Garuda - Garba Rujukan Digital

Penerapan Metode Fuzzy Time Series Using Percentage Change Nurul Hidayah; Ika Purnamasari; Memi Nor Hayati
EKSPONENSIAL Vol 7 No 2 (2016)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (107.311 KB)

In 1993, Song and Chissom introduce fuzzy times series is capable of handling the problem of data forecasting if historical data are the values of linguistic. The study uses the modeling outline by way of fuzzy relation equations and approximate reasoning to predict the number of students. In this study, the approach to the theory of fuzzy time series used is fuzzy time series using percentage change developed by Stevenson and Porter in 2009. The case studies used in this study is the population of East Kalimantan Province. This study aims to determine how the application of fuzzy time series method using percentage change in the population of East Kalimantan from 1980 until 2013. Forecasting is done menggukan linguistic value of the fuzzy set which is formed of the differences and converted into a percentage of the universe of discourse as a value data. Based on the results of the application of the method using fuzzy time series of the percentage change obtained 12 fuzzy set which is linguistics of the data, the accuracy of forecasting value from 1981 to 2013 using MAPE (Avarage Forcasting Error Rate) that is equal to 0.557%.

Pemantauan Peramalan Akseptor KB Baru Provinsi Kalimantan Timur Menggunakan Simple Moving Average dan Weighted Moving Average dengan Metode Tracking Signal Eric Sapto Raharjo; Memi Nor Hayati; Sri Wahyuningsih
EKSPONENSIAL Vol 7 No 1 (2016)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (218.042 KB)

Simple moving average (SMA) is the basic method used to measure seasonal variations. This method is done by moving the average value counted along the time series. Weighted moving average (WMA) includes selecting weights may be different for each data value and then calculating the weighted average time period of k, the value obtained as the smoothed value.The purpose of this study was to determine the method and the best forecasting model with the results of forecasting on new data on the number of new acceptors KB using tracking signal. Results of this study is to model 3 SMA method is the best monthly tracking signal with a value of -0.0349 to -0.0178 β = 0.1 and β = 0.2 for the forecasting results for the period of January, February, and March 2015 amounted to 8.151, 8.131, and 7.485. For model 3 monthly WMA method is best with a variety of weights W1 = 0.25; W2 = 0.35; W3 = 0,40 tracking signal has a value of -0.0451 to -0.0439 β = 0.1 and β = 0.2 for the forecasting results for the period of January, February, and March 2015 for 8.044, 7.893, and 7.517 , In this case the method of 3-month SMA model is the most appropriate method to forecast the number of new acceptors KB East Kalimantan province.

Penerapan Generalized Poisson Regression I Untuk Mengatasi Overdispersi Pada Regresi Poisson Iim Masfian Nur; Desi Yuniarti; Memi Nor Hayati
EKSPONENSIAL Vol 7 No 1 (2016)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (104.661 KB)

Poisson Regression model is commonly used to analyze count data is assumed to have Poisson distribution where the mean and variance values are equal or also called equdispersion. In fact, this assumption is often violated, because the value of variance is greater than the mean value, this condition is called overdispersion. Poisson regression which is applied to the data that contains overdispersion will imply the value of standard error becomes underestimates, so the conclusion is not valid. One of the models that can be used for overdispersion data is Generalized Poisson Regression I (GPR I). This research discuss the handling of overdispersion on Poisson regression using GPR I, with case study modeling the number of cervical cancer cases in East Kalimantan in 2013. In this research GPR I models meet the criteria for suitability of regression compared Poisson regression models because it has a smaller AIC value.

Metode Regresi Robust Dengan Estimasi Method of Moment (Estimasi-MM) Pada Regresi Linier Berganda Hisintus Suban Hurint; Ika Purnamasari; Memi Nor Hayati
EKSPONENSIAL Vol 7 No 2 (2016)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (556.811 KB)

Method of Ordinary Least Square (OLS) on the regression analysis is a method which is often used to estimate the parameters. In the OLS method, there are several assumptions that must be fulfilled, these assumptions are often not fulfilled when the data contains outlier, so need a method that are robust to the presence of outliers. In this research, studied method of robust regression with MM-estimation. MM-estimation is a combination of estimation methods that have a high breakdown point, namely the Scale estimation(S-estimation) and Least Trimmed Square estimation (LTS estimation) and the method that have higher efficiency point, namely the Maximum Likelihood Type estimation (M-estimation). The first step in the MM-estimation is to find the S-estimator, then set the parameter regression using the M-estimation. The purpose of this study was to determine the effect of price index of foodstuffs ( ), the price index of education ), and the price index of health ) to the CPI for the province of east borneo, where the CPI data contains outliers, namely observation to 13, 31,and 32.

