method. In testing the hypothesis using the Maximum Likelihood Ratio Test method (MLRT) by comparing the value between likelihood below H0 and likelihood below population. Partial of parameters model λ1 (infant mortality) there are six independent variables that have significant influence, namely, delivery by health personnel (X1), pregnant women carry out the program K4 (X3), pregnant women who get Fe3 tablet (X4), handling obstetric complication (X5), exclusively breastfed infants (X7), and households living a clean and healthy life (X8). While for model λ2 (maternal death) only variable handling of neonatal complication (X6) which have no significant influence to response variable.

KAJIAN SIMULASI PENDUGAAN SELANG KEPERCAYAAN BOOTSTRAP BAGI ARAH MEDIAN DATA SIRKULAR

Suhaeni, Cici, Sumertajaya, I Made, Djuraidah, Anik

Indonesian Journal of Statistics and Applications Vol 2 No 1 (2018)
Publisher : Departemen Statistika, IPB dengan Forum Perguruan Tinggi Statistika (FORSTAT)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (530.222 KB)

Abstract

The median direction is one of central tendency of circular data. The estimation process usually requires information about sampling distribution of statistic that want to be used as a parameter estimate. Theoretically, sampling distribution derived from population distribution. But, it is not easy to get sampling distribution of median although the population distribution is known.  When the sampling distribution cannot be derived easily from population distribution, the bootstrap method can be an alternative to handle it. This study wants to evaluate the effect of increasing concentration parameter to the performance of bootstrap confidence interval estimation for median direction through simulation study. Three methods were used to estimate the interval  which are equal-tailed arc (ETA), symmetric arc (SYMA), and likelihood-based arc (LBA). The most important criterion to evaluate them were true coverage and interval width. The simulation results that in general, the increasing of concentration parameter followed by  more narrow interval. For small concentration parameter (k<1), all methods give unstable true coverage and interval width. The authors also identify that those three methods produce intervals with identical width when the parameter concentration is 20 or more. In terms of coverage and interval width, the best method was ETA.

PENERAPAN ANALISIS REGRESI SPLINE UNTUK MENDUGA HARGA CABAI DI JAKARTA

Wulandari, Hestiani, Kurnia, Anang, Sumantri, Bambang, Kusumaningrum, Dian, Waryanto, Budi

Indonesian Journal of Statistics and Applications Vol 1 No 1 (2017)
Publisher : Departemen Statistika, IPB dengan Forum Perguruan Tinggi Statistika (FORSTAT)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (229.572 KB)

Abstract

The chili is an important commodity in Indonesia, which has a fairly large price fluctuations. Fluctuations in prices often raises the risk of loss even have contributed to inflation. Chili price data is time series data that is not independent between observations (autocorrelation) and do not spread to normal. In addition, chili price data does not have the diversity of homogeneous data. One method that can be used to predict the pattern of the data is spline regression. The data used in this study is data the average weekly price of chili in Jakarta from January, 2010 to October, 2015. The best spline model is a second order spline models with three knots. The model has a value of Mean Absolute Percentage Error (MAPE) of 9.57% and determination coefficient of 86.41%. The model obtained in this research is already well in predicting the pattern of the chili price, but it was only able to predict well for a period of one month. Prediction chili prices in Jakarta for November are in the range of Rp 35.565. Keywords: chili price, regression, spline.

AN APPLICATION OF GENETIC ALGORITHM FOR CLUSTERING OBSERVATIONS WITH INCOMPLETE DATA

Ananda, Frisca Rizki, Saefuddin, Asep, Sartono, Bagus

Indonesian Journal of Statistics and Applications Vol 1 No 1 (2017)
Publisher : Departemen Statistika, IPB dengan Forum Perguruan Tinggi Statistika (FORSTAT)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (255.206 KB)

Abstract

Cluster analysis is a method to classify observations into several clusters. A common strategy for clustering the observations uses distance as a similarity index. However distance approach cannot be applied when data is not complete. Genetic Algorithm is applied by involving variance (GACV) in order to solve this problem. This study employed GACV on Iris data that was introduced by Sir Ronald Fisher. Clustering the incomplete data was implemented on data which was produced by deleting some values of Iris data. The algorithm was developed under R 3.0.2 software and got satisfying result for clustering complete data with 95.99% sensitivity and 98% consistency. GACV could be applied to cluster observations with missing value without filling in the missing value or excluding these observations. Performance on clustering incomplete observations is also satisfying but tends to decrease as the proportion of incomplete values increases. The proportion of incomplete values should be less than or equal to 40% to get sensitivity and consistency not less than 90. Keywords: Cluster Analysis, Genetic Algorithm, Incomplete Data.

