p-ISSN: 2723-660 e-ISSN: 2745-5254
Vol. 5, No. 11, November 2024 http://jist.publikasiindonesia.id/
Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 11, November 2024 4815
Comparative Analysis of Risk Premium and Stock Market
Returns in Indonesia: A Case Study of Normal and COVID-
19 Pandemic Periods
Peni Rahmadani
1*
, Adler Haymans Manurung
2
Universitas Trisakti, Jakarta, Indonesia
1
Universitas Bhayangkara Jaya, Jakarta, Indonesia
2
Email: [email protected]
1*
, [email protected]
2
*Correspondence
ABSTRACT
Keywords: Risk Premium;
Return Pasar; COVID-19;
GARCH (1,1)
This research examines the effect of market risk premium (risk
premium) on market returns (JCI). In addition, this study aims to
see the effect of premium risk on market returns during the
COVID-19 Pandemic. The data used in this study is secondary
(JCI data and Deposit Interest Rates) for the period January 2010
– September 2023. The method used in this study is the GARCH
method (1.1). The results of this study show a positive and
significant influence of risk premium on market returns (JCI).
During the COVID-19 Pandemic, risk premiums negatively and
significantly affected JCI returns or the Indonesian stock market.
Introduction
Volatility is a measure that describes the degree of variation or fluctuation in a
value, usually in the context of the price of a financial asset such as stocks, bonds, or
currencies. Volatility also reflects changes in the value of stocks, often used to measure
the uncertainty associated with returns. In the financial world, a high level of volatility
indicates excellent risk but also opens up opportunities for high returns (Firmansyah,
2006; Mukmin & Firmansyah, 2020). Understanding asset volatility is critical for
investors aiming to manage portfolios effectively and achieve optimal investment returns.
In addition to volatility, the concept of risk premium is central to financial
decision-making. Risk premium represents the additional compensation investors expect
for taking on higher risks compared to risk-free assets. This metric becomes even more
vital during periods of economic uncertainty, such as the COVID-19 pandemic. In
Indonesia, the pandemic caused unprecedented market volatility, which highlighted the
critical importance of risk premium in guiding investment strategies.
In the financial economy, aggregate stock market volatility is used as an economic
indicator of government policy. Fund managers often consider risk premiums and
volatility when determining asset allocation, using efficient limit estimation (Manurung,
1997). Annin and Dominic (1998) explained that the equity risk premium is an additional
return investors receive as compensation for their willingness to take on higher stock
investments than the average risk.
Peni Rahmadani, Adler Haymans Manurung
Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 11, November 2024 4816
Estimating volatility and analysing its relationship to equity risk premiums has
become the focus of research in the financial sector. The Capital Asset Pricing Model
(CAPM), as expressed by Sharpe (1964), Lintner (1965), and Black (1976), highlights
the positive relationship between risk or volatility and the expected return of a security.
Manurung's (1997) research found a positive relationship between market volatility and
market risk premiums, although the difference was insignificant from zero.
Research on volatility has been widely conducted by previous researchers, such
as Banumathy & Azhagaiah (2015), who examined the stock market in India; Lin (2018),
who examined stock volatility in China using the GARCH model; Nghi & Kieu (2021)
who analysed stocks in Japan and Vietnam, and Yahaya et al. (2023) who investigated
stock volatility in Nigeria (NGX). Meanwhile, research on risk premiums has been
conducted by Morawakage et al. (2019) and Yue et al. (2023)
However, research specifically addressing risk premiums in emerging markets
remains limited. The current study fills this gap by examining the relationship between
market equity premiums and volatility in Indonesia, particularly during the pandemic
period. This focus provides valuable insights into how emerging markets respond to
global crises and informs investment strategies in similar contexts.
Moreover, the urgency to understand the role of risk premiums in Indonesia is
underscored by the need to stabilize financial markets amidst heightened uncertainty.
Risk premiums offer a lens through which investors can evaluate the trade-offs between
potential returns and associated risks. The insights from this study aim to contribute to
more resilient market strategies, enabling stakeholders to navigate both current and future
economic challenges effectively.
In this article, we employ the GARCH (1,1) model to analyze the relationship
between market risk premiums and volatility in the Indonesia Stock Exchange (IDX). By
doing so, the study seeks to provide a comprehensive understanding of how these
variables interact under normal and crisis conditions, with implications for broader
economic resilience and investor confidence.
Methods
This research uses daily closing price data from the Jakarta Composite Stock Price
Index (JCI) listed on the Indonesia Stock Exchange. The index is weighted and includes
all stocks listed on the IDX, with the daily closing price used to calculate the composite
index. The data sample used in this study includes JCI with daily time series data from
January 1, 2010, to December 31, 2023. Stock trading on the regular market is done five
working days a week. Data is collected by downloading daily composite stock price index
price index information from the Yahoo Finance website.
Data
Composite Stock Price Index (JCI)
The Jakarta Composite Stock Price Index (JCI) is an indicator that describes the
movement of stock prices (Gumanti, 2011). The index also functions as an indicator of
market trends, meaning that the movement of the index describes the condition of the
market at a particular time, whether the market is active or sluggish (Mukmin, 2015). JCI
can be calculated by the following formula (Tobing and Manurung 2008)
Comparative Analysis of Risk Premium and Stock Market Returns in Indonesia: A Case Study
of Normal and COVID-19 Pandemic Periods
Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 11, November 2024 4817
In this case:
IHSG
t
= Composite Stock Price Index in the period t.
Q
0, i
= Number of Shares Listed for the ith share in the basis period (0)
P
t, i
= Stock price to 1 in the period t.
P
t-1, i
= Stock price to 1 in the period t-1.
Return of the Composite Stock Price Index (JCI)
Return is the total profit or loss from an investment over time. Monthly returns
are chosen to calculate volatility based on daily data. Market returns are calculated as
follows (Manurung, 1997) :
󰇛

