PERAMALAN INDEKS HARGA SAHAM GABUNGAN (IHSG) MENGGUNAKAN MODEL VAR-TARCH

Bulan Kemalasari, - and Fitriani Agustina, - and Nar Herrhyanto, - (2025) PERAMALAN INDEKS HARGA SAHAM GABUNGAN (IHSG) MENGGUNAKAN MODEL VAR-TARCH. S1 thesis, Universitas Pendidikan Indonesia.

Abstract

Penelitian ini bertujuan untuk melakukan peramalan Indeks Harga Saham Gabungan (IHSG) menggunakan model Vector Autoregressive (VAR) - Threshold Autoregressive Conditional Heteroskedastic (TARCH). Data yang digunakan dalam penelitian ini adalah data harian Indeks Harga Saham Gabungan (IHSG), Harga Emas Berjangka, Harga Minyak Mentah WTI Berjangka, dan Nilai Tukar Dollar AS terhadap Rupiah Indonesia mulai dari bulan Oktober 2021 sampai Oktober 2024. Pemilihan model VAR-TARCH didasarkan pada karakteristik data keuangan yang cenderung fluktuatif dan memiliki efek asimetris. Tahapan analisis pada penelitian ini meliputi uji stasioneritas, analisis VAR, uji white noise, uji ARCH-LM, penaksiran model ARCH/GARCH, uji signifikansi model ARCH/GARCH, uji Sign Bias Test, estimasi parameter TARCH, uji signifikansi TARCH, hingga evaluasi keakuratan peramalan menggunakan nilai MAPE. Hasil penelitian menunjukkan bahwa model VAR(2)-TARCH(1,1) mampu menangkap pola pergerakan IHSG dengan baik, ditunjukkan oleh nilai MAPE dibawah 10% yaitu sebesar 5,7173%. Hasil penelitian ini mengindikasikan bahwa model VAR-TARCH dapat menjadi alat yang efektif untuk melakukan peramalan IHSG.

This study aims to forecast the Indonesia Composite Index (IDX Composite) using the Vector Autoregressive (VAR) - Threshold Autoregressive Conditional Heteroskedastic (TARCH) model. The data used in this research consists of daily data from the Indonesia Composite Index (IDX Composite), Gold Futures Prices, WTI Crude Oil Futures Prices, and the US Dollar to Indonesian Rupiah Exchange Rate from October 2021 to October 2024. The selection of the VAR-TARCH model is based on the characteristics of financial data, which tends to be fluctuative and exhibits laverage effects. There are several stages in this study include stationarity tests, VAR analysis, white noise tests, ARCH-LM tests, ARCH/GARCH model estimation, ARCH/GARCH model significance tests, Sign Bias Tests, TARCH parameter estimation, TARCH significance tests, and forecasting accuracy evaluation using MAPE values. The results show that the VAR(2)-TARCH(1,1) model effectively captures the IDX Composite movement patterns, demonstrated by a MAPE value below 10%, specifically 5.7173%. These findings indicate that the VAR-TARCH model can be an effective tool for forecasting the IDX Composite.

	Text S_MAT_2103177_Title.pdf Download (808kB)
	Text S_MAT_2103177_Chapter1.pdf Download (269kB)
	Text S_MAT_2103177_Chapter2.pdf Restricted to Staf Perpustakaan Download (525kB)
	Text S_MAT_2103177_Chapter3.pdf Download (435kB)
	Text S_MAT_2103177_Chapter4.pdf Restricted to Staf Perpustakaan Download (1MB)
	Text S_MAT_2103177_Chapter5.pdf Download (338kB)
	Text S_MAT_2103177_Appendix.pdf Restricted to Staf Perpustakaan Download (1MB)

Item Type:	Thesis (S1)
Additional Information:	ID SINTA Dosen Pembimbing: Fitriani Agustina: 5981275 Nar Herrhyanto: 6861627
Uncontrolled Keywords:	Peramalan, IHSG, VAR, TARCH Forecasting, IDX Composite, VAR, TARCH
Subjects:	H Social Sciences > HG Finance Q Science > QA Mathematics
Divisions:	Fakultas Pendidikan Matematika dan Ilmu Pengetahuan Alam > Program Studi Matematika - S1 > Program Studi Matematika (non kependidikan)
Depositing User:	Bulan Kemalasari
Date Deposited:	02 May 2025 23:54
Last Modified:	02 May 2025 23:54
URI:	http://repository.upi.edu/id/eprint/132879

Actions (login required)

View Item