Abstract
Autoregressive Integrated Moving Average is a model that commonly used to model time series data. One model that can be modeled is Moving Average (MA). In this study, the estimation of parameters was performed to produce the model estimator parameter, where if the order component of the MA model is known, then the methods that can be used are the Ordinary Least Square (OLS) method, Moment method, and Maximum Likelihood method. But in fact, there are often assumption deviations when using the OLS method, one of which occurs heteroscedasticity (variant is not constant) which is produce a poor estimator. This study used both Moment and Maximum Likelihood method in estimating the parameter of the 1st Moving Average model, denoted by MA (1). The result showed that MA (1) parameter model using Moment method gave better result than Maximum Likelihood method. This can be seen from the value of Schwartz Bayesian Criterion (SBC) of both Moment and Maximum Likelihood method parameter estimator with magnified amount of data and various parameters values generated.References
- Aswi dan Sukarna (2006). Analisis Deret Waktu. Makasar: Andira Publisher.
- Kirchgassner, G., dan Jurgen W. (2007) Introduction to Modern Time Series Analysis. Berlin: Springer-Verlag.
- Rodliyah, I. (2016). Perbandingan Metode Bootstrap dan Jackknife dalam Mengestimasi Parameter Regresi Linier Berganda, Jurnal Matematika dan Pendidikan Matematika, Vol 1, No 1, 77.
- Makridakis, S., Steven C., dan Wheelwrigth, V. (1999) Metode dan Aplikasi Peramalan Edisi Kedua. Terjemahan Andriyanto, Sus, U., dan Basith, A., Jakarta: Erlangga.
- Wei, W.W.S. (2006) Time Series Analysis Univariate and Multivariate Methods. California: Addison-Wesley Publishing Company.
- Yamin, M. (2015) Peramalan Pola Data Musiman dengan Model Winter’s dan ARIMA., Vol 11, No 1, 73.
- Bain L.J., dan Engelhardt, M. (1992) Introduction to Probability and Mathematical Statistics. California: Duxbury Press