󰇜 (5)
Where:
I
t
= Market indices at the end of the month t
I
t-1
= Pasae index at the end of the month t-1
The natural log is used to determine the continuously combined returns.
Risk Premium
The risk premium is the difference between the market yield and the risk-free
interest rate and is calculated as follows (Manurung, 1997)



(4)
Where,
R
mt
= Stock yield for the period i
R
it
= Risk-free interest rate (3-month term deposit rate at the beginning of the month
t)
= Monthly volatility
The interest rate data is based on the current 3-month deposits from Bank
Indonesia.
Volatility
The calculation of monthly volatility is based on the daily stock returns. The
standard deviation of the sample is employed to quantify historical volatility. The formula
for the standard deviation or volatility, derived from the sample of n observations of the
R (return) variable, is as follows: (Manurung, 1997)
Peni Rahmadani, Adler Haymans Manurung
Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 11, November 2024 4818

󰇛
󰎞󰇜


(6)
Where
Ri
= Stock yield for period i
R = Average stock yield over a period
n = Number of Observations
COVID-19 Pandemic
The COVID-19 pandemic in Indonesia officially began on March 2, 2020, and
ended on June 21, 2023. So, in this study, the COVID-19 pandemic data starts from March
2022 and ends in June 2023 by providing the number 1 for the months of the COVID-19
Pandemic and the number 0 for the months that are not the COVID-19 Pandemic.
ARCH-GARCH
Heteroscedasticity describes the change in volatility over a time horizon. One of
the models to overcome heteroscedasticity is the Generalized Autoregressive Conditional
Heteroscedasticity (GARCH) proposed by Bollerslev (1986)
The ARCH model was initially developed by (Engle, 1982). ARCH Declare under
the random variable Y, taken from the conditional density function 󰇛
󰇜, Then
the estimated value of today depends on past performance, for example, as follows:


(1)
Where,
E(
󰇜 = 0
and variants of
=





(2)
The above equation is called ARCH (q). This reveals that the conditional variance
changes the time siring as a function of past errors, leaving a constant unconditional
variance (W).
Bollerslev (1986) extended the ARCH(q) model to what is called GARCH(p,q).
GARCH (p,q) is formulated as follows:






(3)
This context is a conditional variance that changes over time as a function of past
errors and past conditional variances. (Bollerslev, 1986) notes that
and

