Analisis Risiko Saham Subsektor Kesehatan Dengan Mempertimbangkan Faktor Makroekonomi Menggunakan Conditional Value at Risk Berbasis Regresi Kuantil

Dira, Nadia Putri (2026) Analisis Risiko Saham Subsektor Kesehatan Dengan Mempertimbangkan Faktor Makroekonomi Menggunakan Conditional Value at Risk Berbasis Regresi Kuantil. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003221011-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Pandemi COVID-19 menunjukkan pentingnya sektor kesehatan sebagai penopang stabilitas nasional, sehingga analisis risiko saham subsektor kesehatan menjadi semakin relevan mengingat tingginya ketergantungan perusahaan terhadap pendanaan pasar modal dan pengaruh faktor makroekonomi seperti nilai tukar USD/IDR serta harga minyak mentah dunia. Penelitian ini bertujuan mengestimasi risiko ekstrem dan risiko sistemik saham subsektor kesehatan di Indonesia menggunakan Value at Risk (VaR) berbasis Extreme Value Theory (EVT) dan Conditional Value at Risk (CoVaR) berbasis regresi kuantil. Data yang digunakan berupa return harian saham KLBF, MIKA, SILO, dan HEAL, serta data nilai tukar USD/IDR dan harga minyak mentah West Texas Intermediate (WTI) periode 3 Juli 2023-30 Desember 2025. Analisis dilakukan melalui statistika deskriptif, Granger Causality Test, estimasi VaR berbasis EVT-Peaks Over Threshold, serta estimasi CoVaR menggunakan regresi kuantil dengan Backward Elimination. Hasil penelitian menunjukkan bahwa SILO dan HEAL memiliki tingkat risiko yang lebih tinggi dibandingkan KLBF dan MIKA. Uji kausalitas Granger mengindikasikan adanya hubungan kausalitas antara saham subsektor kesehatan dan variabel makroekonomi, dengan KLBF sebagai saham yang menerima pengaruh terbanyak. Estimasi VaR menunjukkan bahwa SILO memiliki risiko ekstrem tertinggi, namun hasil backtesting menunjukkan bahwa model VaR berbasis EVT tidak valid dalam merepresentasikan risiko ekstrem secara konsisten. Sebaliknya, estimasi CoVaR menunjukkan bahwa risiko sistemik saham subsektor kesehatan dipengaruhi oleh keterkaitan antar saham. Model CoVaR hasil Backward Elimination menghasilkan estimasi yang lebih sederhana, akurat, dan valid berdasarkan Proportion of Shortfall dan Kupiec Test. Secara keseluruhan, CoVaR memberikan kinerja yang lebih baik dibandingkan VaR dalam mengukur risiko pada saham subsektor kesehatan.
=======================================================================================================================================
The COVID-19 pandemic highlighted the importance of the healthcare sector as a pillar of national stability, making risk analysis of healthcare subsector stocks increasingly relevant given the sector’s reliance on capital market financing and exposure to macroeconomic factors such as the USD/IDR exchange rate and global crude oil prices. This study aims to estimate extreme risk and systemic risk in Indonesian healthcare subsector stocks using Value at Risk (VaR) based on Extreme Value Theory (EVT) and Conditional Value at Risk (CoVaR) based on quantile regression. The data consist of daily stock returns of KLBF, MIKA, SILO, and HEAL, along with USD/IDR exchange rate and West Texas Intermediate (WTI) crude oil price data from July 3, 2023, to December 30, 2025. The analysis was conducted using descriptive statistics, the Granger Causality Test, EVT-Peaks Over Threshold-based VaR estimation, and CoVaR estimation through quantile regression with Backward Elimination. The results indicate that SILO and HEAL exhibit higher risk levels than KLBF and MIKA. The Granger causality test reveals causal relationships between healthcare subsector stocks and macroeconomic variables, with KLBF being the stock influenced by the largest number of variables. VaR estimation shows that SILO has the highest level of extreme risk; however, backtesting results indicate that the EVT-based VaR model is not valid for consistently representing extreme risk. In contrast, CoVaR estimation demonstrates that systemic risk in healthcare subsector stocks is driven by interconnections among stocks. The CoVaR model obtained through Backward Elimination produces a more parsimonious, accurate, and valid risk estimate based on the Proportion of Shortfall and Kupiec Test. Overall, CoVaR outperforms VaR in measuring risk within the healthcare subsector.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Conditional Value at Risk, Extreme Value Theory, Granger Causality Test, Regresi Kuantil, Value at Risk, Quantile Regression
Subjects:	H Social Sciences > HG Finance > HG4529 Investment analysis H Social Sciences > HG Finance > HG4910 Investments H Social Sciences > HG Finance > HG4915 Stocks--Prices
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Nadia Putri Dira
Date Deposited:	30 Jul 2026 01:59
Last Modified:	30 Jul 2026 01:59
URI:	http://repository.its.ac.id/id/eprint/140254

Actions (login required)

View Item