This Author published in this journals
All Journal MATEMATIKA
Warsito Budi
Unknown Affiliation

Published : 2 Documents
Articles

Found 2 Documents
Search

UJI LINEARITAS DATA TIME SERIES DENGAN RESET TEST Budi, Warsito; Ispriyanti, Dwi
MATEMATIKA Vol 7, No 3 (2004): JURNAL MATEMATIKA
Publisher : MATEMATIKA

Show Abstract | Original Source | Check in Google Scholar | Full PDF (54.272 KB)

Abstract

  Tulisan ini membahas prosedur pengujian linearitas data time series menggunakan uji RESET test versi Ramsey dan Lagrange Multiplier. Uji yang digunakan adalah uji yang telah diperbaiki dengan pembentukan komponen utama dari bentuk polinomial pada persamaan uji. Prosedur uji kemudian diterapkan pada data simulasi untuk model linear AR(2), AR(2) dengan outlier dan model nonlinear  LSTAR(2) dengan n = 200. Pengujian menunjukkan hasil yang mirip diantara kedua uji dimana data simulasi dari model linear tidak menjamin kelinearan, sedangkan data simulasi model nonlinear secara signifikan berbentuk nonlinear pada taraf 5%.  
PENENTUAN UNIT HIDDEN OPTIMAL PADA MODEL NEURAL NETWORK DENGAN ANALISIS KONTRIBUSI INCREMENTAL SEL Budi, Warsito
MATEMATIKA Vol 2, No 8 (2005): JURNAL MATEMATIKA
Publisher : MATEMATIKA

Show Abstract | Original Source | Check in Google Scholar | Full PDF (70.871 KB)

Abstract

This paper discusses about choosing the optimal number of hidden units at neural network models which is applied to the Composite Stock Price Index data in Surabaya Stock Exchange. One of the problem in fitting NN models is  an NN model which fits well may give poor out-of-sample forecasts. Thus it is required traditional methods such as ACF and PACF to select a good NN model, e.g. to select appropiate lagged variables as the ‘inputs’. The Incremental Contribution of Cells methods which belong to the general-to-specific procedure is used to choose the optimal number of hidden units. The size and topology of networks is selected by reducing the size of the network through the use of kuadratic correlation coefficients and graphical analysis of network output for every  hidden layer cell. The resulted of NN model is compared with models with different architecture those obtain from the Box-Jenkins methods. The Akaike’s Information Criterion and Schwartz Bayesian Criterion are used for comparing different models.