Analisis Autokorelasi Spasialtitik Panas Di Kalimantan Timur Menggunakan Indeks Moran dan Local Indicator Of Spatial Autocorrelation (LISA) Nurmalia Purwita Yuriantari; Memi Nor Hayati; Sri Wahyuningsih
EKSPONENSIAL Vol 8 No 1 (2017)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (773.151 KB)

In the last few decades has developed statistical methods relating to spatial science, is the spatial statistics. Spatial Statistics aims to analyze spatial data. The case studies in this study was the amount of hotspots in East Kalimantan by Regency/City in years 2014-2016. This study aimed to analyze the existence of spatial autocorrelation in the data the amount of hotspots as well as determine the level of vulnerability to potential areas of forest and land fires in East Kalimantan by Regency/City in 2014-2016. The method used to analyze the global spatial autocorrelation is the Moran Index method and Local Indicators of Spatial Autocorrelation (LISA) for analyze spatialautocorrelation locally. The results of the analysis of global spatial autocorrelation using the Moran index with α = 20% showed there spatial autocorrelation amount of hotspots in East Kalimantan in 2014, 2015, and 2016. Meanwhile, the analysis results locally using LISA showed that there spatial autocorrelation in several Regency/City in East Kalimantan in 2014, 2015 and 2016. The analysis results Regency/City that belong to the vulnerable category of forest and land fires is Bontang City, Kutai Barat Regency, Kutai Kartanegara Regency, Mahakam Ulu Regency, dan Penajam Paser Utara Regency and Samarinda City.

Pemodelan Jumlah Kematian Bayi di Provinsi Nusa Tenggara Timur Tahun 2015 Dengan Regresi Poisson Pratama Yuly Nugraha; Memi Nor Hayati; Desi Yuniarti
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 (564.515 KB)

Poisson regression is one of the non-linear regression analysis whose response variable is modeled with Poisson distribution. The parameter estimation Poisson regression model using Maximum Likelihood Estimation (MLE). This study aims to model the number of infant mortality in East Nusa Tenggara Province in 2015 and what factors affect the occurrence of cases of infant mortality in East Nusa Tenggara Province using Poisson regression. The results of research with Poisson regression factors influencing the number of infant mortality is the number of deliveries assisted by health personnel (x1), the percentage of pregnant women receiving FE3 tablets (x2), the number of obstetric complications handled (x4), the percentage of low birth weight babies (x5), the number of exclusively breastfed babies (x6), the percentage of households Live clean and healthy (x7), and the number of deliveries is helped by non-medical personnel (x8).

Model Regresi Logistik Spasial Tiara Nurul Ma’ala; Desi Yuniarti; Memi Nor Hayati
EKSPONENSIAL Vol 7 No 2 (2016)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (176.03 KB)

Logistic regression modeling procedure is applied to model the response variable (Y) which is based on one or more categorical explanatory variable (X) which is categorical or continuous. In the application of logistic regression is often found that there are spatial influences that affect the model. The existence of spatial relationships between regions that cause necessary to accommodate the spatial diversity into the model, so that the analysis used logistic regression spatial. First law of geography says that everything is related to everything else, but near things are more related than distant things. Then, when a region becomes a major cause of the spread of a disease is suspected, the region will provide the spread of a disease to the new area adjacent to it. The way to find out the adjacent area with the same characteristics can be done with spatial logistic regression method.The spread of TB disease in Samarinda City is quite high. TB is a chronical disease which has been known by the public and feared of its infection. This study’s aim is to determine the appropriate model to estimate the spread of TB disease. From this model it is known that the factors that influence the number of people with TB disease in every village in Samarinda City in the year 2013 are the number of primary school in every village and the spatial effect. This means that there is the influence of spatial factors to the spread of TB disease in every village in Samarinda City in the Year 2013.

