The 2nd International Conference On Applied Statistics (ICAS 2016)

Yudhie Andriyana — Sat, 01 Apr 2017 00:00:00 +0700

Table of Contents
((http://icas.fmipa.unpad.ac.id/proceeding/)

Segmentation and Implementation Markov Chain for Flooding Case in Jakarta from 2012 â€“ 2015

Baharudin Machmuda, Ayundyah Kesumawatib — Sat, 06 May 2017 00:00:00 +0700

The data obtained in this research is data flood events and the number of flood evacuees in Jakarta, where the
data was obtained from Regional Disaster Management Agency of Jakarta is recapitulated by the field of Information and
Control is the Operations Control Center Management Section (operational center) which is the monthly data for the year
2012 until 2015. Based on these data we want to know overview of the recent floods and the number of flood evacuees in
the province DKI Jakarta by five municipalities (West Jakarta, East Jakarta, North Jakarta, South Jakarta, and Central
Jakarta) and to determine the circumstances of the case chances of flooding and the number of flood evacuees in Jakarta
in 2012 to 2015. The analysis used for processing such data a descriptive analysis and Markov Chain using Microsoft
Excel 2007 to create pareto diagram and tables as well as perform a descriptive analysis by mapping using GIS software.
Based on the Pareto diagram obtained information that floods and the number of refugees during the interval 2012 to
2015 the highest in the year 2013. The table presents the status of flooding each month in the year 2012 to 2015 and state
transitions matrix chances of the flood situation and the number of refugees. Meanwhile, from a map obtained an
overview of the flood situation and the number of flood evacuees in five municipalities in Jakarta.
Keywords: Flood, Refugees, Map, Markov Chain, Descriptive

Scan Statistic Hotspot Detection and ORDIT Ordering Based on Health Multivariable Data in Depok

Choirul Basir, Yekti Widyaningsih — Sat, 06 May 2017 00:00:00 +0700

Health factors and circumstances of residents in an area play an important role in determining the quality of
a particular area, which is related to the environmental factors and population. This paper focuses on the quality of the
measured area for several factors using Scan Statistic hotspot detection and ORDIT (Ordering Dually In Triangles)
methods. Scan Statistics is used to detect the hotspot area of an interest; and ORDIT is a method to rank areas based
on several variables. The factors (or variables) that be used in these study are the number of infant with low birth
weight, malnourished children under five, underfive mortality, maternal deaths, births without the help of health
personnel, infants without handling the baby's health, and babies without basic immunization in every public health
center area in Depok. The observation unit is public health center area. The results of this study show that the hotspot
tends to be in the eastern part of Depok City, while ORDIT ranking yield that the most severe area is in Sukatani
health center. The results of this study are able to provide the meaningful suggestion for The Local Government about
the ranking of severity in the area based on several factors. So that the local governments can adopt policies to
improve the areas that assumed as the most severe.
Keyword: ORDIT, SaTScan, Scan Statistic, Hotspot Detection.

A Bayesian Spatio Temporal for Forecasting of Infectious Diseases by Means CAR Bayes

I Gede Nyoman Mindra Jaya, . Zulhanif, Bertho Tantular, Neneng Sunengsih — Sat, 06 May 2017 00:00:00 +0700

The development model for forecasting purpose in disease mapping is a very necessity. We not only
need the pattern of spread of the disease but also require a predictive value relative risk figures for each location
in the next period. This is necessary as a preventive measure for prevention of this disease provide a greater
negative impact. This research focus to develop a forecasting model in disease mapping by means CAR Bayes.
We applied our method to the dengue fever disease in Bandung city. We found that the humidity and larvae free
rate have a big effect on the relative risk. The forecasting result follows time trend which every mount the relative
risk increase.
Keyword: CAR Bayes, disease mapping, spatio temporal.

