Alvita Rachma Devi
Unknown Affiliation

Published : 4 Documents
Articles

Found 4 Documents
Search

ANALISIS DATA INFLASI INDONESIA MENGGUNAKAN METODE FOURIER DAN WAVELET MULTISCALE AUTOREGRESIVE Suparti, Suparti; Santoso, Rukun; Prahutama, Alan; Yasin, Hasbi; Devi, Alvita Rachma
Seminar Nasional Variansi (Venue Artikulasi-Riset, Inovasi, Resonansi-Teori, dan Aplikasi Statistika) 2018: Tahun 2018
Publisher : Seminar Nasional Variansi (Venue Artikulasi-Riset, Inovasi, Resonansi-Teori, dan Aplikasi Statistika)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (884.754 KB)

Abstract

Analisis regresi merupakan metode statistika untuk mengetahui hubungan antara variabel prediktor dan variabel respon. Pendekatan regresi dapat dilakukan dengan  pendekatan parametrik dan nonparametrik. Pendekatan parametrik ketat dengan asumsi dan harus dipenuhi untuk mendapatkan model yang baik. Sementara pendekatan nonparametrik tidak ketat dengan asumsi karena metode tersebut didasarkan pada pendekatan kurva yang tidak diketahui bentuknya. Pendekatan nonparametrik dapat dilakukan dengan beberapa pendekatan diantaranya metode Fourier dan Wavelet. Metode Fourier merupakan metode yang didasarkan pada deret cosinus atau sinus. Metode Fourier sangat sesuai untuk data yang mengalami pola berulang atau stasioner. Sedangkan pada pemodelan wavelet tidak hanya terbatas pada data berulang atau stasioner saja, akan tetapi juga mampu memodelkan data yang tidak stasioner. Pada penelitian ini dimodelkan nilai Inflasi di Indonesia dari Januari 2007 sampai Agustus 2017.  Variabel responnya adalah nilai inflasi, sedangkan variabel prediktornya adalah waktu. Metode Fourier dengan K=100 menghasilkan MSE sebesar 0,846216 dan R2 sebesar 80,12%. Model Wavelet menggunakan Multiscale Autoregresive dengan filter Haar, J=4 dan Aj = 2  mempunyai MSE sebesar 0,312 dengan R2  sebesar  96,91%.  Pada model Fourier dengan K=100 diperlukan parameter sebanyak 102 buah sedangkan model wavelet dengan J=4 dan Aj = 2 hanya diperlukan parameter sebanyak 10 buah. Jadi model wavelet sangat efisien dengan kinerja yang lebih bagus dibandingkan dengan model Fourier. Kata Kunci: Inflasi, nonparametrik, Fourier, Wavelet, MSE
ANALISIS INFLASI KOTA SEMARANG MENGGUNAKAN METODE REGRESI NON PARAMETRIK B-SPLINE Devi, Alvita Rachma; Mukid, Moch. Abdul; Yasin, Hasbi
Jurnal Gaussian Vol 3, No 2 (2014): Wisuda Periode April 2014
Publisher : Jurusan Statistika UNDIP

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (386.933 KB)

Abstract

Inflation is an important consideration for investors to invest in an area. An accurate prediction of inflation is required for investors in conducting a careful planning.  One of  the method to find the predicted value of inflation is by using B-Spline regression, a nonparametric regression which is not depend on certain assumptions, thus providing greater flexibility. The optimal B-Spline models rely on the optimal knots that has a minimum Generalized Cross Validation (GCV). By using Semarang year-on-year inflation data from January 2008 - August 2013, the optimal B-spline models in this study are on the order of 2 ( linear ) with 2 knots, that is 5,99 and 6,09. Prediction of Semarang inflation in 2014 fluctuated around the number five and six and inflation in the end of 2014 is 6,286394%.
ANALISIS INFLASI KOTA SEMARANG MENGGUNAKAN METODE REGRESI NON PARAMETRIK B-SPLINE Devi, Alvita Rachma; Mukid, Moch. Abdul; Yasin, Hasbi
Jurnal Gaussian Vol 3, No 2 (2014): Wisuda Periode April 2014
Publisher : Departemen Statistika FSM Undip

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (386.933 KB)

Abstract

Inflation is an important consideration for investors to invest in an area. An accurate prediction of inflation is required for investors in conducting a careful planning.  One of  the method to find the predicted value of inflation is by using B-Spline regression, a nonparametric regression which is not depend on certain assumptions, thus providing greater flexibility. The optimal B-Spline models rely on the optimal knots that has a minimum Generalized Cross Validation (GCV). By using Semarang year-on-year inflation data from January 2008 - August 2013, the optimal B-spline models in this study are on the order of 2 ( linear ) with 2 knots, that is 5,99 and 6,09. Prediction of Semarang inflation in 2014 fluctuated around the number five and six and inflation in the end of 2014 is 6,286394%.
APPLICATION OF NON PARAMETRIC BASIS SPLINE (BSPLINE) IN TEMPERATURE FORECASTING Caraka, Rezzy Eko; Devi, Alvita Rachma
Jurnal Statistika Universitas Muhammadiyah Semarang Vol 4, No 2 (2016): Jurnal Statistika
Publisher : Program Studi Statistika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Muham

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

Abstract

Weather is important but hard to predictlay people and scientists alike will agree. The complexity of system limits the knowledge about it and therefore its predictability even over a few days. It is complex because many variables within the Earthsatmosphere, such as temperature and they do so nonlinearly. B-spline as a basis for one-dimensional regression and we extend this paper by using B-spline to construct a basis for bivariate regression. This construction gives a basis in two dimensions with local support and hence a fully flexible family of fitted mortality surfaces one of the principal motivations behind the use of B-spline as the basis of regression is that it doesnot suffer from the lack of stability that can so bedevil ordinary polynomial regression. The essential difference is that B-spline have local non-zero support in contrast to the polynomial basis for standard regression. The optimal B-Spline models rely on theoptimal knots that has a minimum Generalized Cross Validation (GCV)Keywords: Temperature, B-Spline, Generalized Cross Validation, non-parametric