cover
Contact Name
Meiliyani Siringoringo
Contact Email
meiliyanisiringoringo@fmipa.unmul.ac.id
Phone
+6285250326564
Journal Mail Official
eksponensial@fmipa.unmul.ac.id
Editorial Address
Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Mulawarman Jl. Barong Tongkok, Kampus Gunung Kelua Kota Samarinda, Provinsi Kalimantan Timur 75123
Location
Kota samarinda,
Kalimantan timur
INDONESIA
Eksponensial
Published by Universitas Mulawarman
ISSN : 20857829     EISSN : 27983455     DOI : https://doi.org/10.30872/
Jurnal Eksponensial is a scientific journal that publishes articles of statistics and its application. This journal This journal is intended for researchers and readers who are interested of statistics and its applications.
Articles 205 Documents
Peramalan Curah Hujan di Kota Samarinda Menggunakan Autoregressive Integrated Moving Average (ARIMA) Syawal, Al Fitri; Wahyuningsih, Sri; Siringoringo, Meiliyani
EKSPONENSIAL Vol. 13 No. 2 (2022)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1085.686 KB) | DOI: 10.30872/eksponensial.v13i2.1058

Abstract

Autoregressive Integrated Moving Average (ARIMA) is a forecasting model for time series data analysis. In this study, the modeling and forecasting of monthly rainfall in Samarinda City was carried out using the ARIMA model. The results showed that the ARIMA (6, 1, 1) model was the best model . The results of forecasting rainfall for the period January to December 2022 in Samarinda City using the ARIMA (6, 1, 1) model show that rainfall tends to be constant every month. The lowest level of rainfall occurred in January 2022, which was 210.3869 mm. The highest level of rainfall occurred in April 2022, which was 271.5705 mm.
Analisis Cluster Single Linkage Berdasarkan Potensi Desa Di Kabupaten Kutai KartanegaraTahun 2019 Suyanto, Suyanto; Syaripuddin, Syaripuddin; Wasono, Wasono
EKSPONENSIAL Vol. 12 No. 1 (2021)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (614.371 KB) | DOI: 10.30872/eksponensial.v12i1.761

Abstract

Data mining is a step in the process of Knowledge Discovery in Database (KDD) which consists of the application of data analysis and the discovery of algorithms that produce certain enumerations of patterns in the data,Cluster Analysis is one of the methods in multivariate statistical analysis that is used to group objects into groups based on their characteristics, so the objects in one group have more homogeneous characteristics compared to objects in other groups. Single Linkage is a clustering process based on the closest distance between objects. If two objects are separated by a short distance, then the two objects will merge into one cluster. This study aims to obtain a cluster of village potential in Kutai Kartanegara Regency in 2019, based on the variable availability of educational facilities, the availability of health facilities, the availability of health workers, the availability of coin / card public telephones, the existence of lodging, the existence of market buildings, the existence of supermarkets, the existence of banks, the population obtaining credit facilities, the existence of other Non KUD cooperatives., Based on the results of the analysis, it can be seen that, Clusters formed in the grouping of potential villages / villages in Kutai Kartanegara Regency using a single linkage method are as many as 2 clusters.
Penaksiran Parameter Model Mixed Geographically Weighted Regression (MGWR) Data Indeks Pembangunan Manusia di Kalimantan Tahun 2016 Mita Asti Wulandari; Suyitno Suyitno; Wasono Wasono
EKSPONENSIAL Vol 10 No 2 (2019)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (795.642 KB)

Abstract

Mixed Geographical Regression (MGWR) model is a combination of global linear regression model and GWR model. Some MGWR parameters are global (the same value) and the other parameters are local (different values) ​​at each observation location. The purpose of this study is to obtain MGWR model for every District’s HDI and to obtain the factors that significantly influence District HDI in East Kalimantan, Central Kalimantan and South Kalimantan Provinces. Estimating parameters for global parameters use Ordinary Least Square (OLS) method. Estimating parameters for local parameters use Weighted Least Square (WLS) method, where weighting spatial is determined by using gaussian adaptive function. Based on the result of MGWR parameters testing, it was concluded that the school enrollment rates (SMP) affected the HDI of all districs in East Kalimantan, Central Kalimantan and South Kalimantan provinces. The population density and the percentage of poor people influence locally to HDI.
Penaksiran Parameter dan Pengujian Hipotesis Model Regresi Weibull Univariat Suyitno Suyitno
EKSPONENSIAL Vol 8 No 2 (2017)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (509.861 KB) | DOI: 10.30872/eksponensial.v8i2.41