A Spatial Bivariate Design on Stream Networks

Achmad Bachrudin, Norizan Bt Mohamed, . Sudradjat, . Sukono, Emi Sukiyah — Sat, 01 Apr 2017 00:00:00 +0700

Spatial processes are modelling instrument which play an important role in an environmental sciences and
ecology. Ver Hoeff et al. (2006) and Cressie et al. (2006) developed a stationary process on a spatial statistics for stream
networks which are widely used on a river networks. These models are assumed for an univariate case. In the
environmental sciences and ecology are generally measured more than one variable. The objective of this paper is to build
a spatial Statistics in stream networks for bivariate.
Keywords: Spatial process, Stream networks, Bivariate

Revealing the Real Economic Activity: How Does Ramadan Affect the Retail Prices of Key Food Commodities in Indonesia

Masarina Flukeria, Dewi Agita Pradaningtyas, Muchammad Romzi — Sat, 01 Apr 2017 00:00:00 +0700

The economic activity of the Indonesian people is strongly affected by the Islamic events, especially Ramadan.
Economic activity in Indonesia always increases in the month where Ramadan falls. This is mainly because there is a
large increase on the consumption expenditure of Indonesian people in Ramadan. This paper aims to analyze Ramadan
effect on the movement of the retail prices of 10 key food commodities in Indonesia, i.e.: rice, purebred chicken meat,
purebred chicken eggs, beef, red chili, small chili, sugar, cooking oil, flour, and condensed milk. Monthly series of the 10
key food commodities from January 2000 until December 2014 are obtained from BPS Statistics Indonesia.
Ramadan is a moving holiday since it does not always fall in the same period/month every year because of the different
day-length period between Islamic calendars with National calendar. The movement of the moving holiday makes it
difficult to compare retail price data between periods where Ramadan falls. Therefore, the identification of Ramadan
effect along with seasonal adjustment on the series should be done to reveal the true movement of the price behavior
underlying the series and reflects real economic movements without the misleading seasonal changes.
We made seasonal adjustment of the price of several key commodities using X-12 Autoregressive Integrated Moving
Average (ARIMA) method. It is a combination of X-11 method, non-parametric smoothing based on moving averages and
linear regression model with ARIMA time series errors models. We built a special regressor with quadratic ramp up,
quadratic ramp down, and linear model to account for Ramadan effect. The result of the analysis showed that Ramadan is
proven to be statistically significant in affecting the retail prices of several key food commodities in Indonesia. The
influences of Ramadan and predictable seasonal patterns should be removed to reveal the real movement of key food
commodities prices from month to month.
Keywords: ramadan effect, retail prices, key food commodities, seasonal adjustment

Determining Value at Risk Based On Copula and GARCH

Margareth S.P. Silitonga, Lienda Noviyanti, Achmad Bachrudin — Sat, 06 May 2017 00:00:00 +0700

Copula model has become more popular in risk dependency structure modelling because copula able to
completely model dependency structure of multivariate distribution linearly or non-linearly. To estimate Value at Risk
(VaR) of a portfolio, one can model a marginal distribution of risk position and choose the right parametric copula to
model dependency ratio and goodness of fit test matter from the new model. The objective of this research is to answer
these questions. How to determine the value of VaR with Garch â€“ Copula proxy. Data used are Central Asia Bank
(BBCA), Waskita (WSKT) and Semen Indonesia (SMGR) stocks collected from December 1st, 2014 to November 30th,
2016 which consist of 516 of trade days. The application method of Garch-Copula as follows: First ARIMA and Garch
modeling, then copula function is used to model the compound distribution. Based on the research result, VaRâ€™s
computation with 90% level of confidence, stocks return of BBCA and WSKT in 90% level of confidence is
0,007013151. That means if an investor invested 1.000.000 rupiahs in BBCA and WSKT portfolio stocks the investor
would likely experience maximum loss at 7.013,15 rupiah in a day.
Keyword: Value at Risk, GARCH, Copula.

Generalized Space Time Autoregressive Integrated Moving Average (GSTARIMA) Model to Forecast Cocoa Export Volume

Lumâ€™atul Qomariyah, Toni Toharudin, . Soemartini — Sat, 01 Apr 2017 00:00:00 +0700

Generalized Space Time Autoregressive (GSTAR) is one of time series model used to forecast the data
consisting the element of space and time. This model is limited to the stationary and non-seasonal data. Generalized
Space Time Autoregressive Integrated Moving Average (GSTARIMA) is GSTAR development model that
accommodates the non-stationary and seasonal data. In this research, the model was applied to the monthly cocoa export
volume data from DKI Jakarta, Jawa Tengah and Jawa Timur in the last 8 years. Indonesian cocoa export volume in the
third position in the world trade, after Ivory Coast and Ghana. Identification of the AR and MA are using the minimum
value of AIC. Spatial order is chosen in first order because all of the provinces in this research are located in one island.
From the two spatial weight matrix, which distance inverse and normalized cross-correlation between locations to the
corresponding lag, we have the minimum MSE value to the data is distance inverse.
Keywords: Space time, GSTAR, GSTARIMA, Cocoa