EVALUASI KEPUASAN PENGGUNA JASA LABORATORIUM KIMIA PT KRAKATAU STEEL (PERSERO) TBK TAHUN 2012-2013

Zaikarina, Hilda, Erfiani, ., Sumertajaya, I Made

Indonesian Journal of Statistics and Applications Vol 1 No 1 (2017)
Publisher : Departemen Statistika, IPB dengan Forum Perguruan Tinggi Statistika (FORSTAT)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (524.185 KB)

Abstract

One of the services contained in PT Krakatau Steel (Persero) Tbk is the chemical composition analysis services in the chemistry lab. Management system that will create a well-managed laboratoryperformance is optimal. Manage standard chemistry laboratory is SNI ISO/IEC 17025. Discussed in this standard laboratory management such as through customer feedback. Laboratory customers selected through stratified random sampling with customer categories as strata, like suppliers, derived from plant and internal processes are not routine. In the research lab result that the customer will be satisfied, including services rendered for Customer Satisfaction Index (CSI) is greater than 70% with the overall characteristics of the respondents subscription in the laboratory was 11.6 years. Overall the indicators included in the priority importance performance analysis (IPA) and has a value kesenjangan beyond the maximum tolerance through kesenjangan analysis approach is the completeness of laboratory equipment (F) and speed of service (K). Keywords : customer satisfaction index (CSI), gap analysis, importance performance analysis (IPA)

IDENTIFIKASI KARAKTERISTIK ANAK PUTUS SEKOLAH DI JAWA BARAT DENGAN REGRESI LOGISTIK

Perhati, Tina Aris, Indahwati, ., Susetyo, Budi

Indonesian Journal of Statistics and Applications Vol 1 No 1 (2017)
Publisher : Departemen Statistika, IPB dengan Forum Perguruan Tinggi Statistika (FORSTAT)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (275.94 KB)

Abstract

School dropouts are the problem in education which is the condition of children who do not have the opportunity to complete their education that they couldnt obtain degree certificate due to certain factors. Based on SUSENAS 2013, there is 2.15% of children aged 7-15 years old in West Java who dropped out of school. Three aspects that have great potential on the incidence of school dropouts are characteristic of social, economy, and demography. This study uses logistic regression analysis to determine the effect of school dropouts by the three aspects. The results of logistic regression analysis at 5% significance level indicates that the characteristics of social, economy, and demography that have significant effect on the incidence of school dropouts are the low education of household head, more than four household members, less than the poverty line household expenditure per capita, residence location in urban areas, and boys. The resulting model is sufficientfor estimation with the sensitivity value of 70.20% and the area under the ROC curve of 76.42%. Keywords: logistic regression, ROC curve, school children, sensitivity.

PENDUGAAN PARAMETER FUNGSI COBB-DOUGLAS GALAT ADITIF DENGAN ALGORITME GENETIKA

Hanif, Iqbal, Soleh, Agus M, Alamudi, Aam

Indonesian Journal of Statistics and Applications Vol 1 No 1 (2017)
Publisher : Departemen Statistika, IPB dengan Forum Perguruan Tinggi Statistika (FORSTAT)

Show Abstract | Original Source | Check in Google Scholar | Full PDF (747.491 KB)

Abstract

Cobb-Douglas function with additive errors is a function which can be used to analyse the relationship between production output and production factors. The method commonly used to estimate the parameter of that function is Nonlinear Least Square (NLS) and a common algorithm for this method is Gauss Newton iteration (NLS-GN). However, NLS-GN method has less-optimum results when analysing multicolinearity data. A possibly better method for this analysis is Genetic Algorithm (NLS-GA). The purpose of this study is to analyse the use of Genetic Algorithm to estimate parameters of Cobb-Douglas function with additive errors. The results show that NLS-GA method could not produce a better parameter estimator than NLS-GN method does but it produced a better parameter estimator in analysing multicolinearity data. NLS-GA method is capable of producing a better model with predictive ability than NLS-GN method does with real data. Keywords: cobb-douglas function, genetic algorithm, nonlinear least square