Abstract

In this study, a univariate Weibull regression model is discussed. The Weibull regression is a regression model developed from the Weibull distribution, that is the Weibull distribution depending on the covariates or the regression parameters. The univariate Weibull regression (UWR) model can involve the survival function model and the mean model of the response variable with the scale parameter stated in the terms of the regression parameters. The aim of this study is to estimate the UWR model parameters using the maximum likelihood estimation (MLE) method, and to test the regression parameters. The result shows that the closed form of the maximum likelihood estimator can not be found analytically, and it can be approximed by using the Newton-Raphson iterative method. The regression parameters testing involves simultaneous and partial test. The test statistic for simultaneous test is Wilk's likelihood ratio. Wilk statistic follows Chi-square distribution, which can be derived from the likelihood ratio test (LRT) method. The test statistic for partial test is Wald and it follows standard normal distribution. The alternative test statistik for partial test is squared of Wald statistic, where it follows Chi-square distribution with one degree of freedom.
Optimasi Parameter Pemulusan Pada Metode Peramalan Double Exponential Smoothing Holt Menggunakan Golden Section: Studi Kasus : NTPT Provinsi Kalimantan Timur Tahun 2014-2019 Yani, Tika Anggre Ria; Wahyuningsih, Sri; Siringoringo, Meiliyani
EKSPONENSIAL Vol. 13 No. 1 (2022)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (728.707 KB) | DOI: 10.30872/eksponensial.v13i1.880

Abstract

Double Exponential Smoothing Holt (DES Holt) is a method that can be used when the data pattern shows a trend pattern. Determination of smoothing parameters usually uses trial and error, but this method still has inefficient results to get the best accuracy. One method that can be used to determine the smoothing parameters value is the golden section method. The application of the DES Holt and golden section methods will be carried out to predict the Exchange Rate of Farmers Subsector Livestock (ERFSL) of East Kalimantan Province. The purpose of this study was to obtain forecasting results and the level of accuracy of the ERFSL of East Kalimantan Province for the period January, February, and March 2020 using the DES Holt methods with the golden section smoothing parameter optimization method. The Forecasting results of DES Holt method have increased in the next three periods with an accuracy rate of 0.8856663%. The level of accuracy of forecasting results using the DES Holt methods has a MAPE value of less than 10%, which means the methods very good for predicting the ERFSL of East Kalimantan Province.
Pemodelan Indeks Pembangunan Manusia (IPM) Menggunakan Analisis Regresi Probit: Studi Kasus: Indeks Pembangunan Manusia (IPM) di Pulau Kalimantan Tahun 2017 Christyadi, Santo; Satriya, Andi M Ade; Goejantoro, Rito
EKSPONENSIAL Vol. 11 No. 2 (2020)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (936.499 KB) | DOI: 10.30872/eksponensial.v11i2.662

Abstract

Ordinal probit regression analysis is non-linear regression analysis that used to find affected independent variables for ordered categorical dependent variable and regression model in this analysis used Normal cumulative distribution function. Parameter estimation in this model used Maximum Likelihood Estimation (MLE) method. This model has been applied to Human Development Index (HDI) in Borneo Island in 2017 case study. HDI is the most important measurement in improving the human development quality in all cities/regencies in Indonesia. Some factors that affected to IPM, they are Life Expectancy (X1), School Expectancy (X2), Spending per Capita (X3), Average School Duration (X4), and Labour Force Participation Rate (X5). Based on research that was performed by researcher, resulted two factors affecting to HDI, those are Life Expetancy and Average School Duration. This model has classification accuracy of 89,29%, APER (Apparent Error Rate) value of 10,71%, and AIC (Akaike Information Criterion) value of 39,75; this model was very good because prediction value is almost approaching to observation value (actual value).
Penerapan Model Seasonal Autoregressive Fractionally Integrated Moving Average Pada Data Inflasi di Indonesia Edy Fahrin; Memi Nor Hayati; Meiliyani Siringoringo
EKSPONENSIAL Vol 10 No 2 (2019)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (618.603 KB)