Determining the Best Value of Window Length (L) in Singular Spectrum Analysis (SSA) Method

Nurul Jannah Amdayania, Gumgum Darmawan, Yudhie Andriyana, Neneng Sunengsih — Sat, 01 Apr 2017 00:00:00 +0700

Singular Spectrum Analysis (SSA) is a forecasting method that involve trajectory matrix to decompose
the time series data. Trajectory matrix is a multidimensional series as a result of transformation of unidimensional
time series data. The application of trajectory matrix consists a window length (L) as a dimension of its matrix.
The calculation to obtain L value is based on autocorrelation function of monthly rainfall data in the nearby area
from Juanda Airport, Surabaya during the period of January 1981 until December 2012. The study produces L
value in amount of 107 and indicates that the calculation to obtain L value based on autocorrelation function is
more reliable than the trial and error process.
Keywords: Autocorrelation, Blind Source Separation, Rainfall, Singular Spectrum Analysis, Window Length.

The Application of Seasonal Autoregressive Fractionally Integrated Moving Average (SARFIMA) in Forecasting of River Streamflow

Dadang Ruhiat, Toni Toharudin, Gumgum Darmawan — Sat, 01 Apr 2017 00:00:00 +0700

Time series modeling can be used in various fields including hydrology. River streamflow is one of
the hydrological parameters which is not only affected by seasonal factors but also often identified to possess
long memory pattern. In this paper, a modeling using Seasonal Autoregressive Fractionally Integrated Moving
Average (SARFIMA) will be applied. The data used is historical data of Cimanuk river streamflow which is
the result of 20-year documentation in monthly interval. SARFIMA model is then compared with ARFIMA.
The analysis is done to comprehend how SARFIMA model is able to model seasonal factors and long memory
pattern which is shown by the data of Cimanuk river streamflow. The result of the analysis shows that
SARFIMA model is not suitable for this data based on MSE and MAPE value.
Key words: Sarfima, seasonal factors, MAPE.

Seasonal Test for Non-Stationary Time Series Data by Means of Periodogram Analysis

Gumgum Darmawan, Budhi Handoko, Yusep Suparman — Sat, 01 Apr 2017 00:00:00 +0700

A seasonal phenomenon is common in our daily activities. Many business and economic time series
data contain a seasonal phenomenon that repeats itself after a regular period of time. The smallest time period for
this repetitive phenomenon is called the seasonal period. A seasonal test for time series data is well identified by
Fisherâ€™s exact test in periodogram analysis. However, the test is only accurate for stationary seasonal time series
data without trend. So, in this research we apply seasonal test not only for stationary time series data but also for
non-stationary data . Performance of this test is applied for both types of seasonal time series data.
Keywords: Fisherâ€™s Exact Test, Periodogram Analysis, Seasonal Time Series Data.

Implementation of a Multiple Regression Analysis in Knowledge of Occupational Safety and Health to The Charging PEKA (Pengamatan Keselamatan Kerja) Application in PT Pertamina EP Asset IV Field Cepu 2016

Sofi Khoirun Nisak, Ayundyah Kesumawati — Sat, 01 Apr 2017 00:00:00 +0700

Healthy, Safety, and the Environment (HSE) becomes one of the important things that is never
escapable from PT. Pertamina EP Asset IV Field Cepu company claimed HSE golden rules through Pengamatan
Keselamatan Kerja (PEKA) online application. This application has a purpose in increasing mindfulness workers,
fellow and guest concerning safety work aspect. In 2015, safety worker element that is Unsafe Action and Unsafe
Condition in Pertamina Cepu get a rise significantly. The analysis of mindfulness worker of safety worker in
filling PEKA online is less. There are some obstacle factors in filling PEKA, one of them is skills of the worker.
Therefore, purpose of this research is to know how big the influence of knowledge in healthy and safety act (K3),
Unsafe Action and Unsafe Condition, and also PEKA skill of mindfulness worker in filling PEKA. Multiple
Regression Analysis is used in this research. For every research the data consists of research questionaire and
recapitulation data of online PEKA 2015. After an analysis of multiple regression and the assumption was done,
in regressions model was got two factors which have dominant influence of mindfulness worker in inputting
online PEKA, there are workers knowledge factor about K3 and workers knowledge about Unsafe Action and
Unsafe Condition with all of the classic assumption of regressions model multiple linier.
Keywords : PEKA online application, Unsafe Action and Unsafe Condion, K3, Multiple Regression Analysis,
Regressionâ€™s Model

