Herni Utami
Department of Mathematics Gadjah Mada University, Indonesia

Published : 7 Documents
Articles

Found 7 Documents
Search

THE EFFECT OF THE NUMBER OF INTERVALS TO THE SENSITIVITY AT ANALYSIS OF DIFFERENTIAL ITEM FUNCTIONING USING MANTEL-HAENSZEL’S CHI-SQUARE PROCEDURE Utami, Herni; Hidayati, Kana
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 4, No 2 (2004)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

At analysis of item bayes or called with differential item functioning (DIF) using the Mantel-Haenszel’s Chi–squareprocedure, the students in a group is grouped pursuant to their reached score, in a certain interval. This research is aimed atrevealing the effect of the number of interval to the sensitivitas at DIF analysis using the Mantel-Haenszel’s Chi-Squareprocedure. Data used at this research is the responses of students of the third grade of SLTPN in Yogyakarta to UAN in2002 / 2003 academic year. Analysis DIFin this research is conducted by making 3, 4, 5, 6, 7, 8, and 9 intervals in students’group pursuant to their reached score using Mantel-Haenszel‘s Chi-Square procedure. The result of this research showedthat the number of intervals causes the differencies of the number of items load DIF significantly in every interval, and itcauses the differencies of sensitivity in the DIF detection; and making 4 intervals in group of students is the most sensitiveway in the DIF detection using Mantel-Haenszel methods, than others.
ANALISIS REGRESI TERPOTONG Utami, Herni
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 4, No 2 (2004)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

Analisis regresi terpotong merupakan pengembangan dari analisis regresi klasik dengan menambah konstanta pemotongtertentu. Misalkan variabel random y menyatakan variabel dependen/respon dan x1, x2 , ... xp merupakan variabelindependen, maka model regresi klasik adalah y = x¢b + e dengan asumsi e ~ N(0,s2). Akibatnya y juga berdistribusiNormal dengan mean E(y | x) = x¢b dan variansi s2. Selanjutnya jika harga y > a maka diperoleh regresi terpotong denganmean E(y | y > a) = x¢b + sl dan variansi var(y) = s2[1 - s] dengan l = f (a) / F (a), a = ( x¢b - a)/s, dan d = l(l-a)(Greene, 1997) [?].
Forecasting electricity load demand using hybrid exponential smoothing-artificial neural network model Sulandari, Winita; Subanar, Subanar; Suhartono, Suhartono; Utami, Herni
International Journal of Advances in Intelligent Informatics Vol 2, No 3 (2016): November 2016
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (530.21 KB) | DOI: 10.26555/ijain.v2i3.69

Abstract

Short-term electricity load demand forecast is a vital requirements for power systems. This research considers the combination of exponential smoothing for double seasonal patterns and neural network model. The linear version of Holt-Winter method is extended to accommodate a second seasonal component. In this work, the Fourier with time varying coefficient is presented as a means of seasonal extraction. The methodological contribution of this paper is to demonstrate how these methods can be adapted to model the time series data with multiple seasonal pattern, correlated non stationary error and nonlinearity components together. The proposed hybrid model is started by implementing exponential smoothing state space model to obtain the level, trend, seasonal and irregular components and then use them as inputs of neural network. Forecasts of future values are then can be obtained by using the hybrid model. The forecast performance was characterized by root mean square error and mean absolute percentage error. The proposed hybrid model is applied to two real load series that are energy consumption in Bawen substation and in Java-Bali area. Comparing with other existing models, results show that the proposed hybrid model generate the most accurate forecast
ANALISIS REGRESI TERPOTONG Utami, Herni
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 4, No 2 (2004)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Analisis regresi terpotong merupakan pengembangan dari analisis regresi klasik dengan menambah konstanta pemotongtertentu. Misalkan variabel random y menyatakan variabel dependen/respon dan x1, x2 , ... xp merupakan variabelindependen, maka model regresi klasik adalah y = x¢b + e dengan asumsi e ~ N(0,s2). Akibatnya y juga berdistribusiNormal dengan mean E(y | x) = x¢b dan variansi s2. Selanjutnya jika harga y > a maka diperoleh regresi terpotong denganmean E(y | y > a) = x¢b + sl dan variansi var(y) = s2[1 - s] dengan l = f (a) / F (a), a = ( x¢b - a)/s, dan d = l(l-a)(Greene, 1997) [?].
PERAMALAN NILAI TUKAR DOLAR AMERIKA TERHADAP INDONESIA DENGAN MODEL MAXIMAL OVERLAP DISCRETE WAVELET TRANSFORM-AUTOREGRESSIVE MOVING AVERAGE Farima, Vega Zayu; Utami, Herni
Jurnal Statistika Universitas Muhammadiyah Semarang Vol 6, No 1 (2018): Jurnal Statistika
Publisher : Program Studi Statistika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Muham

