Penerapan Model Generalized Space Time Autoregressive with Exogenous Variable (GSTARX) pada Peramalan Harga Cabai Rawit Merah di Pulau Jawa

Puspitasari, Mumpuni Dwi (2025) Penerapan Model Generalized Space Time Autoregressive with Exogenous Variable (GSTARX) pada Peramalan Harga Cabai Rawit Merah di Pulau Jawa. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5002211105-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (4MB) | Request a copy

Abstract

Cabai rawit merah merupakan salah satu komoditas hortikultura dengan harga yang sangat fluktuatif di Indonesia, terutama di Pulau Jawa. Harga cabai rawit merah yang fluktuatif ini seringkali dipengaruhi oleh tingginya permintaan cabai terutama menjelang hari-hari besar keagamaan, oleh karena itu diperlukan adanya pendekatan kuantitatif dalam menganalisis data harga cabai rawit merah di Pulau Jawa. Pada analisis multivariate time series spasial-temporal, data tidak hanya berhubungan dengan waktu sebelumnya, tetapi juga berhubungan dengan lokasi lainnya. Salah satu model multivariate time series spasial-temporal yaitu Generalized Space Time Autoregressive (GSTAR). Penelitian ini menerapkan model GSTAR dengan penambahan variabel eksogen berupa variasi kalender (GSTARX) untuk memodelkan dan meramalkan data harga cabai rawit merah pada empat provinsi di Pulau Jawa dengan estimasi yang digunakan adalah Ordinary Least Square (OLS) serta menggunakan bobot lokasi seragam. Hasil penelitian menunjukkan bahwa model GSTARX(1_1)-OLS dengan semua parameter merupakan model terbaik dengan nilai RMSE sebesar 14518 dan MAPE sebesar 15.45%. Hasil peramalan pada data harga cabai rawit merah menunjukkan fluktuasi yang tidak terlalu signifikan dan terdapat kenaikan harga cabai rawit merah pada bulan terjadinya Hari Raya Idul Fitri dan Hari Raya Natal di semua lokasi.
===============================================================================================================================
Red cayenne pepper is one of the horticultural commodities with very fluctuating prices in Indonesia, especially in Java Island. The fluctuating price of red cayenne pepper is often influenced by the high demand for chili, especially around religious holidays, therefore a quantitative approach is needed in analyzing red cayenne pepper price data in Java Island. In the spatial-temporal multivariate time series analysis, data is not only related to the previous time, but also related to other locations. One of the spatial-temporal multivariate time series models is Generalized Space Time Autoregressive (GSTAR). This study applies the GSTAR model with the addition of exogenous variables in the form of calendar variations (GSTARX) to model and predict red cayenne pepper price data in four provinces in Java with the estimation used is Ordinary Least Square (OLS) and uses uniform location weights. The results of the analysis show that the GSTARX(1_1)-OLS model with all parameters is the best model with RMSE value of 14518 and MAPE of 15.45%. The forecasting results on the red cayenne pepper price data show that fluctuations are not too significant and there is an increase in the price of red cayenne pepper in the months of Eid al-Fitr and Christmas in all locations.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	GSTAR, Variabel Eksogen, Harga Cabai Rawit Merah. GSTAR, Exogenous Variable, Red Cayenne Pepper Price
Subjects:	H Social Sciences > HA Statistics > HA30.3 Time-series analysis Q Science > QA Mathematics Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA280 Box-Jenkins forecasting Q Science > QA Mathematics > QA278 Cluster Analysis. Multivariate analysis. Correspondence analysis (Statistics)
Divisions:	Faculty of Mathematics and Science > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Mumpuni Dwi Puspitasari
Date Deposited:	01 Aug 2025 06:04
Last Modified:	01 Aug 2025 06:04
URI:	http://repository.its.ac.id/id/eprint/124769

Actions (login required)

View Item