Bayesian Estimation of Mixed Effects Models of Fertilizer Response with Independent Skew-Normally Distributed Random Parameter

Mohammad Masjkur, Henk Folmer — Sat, 01 Apr 2017 00:00:00 +0700

The mixed effects model has been used for modelling the fertilizer response to predict the optimum doses.
However, a major restriction of this type of models is the normality assumption of the random parameter component.
The purpose of this paper is to investigate the performance of random parameter models of fertilizer dosing with
independent skew-normally distributed random parameter components. We compare the Linear Plateau, Spillman-
Mitscherlich, and Quadratic random parameter models with different random effects distribution assumption, i.e. the
normal, Skew-normal, Skew-t, Skew-slash, and Skew-contaminated distributions and the random errors following
symmetric normal independent distributions. The method is applied to datasets of multi-location trials of potassium
fertilization of soybeans. The results show respectively that the Skew-t Model is the best Linear Plateau Response
Model, the Normal Model for Spillman-Mitscherlich Response Model, and the Skew-t Model for the Quadratic
Response Model. However, overall the normal Spillman-Mitscherlich Response Model is the best model for soybean
yield prediction.
Keywords: Bayesian estimation, Dose-response model, Random parameter model, Skew-normal independent
distributions.

Modelling the Amount of Crime in Indonesia Using Geographically Weighted Negative Binomial Regression Approach

. Suliyanto — Sat, 01 Apr 2017 00:00:00 +0700

Acts of criminality is the act of someone who may be liable to punishment on the basis of the criminal code or
the laws and other regulations in force in Indonesia. So far the increase and decrease of crime tend to be small, but the
averAGE NUMBER OF CRIMINAL ACTS IN Indonesia is still very high. Various theories concerning the cause of the
crime have been proposed by experts from various disciplines and fields of science, but so far it is still not well there is
one answer to a satisfactory settlement. According to the theory of cartography/geography, crime spread into a region
geographically or socially. It means there is a spatial aspects in the spread amount of crime through social relations or
human interaction. Modeling problems of criminality in Indonesia cannot be done globally because according to the
theory of spatial elements of cartography/geography is very noteworthy. Regression analysis involving the geographical
aspect known as spatial regression. Method of spatial regression approach that is often used to model data in the form of
response variables divide tubers (count) is a geographically weighted poisson regression (GWPR). In the application
model GWPR often data do not meet the assumption that average and variansi are the same, but often variansi is greater
than the mean, the case is usually called overdispersi. Negative binomial regression (NBR) model is one of the models
that could be used to resolve the case of the overdispersi. NBR model involving the location called geographically
weighted negative binomial regression (GWNBR). In this paper we discussed the amount of crime in Indonesia modeling
using GWNBR approaches. The data used are secondary data sourced from publications BPS 2014 that includes 31
provinces in Indonesia. The results obtained show that the GWNBR model can cope with case overdispersi. The results
of a test of suitability of the model shows that the model GWNBR in accordance. There are five predictors variables, i.e.
the percentage of the poor population (ð‘¿ðŸ), the open unemployment rate (ð‘¿ðŸ), percentage of population aged 10 years or
over who have never school (ð‘¿ðŸ‘ ), overcrowding (ð‘¿ðŸ’), and per-capita gross regional domestic product ( ð‘¿ðŸ“ ) jointly
significant effect against the amount of crime in Indonesia(ð’š). Test result predictor variables individually shows that the
variables ð‘¿ðŸ , ð‘¿ðŸ‘ , ð‘¿ðŸ’ , and ð‘¿ðŸ“ each significantly influential in all provinces in indonesia, while the predictor variables ð‘¿ðŸ
do not affect significantly in the province of NAD and province of North Sumatra.
Keywords: Crime, Overdispersion, GWPR, NBR, GWNBR.