Abstract

Current inflation data is influenced by previous inflation data. Inflation data from time to time is indicated to have a long memory and seasonal pattern. The Seasonal Autoregressive Fractional Integrated Moving Average (SARFIMA) model is one of the models used to predict data that has a long memory and seasonal pattern. The purpose of this research was to find out the the best SARFIMA model and forecast inflation in 2018 using the best SARFIMA model. The sample in this research was Indonesian monthly inflation data for the period January 2008 to December 2017. There are four stages of SARFIMA modeling, namely model identification, parameter estimation, diagnostic checking, and application of models for forecasting. Based on the results of the analysis, the best SARFIMA model selected based on the AIC and MSE criteria is the SARFIMA model with d = 0.687. The results of inflation forecasting from January to December 2018 show a fluctuating value every month with the inflation rate at 3.30% - 3.65%.
Penentuan Besaran Premi Asuransi Jiwa Berjangka dengan Model True Fractional Premiums Muhammad Al-Firdaus Erdian; Ika Purnamasari; Wenny Kristina
EKSPONENSIAL Vol 9 No 1 (2018)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (451.092 KB) | DOI: 10.30872/eksponensial.v9i1.271

Abstract

The model of the payment of life insurance premium that can be paid more than once a year is called fractional premiums. This model consists of two types, namely true fractional premiums and apportionable premium. The true fractional premiums is divided into two models of payment of compensation, namely discrete payment model and continuous payment model. This study aims to find out the comparison of 20 years life insurance premium with true fractional premiums model based on gender and number of payments made in a year from both payment models. The data used in this research is the simulation data. Based on the research result, it is found that the amount of life insurance premium using discrete compensation payment model is cheaper than the one using the continuous payment model. While based on gender, the premium of male is more expensive than female. Based on the amount of payments made in one year, payments made each month are more expensive than the payments made each quarter and semester.
Pengklasifikasian Status Gizi Balita di Puskesmas Sempaja Samarinda menggunakan Probabilistic Neural Network (PNN) Tahun 2019 Lestari, Putri Ayu Dwi; Hayati, Memi Nor; Nasution, Yuki Novia
EKSPONENSIAL Vol. 12 No. 2 (2021)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1059.709 KB) | DOI: 10.30872/eksponensial.v12i2.812

Abstract

Probabilistic Neural Network (PNN) is a model in Artificial Neural Networks (ANN) that is used for classification. PNN depends on the smoothing parameter (α). PNN has the advantage of being able to value of problems that previously existed in the back propagation method of ANN. The PNN method in this study was applied to the nutritional status of toddlers. Assessment of the nutritional status of toddlers can be determined through measurements of the human body known as anthropometry. Parameters for determining nutritional status based on anthropometry are age, weight and height. Therefore, in this study, a classification of the nutritional status of children under five is carried out to determine whether the toddler is experiencing good nutrition or poor nutrition. It was found that PNN with the best classification accuracy rate on the nutritional status of toddlers, namely the proportion of training data and testing data of 50%: 50% with α = 1, with accuracy results between training data and training data of 85% and accuracy results between data testing of the training data by 70%.
Analisis Cluster Pada Data Kategorik dan Numerik dengan Pendekatan Cluster Ensemble: Studi Kasus: Puskesmas di Provinsi Kalimantan Timur Kondisi Desember 2017 Lestari, Nur Aini Ayu; Hayati, Memi Nor; Amijaya, Fidia Deny Tisna
EKSPONENSIAL Vol. 11 No. 2 (2020)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (698.379 KB) | DOI: 10.30872/eksponensial.v11i2.652

Abstract

Cluster analysis used to process categorical and numerical data at once is Cluster Ensemble algorithm Based on Mixed Data Clustering (algCEBMDC), which is a cluster algorithm with an ensemble cluster approach. The method used for numerical data is Agglomerative Nesting (AGNES) algorithm and for categorical data is the RObust Clustering using linK (ROCK) algorithm. The best clustering method and the optimum number of clusters in the AGNES algorithm is selected based on the maximum Pseudo-F value and the minimum icdrate value. The optimum number of clusters in the ROCK algorithm is selected using the minimum value of ratio . The purpose of this study was to make a group of 179 Puskesmas in East Kalimantan on December 2017. Based on the results of the analysis, obtained 5 optimum cluster for numerical clustering with the AGNES algorithm and 2 optimum cluster for categorical clustering data with the ROCK algorithm. Final cluster for mixed data clustering obtained 2 optimum cluster at a threshold of 0.2 and 0.3 with value of ratio is . The first cluster consists of 83 Puskesmas and cluster two of 96 Puskesmas.

Page 10 of 21 | Total Record : 205