Peramalan Menggunakan Metode Fuzzy Time Series Cheng Sumartini Sumartini; Memi Nor Hayati; Sri Wahyuningsih
EKSPONENSIAL Vol 8 No 1 (2017)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (513.357 KB)

Forecasting process play an important role in time series data as required for decision-making process. Fuzzy Time Series (FTS) is a concept known as artificial intelligence which use to predict a problem where the actual data was formed in the values of linguistic. This study discusses the FTS method developed by Cheng to forecast the Composite Stock Price Index (CSPI) in October 2016. Within FTS, long intervals determined in beginning process. Based on FTS Cheng method with interval determination using frequency distribution, forecasting stock index based on data from January 2011-September 2016 result forecast for the month of October 2016 was 5.367.98 points. Based on calculation of MAPE, CSPI data from January 2011-September 2016 had an error value as big as 2.56% and has an accuracy of forecasting results amounted to 97.44%. Forecasting use the FTS Cheng has a great performance because it has MAPE value below 10%.

Peramalan dengan Metode Seasonal Autoregressive Integrated Moving Average (SARIMA) di Bidang Ekonomi Verawaty Bettyani Sitorus; Sri Wahyuningsih; Memi Nor Hayati
EKSPONENSIAL Vol 8 No 1 (2017)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (429.049 KB)

A present event is probably a reiteration from a past event. The reiteration of an event every particular time period indicates seasonal pattern. Seasonal Autoregressive Integrated Moving Average (SARIMA) is one of the methods that is used for data forecasting which has seasonal pattern. The purposes of this research are finding out the best SARIMA model and forecasting the inflation in Indonesia for period January 2016 until December 2016 using the best SARIMA model. Sample of this research is 96 Indonesia inflation data (mtm) for period January 2008 until December 2015. The technique of this research is purposive sampling. There are five steps of SARIMA method, those are model identification, model estimating, diagnostic checking, selecting the best model, and forecasting. Based on the analysis, the best SARIMA model is SARIMA (1,0,0)(0,1,0)12. The forecasting of Indonesia inflation 2016 has similar pattern with the previous time. The inflation increases in January 2016 and decreases in February 2016 until April 2016. The inflation increases again in Mey 2016 until August 2016 and decreases in September 2016 until November 2016. At last, the inflation increases in December 2016.

Penerapan Analisis Joint-Space dan Analisis Faktor dalam Persepsi Mahasiswa FMIPA UNMUL terhadap Penggunaan Aplikasi Messenger pada Smartphone Emi Harmianti; Ika Purnamasari; Memi Nor Hayati
EKSPONENSIAL Vol 7 No 1 (2016)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (217.243 KB)

Multidimensional Scaling Analysis (MDS) is a technique that can be used to determine the relative views of respondents to an object which is then represented in a multidimensional map. Joint-Space Analysis is a type of MDS that aims to determine the coordinates of the position of each object and variable pictured together on a map perception (perceptual map). While the factor analysis is a branch of multivariate analysis to determine the factors of concern to respondents. This study aims to determine the position of messenger applications on smartphones based on attributes that are owned, as well as to identify factors that concern respondents in choosing the messenger application based on attributes of the messenger application by the respondents are students FMIPA UNMUL. The data used in this research is primary data from research by spreading the questionnaire with the number of respondents (students FMIPA UNMUL) as many as 100 people. Results from this study indicate that the BlackBerry Messenger application, LINE, WhatsApp best position with all superior attributes that exist within the application.While the application KakaoTalk third place with some excellent attributes of the display, application updates, promotions, connection, performance applications, contacts and groups, stickers and emoticons, as well as account settings. Meanwhile, the Yahoo Messenger application and WeChat is the weakest of applications in a variety of attributes that exist in the messenger application. From the results of the factor analysis, found that there are two factors that concern the consumer in choosing a smartphone messenger app that attribute connections and promotion.

Title

Found 10 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 10 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 10 Documents
Search