Double Hurdle Model for Censor Data

Defi Yusti Faidah, Resa Septiani Pontoh — Sat, 01 Apr 2017 00:00:00 +0700

Double hurdle model is used to describe the relationship between the response variables and predictor
variables. Here, the response variable in censored data and predictor variables in continuous, discrete, or a mixture of
both. Censored data have zero value for partly observations, and the rest have varying value. Another its characteristic
is partly values of specific range are transformed as a single value. The classical linear regression analysis can not be
used to see the relationship of variables that are censored. Meanwhile, the logistic regression analysis can not describe
the observation values vary. Therefore, the double hurdle approach can be used to resolve this issue. Double Hurdle
Model is a combination of logit and truncated regression.
Keywords: Censored Data, Double Hurdle

Elastic-Net Regularization in Statistical Downscaling to Estimate Rainfall

Dindha Fadhilah Dinati, Akbar Rizki, Aji Hamim Wigena — Sat, 01 Apr 2017 00:00:00 +0700

The impact of climate change and the importance of rainfall as the climate elements so that estimation
of rainfall is important to be implement. The estimation of rainfall used statistical downscaling (SD) technique
which utilize functional relationship approach between local scale data (rainfall) and global scale data (Global
Circulation Model output-GCM). In general, GCM output data are multicollinear, so it is required a technique to
overcome multicollinearity such as elastic-net regularization. The data used are GCM output above Indramayu
regency as explanatory variables and the monthly rainfall data ZOM 79 as response variables. The result shows
that the rainfall estimations with elastic-net at ZOM 79 from 2010 to 2013 were consistent.
Keywords: Elastic-net, multicolinearity, statistical downscaling.

Statistical Downscaling with Gamma Distribution and Elastic Net Regularization

Sri Maulidia Permatasari, Anik Djuraidah; Agus M Soleh — Sat, 01 Apr 2017 00:00:00 +0700

Rainfall data are more than or equal zero and can be represented using Gamma distribution. In statistical downscaling the local scale rainfall data are used as the response variable to develop functional relation with global scale precipitation data of Global Circulation Model (GCM) output as the predictor variables. Generally, GCM output are multicollinear and regularization method can solve the problem. This paper develops a statistical downscaling model with the response of Gamma distribution using ridge regularizations and elastic net regularizations. Data are monthly rainfall in Indramayu at 1981-2013 and monthly precipitation data of GCM output in 1981-2013. The result shows that the elastic net (standard deviation of RMSEP value is 22.7 mm/month and standard deviation of correlation between actual and predicted value is 0.20 in four years) is more consistent than ridge regularization (standard deviation of RMSEP value is 35.7 mm/month and standard deviation of correlation between actual dan predict rainfall is 0.22 in four years) in predicting a next year rainfall.

Keywords: Gamma Distribution, Statistical Downscaling, Global Circulation Model, Ridge, Elastic Net

Normal Multivariate Based Clustering of Regencies in East Java Province-Indonesia

Emi Arifiliana, Yusep Suparman, Enny Supartini — Sat, 01 Apr 2017 00:00:00 +0700

One of the adverse effects of development in Indonesia is the incline of welfare inequality. Particularly
in East Java Province, we can identify this condition among regencies and cities. In this thesis I intend to make
clusters among the regencies with regards to their welfare indicators. This may help the government in giving
development priority program among the regencies for reducing welfare inequality. I used the model-based
clustering method to overcome over-lapping problem found in the welfare data. Based on the Bayesian
Information Criterion, the most fitted cluster model is a three-cluster model with diagonal distributions, variable
volumes, equal shapes, and coordinate axes orientations. The first cluster, the low welfare cluster, consists of
twelve regencies. The second one is the middle welfare cluster consisting fifteen regencies. The third class, the
high welfare cluster, has twelve regencies too. Accordingly, I suggest that the government gives priorities on the
twelve low welfare regencies, particularly in clean water accessibility, literacy, child delivery helping by medical
doctors, poverty elevation, sanitation, and year of schooling.
Keywords: Welfare Indicators, Model Based Clustering, Expectation Maximization, Bayesian Information
Criterion.