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (211.467 KB)

Abstract

Beberapa permasalahan dalam kehidupan sehari-hari perlu untuk diramalkan sebelum diambil keputusan. Nilai tukar mata uang asing yang mempengaruhi kurs Indonesia seperti nilai tukar dolar Amerika sangat perlu diramalkan untuk jangka waktu tertentu. Data kurs memiliki volatilitas yang sangat tinggi dan cenderung tidak stasioner. Transformasi wavelet mampu merepresentasikan informasi waktu dan frekuensi secara bersamaan sehingga dapat digunakan untuk menganalisis data-data nonstasioner. MODWT-ARMA yaitu model hibrid dari Maximal Overlap Discrete Wavelet Transform (MODWT) dan Autoregressive Moving Average (ARMA) yang berhubungan dengan data runtun waktu nonstasioner. Secara teori, nilai detail yang diperoleh dari dekomposisi MODWT adalah stasioner. Hal ini menyebabkan hasil dekomposisi dapat diramalan dengan ARMA. Pada peramalan nilai tukar dolar Amerika terhadap rupiah, diperoleh pemodelan yang fitted dengan data training dan diperoleh nilai MAPE yang kecil yaitu 0.82%. Hal ini mengindikasikan bahwa model gabungan ini efektif untuk menambah keakuratan peramalan.  Kata kunci : Peramalan, Data Runtun Waktu, Dekomposisi, MODWT-ARMA, MAPE.
SECOND ORDER LEAST SQUARE ESTIMATION ON ARCH(1) MODEL WITH BOX-COX TRANSFORMED DEPENDENT VARIABLE Utami, Herni; -, Subanar
Journal of the Indonesian Mathematical Society Volume 19 Number 2 (October 2013)
Publisher : IndoMS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22342/jims.19.2.166.99-110

Abstract

Box-Cox transformation is often used to reduce heterogeneity and to achieve a symmetric distribution of response variable. In this paper, we estimate the parameters of Box-Cox transformed ARCH(1) model using second-order leastsquare method and then we study the consistency and asymptotic normality for second-order least square (SLS) estimators. The SLS estimation was introduced byWang (2003, 2004) to estimate the parameters of nonlinear regression models with independent and identically distributed errors.DOI : http://dx.doi.org/10.22342/jims.19.2.166.99-110
Estimating the function of oscillatory components in SSA-based forecasting model Sulandari, Winita; Subanar, Subanar; Suhartono, Suhartono; Utami, Herni; Lee, Muhammad Hisyam
International Journal of Advances in Intelligent Informatics Vol 5, No 1 (2019): March 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1676.6 KB) | DOI: 10.26555/ijain.v5i1.312

Abstract

The study of SSA-based forecasting model is always interesting due to its capability in modeling trend and multiple seasonal time series. The aim of this study is to propose an iterative ordinary least square (OLS) for estimating the oscillatory with time-varying amplitude model that usually found in SSA decomposition. We compare the results with those obtained by nonlinear least square based on Levenberg Marquardt (NLM) method. A simulation study based on the time series data which has a linear amplitude modulated sinusoid component is conducted to investigate the error of estimated parameters of the model obtained by the proposed method. A real data series was also considered for the application example. The results show that in terms of forecasting accuracy, the SSA-based model where the oscillatory components are obtained by iterative OLS is nearly the same with that is obtained by the NLM method.