Analisis Volatilitas Dan Value At Risk Return Indeks Harga Saham Gabungan Dengan Model Garch-Midas

Pristia, Eva Octa (2023) Analisis Volatilitas Dan Value At Risk Return Indeks Harga Saham Gabungan Dengan Model Garch-Midas. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 06111940000022-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (15MB) | Request a copy

Abstract

Investasi banyak macamnya, namun investasi saham merupakan investasi yang paling populer dikalangan masyarakat dikarenakan sangat praktis dan fleksibel. Pergerakan saham dipengaruhi oleh 2 faktor, yaitu internal return stock market dan eksternal (makroekonomi). Penelitian ini menggunakan model GARCH-MIDAS karena GARCH-MIDAS dapat menghubungkan pengamatan variabel frekuensi tinggi return stock market dengan variabel frekuensi rendah (makroekonomi). Tujuan dari penelitian ini adalah untuk meramalkan volatilitas return IHSG dengan model GARCH-MIDAS, menghitung akurasi peramalan volatilitas return IHSG dengan MSE dan MAE, serta menghitung nilai risiko investasi saham di Indonesia berdasarkan return IHSG dengan VaR. Estimasi parameter pada model GARCH-MIDAS dilakukan dengan MLE. Berdasarkan analisis yang sudah dilakukan menunjukkan bahwa variabel effective federal fund rate memiliki pengaruh yang paling signifikan terhadap volatilitas return IHSG dibandingkan variabel BI interest rate, customer price index dan inflation rate. Hal tersebut ditinjau dari Keakuratan volatilitas return IHSG berdasarkan nilai MSE dan MAE varibel EFFR sebesar 0,003320 dan 0,009280 yang mana memiliki nilai paling kecil diantara variabel makroekonomi lainnya, oleh karena itu model terbaik yang digunakan untuk mengestimasi volatilitas return IHSG adalah dengan menggunakan EFFR sebagai variabel makroekonomi. Sehingga nilai VaR dengan dengan tingkat kepercayaan 99% sebesar 2,7% dan nilai VaR dengan tingkat kepercayaan 95% sebesar 1,9%.
==================================================================================================================================
There are many kinds of investments, but stock investment is the most popular investment among the public because it is very practical and flexible. The movement of stocks is influenced by 2 factors, namely internal (stock market) and external (macroeconomic). This study uses the GARCH-MIDAS model because GARCH-MIDAS can correlate observations of high-frequency return stock market variables with low-frequency variables (macroeconomics). The purpose of this study is to predict IHSG return volatility using the GARCH-MIDAS model, calculate the accuracy of IHSG return volatility forecasting with MSE and MAE, and calculate the risk value of stock investment in Indonesia based on IHSG return with VaR. Parameter estimation in the GARCH-MIDAS model was carried out using MLE. Based on the analysis that has been done, it shows that the variable effective federal fund rate has the most significant influence on the volatility of the IHSG return compared to the BI variables interest rate, customer price index and inflation rate. This is reviewed from the accuracy of the IHSG return volatility based on the MSE and MAE values of the EFFR variables of 0.003320 and 0.009280 which have the smallest value among other macroeconomic variables, therefore the best model used to estimate volatility IHSG return is by using EFFR as a macroeconomic variable. So that the VaR with a 99% confidence level is 22.55% and the VaR value with a 95% confidence level is 15.98%.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Volatilitas, Return, GARCH-MIDAS, MSE, MAE, VaR, MLE, Volatility
Subjects:	Q Science > QA Mathematics Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Eva Octa Pristia
Date Deposited:	02 Aug 2023 08:33
Last Modified:	02 Aug 2023 08:33
URI:	http://repository.its.ac.id/id/eprint/100692

Actions (login required)

View Item