Internet Adoption Analysis in Small and Medium Enterprises of the Tourism Coastal Areas of East Java (Case Study of Regional District Malang)

Kartika Gianina Tileng — Sat, 01 Apr 2017 00:00:00 +0700

This study originated from attraction of researchers about tourism and technology will be the factors which
driving the Indonesian economy. One of the potential of Indonesia is a coastal tourist area since Indonesia is an
archipelago. Recently the user of technology and information systems are increasingly in many ways. Researchers
interests to studying how the progress of use of technology in the tourism sector, so that the outcomes of this research can
provide input to the world of education on the design of technologies needed by Small-Medium-Enterprise (SME)
specialized in the tourism sector as well as providing information on portrait of SME in the tourism sector, especially in
the coastal area of the district of Malang. The plan of this study will be devoted to SME around the beach resort with
interviews, questionnaires, direct observations, carried out under the framework Technology-Organization-Environment
(T-O-E) according to the study Ghobakhloo, Arias-Aranda, Benitez-Amado, in 2011, Kuan and Chau research in 2001,
and Zhu and Kraemer in 2005 that has been developed by researcher from the original research. This research is focused
on discussing the adoption factors internet on SME in the beach area of Malang district, especially in the field of
technology in the framework of Technology-Organization-Environment. Data processing is done by using Path Analysis
supported by SPSS application and AMOS application. Outcomes of this study is expected to be a new discourse in the
technological development in the information technology sector as well as inputs for developers of potential coastal
tourist areas.
Keywords: Tourism, Small-Medium-Enterprise, Multivariate Analysis, Path Analysis, Technology, Organization,
Environment.

Bivariate Poisson Regression in Modelling Infant and Maternal Mortality Rate in West Java Province 2014

Citra Yanuar Widayanti, Yusep Suparman, Bertho Tantular — Sat, 01 Apr 2017 00:00:00 +0700

Reducing infant and maternal mortality are two of the eight of the Millenium Development Goals (MDGâ€™s).
Nevertheless, the two goals are hardly to achieved particularly in West Java Province. Instead of decreasing, infant
mortality rate in West Java Province increased from 26 infant deaths per 1000 live birth in 2010 to 34 infant deaths per
1000 live birth in 2014. The maternal mortality rate in West Java also increased from 226 maternal deaths per 100.000
live birth in 2010 to 369 maternal deaths per 100.000 live birth in 2014. Accordingly, identifying infant and maternal
mortality important factors are required for designing effective development programs to meet the two Millenium
Development Goals (MDGâ€™s). In this paper, we identified the important factors of infant and maternal mortality by means
at Poisson regression. Particularly, we used bivariate Poisson regression model to accommodate interrelation between
infant and maternal mortality. Based on 2014 West Java Health Profile data, we found that percentage of health workers
is the most important factor. The testing parameters for bivariate Poisson regression model of infant mortality and
maternal mortality show that, the pregnant women get a tablet Fe3, treatment of obstetric complications , households
clean and healthy behavior, health workers, and women with the age marriage less than 18 years are significant to infant
and maternal mortality model.
Keywords: Infant Mortality, Maternal Mortality, Poisson Regression, Bivariate Poisson Regression.

Vector Autoregressive Generalized Space Time Autoregressive (VAR-GSTAR) Model with 2-Means Clustering on Rainfall of Central Java

Dewi Retno Sari Saputro, M. Dhamar Widhoro Jati, Purnami Widyaningsih — Sat, 01 Apr 2017 00:00:00 +0700

Monthly interregional rainfall within 29 sub districts/districts of Central Java has big variance.
Because of big variance, it needs clustering. The clustering method is the 2-means clustering. Clustered data
is better than unclustered data. Rainfall data have spatial and temporal effects. Therefore, VAR-GSTAR
model could be applied to monthly rainfall data. VAR-GSTAR model needs a spatial weight to measure
correlation within interregional rainfall. The spatial weight is normalization of cross correlation. VARGSTAR
model has two orders. Autoregressive order is obtained from vector autoregressive (VAR) model
and spatial order is determined from generalized space time autoregressive (GSTAR) model. Because of two
orders, the model could be constructed as VAR-GSTAR (p1) model. The purpose of this research is to apply
VAR-GSTAR model with 2-means clustering on rainfall data within 29 sub districts/districts of Central Java.
The results of this research on rainfall data are VAR-GSTAR (11) model for low cluster and VAR-GSTAR
(21) model for high cluster. VAR-GSTAR (11) has root means square error (RMSE) 173.312 and VARGSTAR
(21) has RMSE 203.272.
Keywords: rainfalls, 2-means clustering, VAR-GSTAR.
INTRODUCTION

Classification Model On Household Clothing Expenses In The City Of Ambon Using Multivariate Adaptive Regression Splines (MARS) Methods

Sobar Dwi Prabowo, Lienda Noviyanti, Titi Purwandari — Sat, 01 Apr 2017 00:00:00 +0700

Traditional market as one of the shopping facility has a special place in our society. Nowadays, the people have
a change of lifestyle: In the past they only had a traditional market, but now they also have a modern market. This
improvement changes the way people shopping. The purpose of this study is to identify a relationship between how
people choose traditional or modern market to buy their household clothing and the variable that affect those decision
using classification method. A good classification method should give the least misclassification rates. Multivariate
Adaptive Regression Spline (MARS) model is one kind of classification method which often used when there are many
categorical variable of response, the data doesnâ€™t have a pre specification model, and the predictor variable consist of
categorical and continuous data type. This research purpose is to get the best model on classification, taking the case
study of household preference on clothing shopping place in Ambon, and its influencing variables, based on 2012â€™s Cost
of Living Surveys (SBH). Method performance is measured by its accuracy rate, Noise Signal Ratio (NSR) and G-Mean
from classification table.
Keywords: Household clothing expenses, MARS, Cost Of Living Survey

Measuring The Citizen Satisfaction of Bandung Using Benefit Performance Index and Principal Component Regression

Yuyun Hidayat, Titi Purwandari, Irlandia Ginanjar — Sat, 01 Apr 2017 00:00:00 +0700

Purpose of this study is to provide information on the quality aspects of the development of Bandung. This was
achieved by constructing a satisfaction index as an indicator of managerial navigation. The increase in the total index
requires identification of the specific problem in the area of development. The Correspondence Analysis has been
classified the development area into 4 areas so that the necessary treatment is different for each area of development.Pilot
survey of 540 people using CIT approach produces 1398 incident ( citizens concern). The principal Component Analysis
procedure resulted in 45 aspects about quality according to citizens lens. The main survey was performed using Multi
Stage Stratified random sampling design with margin of error 5.2% and a confidence level of 95%.
The Mayor Performance Index score is 73.37%. refering to the KEP / 25 / M.PAN / 2/2004. the score is almost reached
EXCELLENT category. Research in four areas result Clustering analysis shows that the correspondent has a specific
development problems in each area. Objects improvements focus on weak points and competitive advantages that have
performance scores 75 or less. Strategic recommendations are given for the four areas. Mayor Performance Index score is
73.37%. referring to the KEP / 25 / M.PAN / 2/2004 Score is almost reached category EXCELLENT.Research in four
areas (the results of clustering using Correspondent Analysis) shows that the problems of development in every area has
its peculiarities. Objects of improvements is focused on weak points and competitive advantages that have performance
scores 75 or less. Strategic recommendations are given for the four areas.
Keywords: Critical incidence Technique. Principal Component Regressions Analysis. Correspondence Analysis.
Customers Satisfaction Index

Desirability Function with Principal Component Analysis for Multi-response Optimization

Sri Winarni, Budhi Handoko, Yeny Krista Franty — Sat, 01 Apr 2017 00:00:00 +0700

Multi-response optimization is the process of getting the combination treatment that produces optimum
responses. In the industry manufacture it is needed to get the best quality product by considering some characteristics
of products simultaneously. This research used optimization method desirability function combined with principal
component analysis. This method is used when there is correlation among quality characteristics product. The
approach used is to convert some of the responses into one objective variable is then used to determine the point of
optimization. Case study in this research is the optimization of 12L14 free machining steel turning process. The result
optimum point was found a cutting speed of 316 m/min, feed rate of 0.13 mm/rev and depth of cut of 0,5826 mm.
Keywords: multi-response optimization, desirability function, principal component analysis.

Classification of Underdeveloped Regency using Probabilistic Neural Networks

Vira Wahyuningrum, Jadi Suprijadi, . Zulhanif — Sat, 01 Apr 2017 00:00:00 +0700

One of the supporting data in the government work plan in order to realize national priorities of
development of underdeveloped regency is data determining the status of regional backwardness. Determination
of the status regency is a process of classifying the area as an underdeveloped regency or not. Classification cases
can be resolved very quickly using computational algorithm's Neural Network. Probabilistic Neural Network
(PNN) is one method of neural network that can be used to resolve cases of classification with very good
performance. PNN only requires one iteration of training so that the process is faster when compared with a Back
Propagation neural network that requires several iterations of training. PNN has a structure consisting of four
layers, namely input layer, pattern layer, summation layer and decision layer. This study applied the PNN method
in the classification of underdeveloped regency in Indonesia. Classification results show that as many as 458 of
the 491 regencies predicted in accordance with the actual status. The classification method with PNN use leads to
good performance with the accuracy value of 93,29 percent, sensitivity of 91,42 percent and specificity of 94,10
percent.
Keywords: Neural Network, Probabilistic Neural Network, classification, underdeveloped regency

Hospital Malnutrition Modelling of Children Suffering Acute Respiratory Infections Using Multivariate Adaptive Regression Spline Approach

Ardi Kurniawan, Nur Chamidah, Intan Pratiwi Utami — Sat, 01 Apr 2017 00:00:00 +0700

Hospital malnutrition is a condition of nutritional insufficiency or nutritional imbalances of patients treated in
the hospital. A patient suffers hospital malnutrition when patientâ€™s weight reduces more than or equal to 2% after
undertaking treatment in the hospital at least two days. A child who is in pain conditions will be susceptible to
malnutrition. There are two possible situations when a child is admitted to the hospital, i.e., malnutrition or
unmalnutrition. In general, the incidence of malnutrition hospital is high enough, which is about 30% to 60%. One of
diseases that affects many children and many patients caused hospital malnutrition is a disease of Acute Respiratory
Infections (ARI). In this paper, we determine a model of the relationship between the incidence of hospital malnutrition of
children suffer ARI and the factors that influence it, i.e., patient age, duration of treatment in hospital, body mass index,
and treatment class. Modelling is conducted by using Multivariate Adaptive Regression Spline (MARS), because the
method allows obtaining interaction among the predictor variables. So that, we obtain statistical model that is more
realistic to actual condition, and get the accuracy of the classification model value.
Keywords: Acute Respiratory Infections, Hospital Malnutrition of Children, Multivariate Adaptive Regression Spline.

The Extension of the Noetherian Conditions for Matrix

Achmad Abdurrazzaq, Ismail bin Moh, Ahmad Kadri bin Junoh — Sat, 01 Apr 2017 00:00:00 +0700

Let be a ring and is a set of matrix with the entries of the matrix element of ring . Set
of matrix together with addition and multiplication matrix is matrix ring. Noetherian is condition of ring (resp.
module) which are every ideal (resp. sub modules) fulfilled ascending chain condition. We study about
Noetherian and locally Noetherian conditions for set of matrix. Some conditions that are fulfilled locally
Noetherian condition of ring and module for set of matrix are proved and also proved that Noetherian module
matrix is also Artinian module.

Preventive Maintenance Scheduling Based On Given Budget Fitness Function Using Generational Genetic Algorithm

Yeny Krista Franty, Budhi Handoko — Sat, 01 Apr 2017 00:00:00 +0700

Cost function analysis is an important activity in order to optimize the multi objective function using
genetic algorithms. This is due to the accuracy of the resulting cost of components will be part of the input to the
programming process which will affect preventive maintenance schedule for components of the engine. Multi
objective cost analysis in optimization will be associated with the reliability of the machine that is expected to be
maximized at minimum cost. The cost analysis will also use technical economic parameters namely the failure of
inflation, inflation of maintenance, replacement cost inflation, and the inflation of rate fixed cost.

The Implementation of Simulated Anealling Algortihm to Determine Preventive Maintainance Schedule

Budhi Handoko, Yeny Krista Franty, Sri Winarni — Sat, 01 Apr 2017 00:00:00 +0700

Simulated Annealing Algorithm is one category of metaheuristic algorithm that could be
implemented to determine determine the preventive maintainance schedule. This algorithm is used to
solve the problem of optimization on three different types of fitness function in order to demonstrate the
result of schedule. Input of the algorithm consist of three components, parameters of time to failure
distribution, cost and budget, and also essential values for the algorithm. Based on the data, it is a weibull
distribution with two parameters with scale parameter lambda = 0,00144 and shape parameter beta =
1,00162. The results of the algorithm process have three recomendation of schedule.The first one, based
on the fitness function 1, the same weight of budget and reliability yield the minimum cost 35,75 million
rupiahs for maintainance activity with schedule for maintainance on 10th and 16th month. Second, using
the second fitness function, the lowest cost reached when the budget provided by the company is 64
million rupiahs, with the schedule of maintainance on 21st and 22nd month. Finally, the third fitness
function recommed the 10% required reliability in order to reach minimum cost of maintainance with the
schedule of maintainance are on the 17th, 19th, and 23rd month.
Keywords: Simulated anealling algorithm, Fitness function, metaheuristic algorithm, weibull distribution,
preventive maintaince