must be
positive in the GARCH (1,1) process (to produce that all
Is positive.
Comparative Analysis of Risk Premium and Stock Market Returns in Indonesia: A Case Study
of Normal and COVID-19 Pandemic Periods
Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 11, November 2024 4819
Results and Discussion
Table 1 illustrates the twenty lowest and highest daily rates of return over the
specified sample period. The lowest daily rate of return was observed in September, while
the highest was observed in March. In 2011, JCI experienced a significant correction due
to investor concerns about the potential for debt defaults in European countries, including
Greece, Portugal, and Spain.
Table 1. Twenty Lowest and Highest Daily Returns
From January 2010 to September 2023
Lowest Daily Return (%)
Highest Daily Return (%)
1
22 September 2011
-8,88
10,19
2
09 March 2020
-6,58
7,27
3
03 October 2011
-5,64
4,76
4
19 August 2013
-5,58
4,76
5
19 March 2020
-5,20
4,65
6
12 March 2020
-5,01
4,55
7
10 September 2020
-5,01
4,55
8
17 March 2020
-4,99
4,07
9
23 March 2020
-4,90
4,06
10
05 August 2011
-4,86
3,98
11
19 August 2011
-4,43
3,90
12
16 March 2020
-4,42
3,82
13
09 May 2022
-4,42
3,53
14
10 January 2011
-4,21
3,50
15
11 November 2016
-4,01
3,44
16
24 August 2015
-3,97
3,44
17
04 June 2012
-3,82
3,35
18
05 May 2010
-3,81
3,32
19
05 September 2018
-3,76
3,32
20
27 August 2013
-3,71
3,26
Source: Yahoo Finance, Data processed, 2024
In March 2020, the highest daily returns were recorded on two occasions. This
can be attributed to the policy stimulus implemented by the government and central banks
in response to the global health crisis caused by the COVID-19 pandemic. In monetary
policy, the central bank engages in quantitative easing by purchasing government
securities, which exerts an influence on capital market performance. Furthermore,
government fiscal stimulus in the form of assistance to businesses also contributes to
supporting capital market performance.
Peni Rahmadani, Adler Haymans Manurung
Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 11, November 2024 4820
Figure 1. Composite Stock Price Index 2010 – 2023
Source: Indo Premier Sekuritas, 2024
Figure 1 shows the movement of the Composite Stock Price Index (JCI). It can be
seen that the JCI from 2010 to 2023 shows an upward trend. Although it shows an upward
trend, the JCI has volatility in the short term, which can be seen in several periods of JCI
experiencing weakness or correction quite deeply, especially during the COVID-19
Pandemic period, namely 2020-2021. Then, JCI was able to recover again in the next
period.
Figure 2. Monthly Volatility of the Indonesia Stock Exchange 2010 – 2023
Source: Yahoo Finance, Data processed 2024
Figure 2 illustrates the monthly volatility pattern of daily market returns from
2010 to 2023. The figure depicts a pronounced peak in March 2020, indicating that the
market index exhibited a significant decline and subsequent doubling in that month. After
Comparative Analysis of Risk Premium and Stock Market Returns in Indonesia: A Case Study
of Normal and COVID-19 Pandemic Periods
Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 11, November 2024 4821
March 2020, volatility demonstrated a relatively modest decline, persisting until the
conclusion of the research period in April 2021.
Descriptive Statistics
Table 2 depicts the descriptive statistics of the calculated risk premium for the
Indonesian market and presents the results corresponding to the Jarque-Bera test for
normality.
Table 2. Descriptive Statistics,
Mean
0.11%
Median
-0.34%
Maximum
24.01%
Minimum
-13,54%
Std. Deviasi
5.67%
Skewness
0.663
Kurtosis
4.86
Jarque-Bera
35.77
Probability
0.000
Statistik Uji ADF
-18.675***
Uji ARCH LM F-Stat
55.67***
Note: *** is significant at the 5% level
The mean daily risk premium in Indonesia is positive at 0.11%. The risk premium
in Indonesia suggests a relatively greater degree of unconditional volatility, as indicated
by standard deviations. The Indonesian market (IDX) exhibited positive skewness and
leptokurtosis during the sample period, indicating a departure from the normal
distribution. The Jarque-Bera test also corroborates the presence of an anomalous
stimulus in risk premiums. A notable kurtosis coefficient signifies a leptokurtic risk
premium within the market. Each risk premium evinces stationarity based on the
outcomes of the ADF test in Table 2. Moreover, the ARCH LM test indicates a substantial
heteroscedasticity in the risk premium. Therefore, there is conditional volatility that
fluctuates over time.
Data Stationary Test Results
Before modelling the relationship between risk premium and JCI returns, testing
the stationarity of each variable is necessary. Stationery testing can be carried out using
the Unit Root Test using Augmented Dickey-Fuller (ADF), by using JCI and Risk
Premium Retun data; the ADF test can be seen as follows:
Table 3. Test Augmented Dickey-Fuller (ADF) Data Return IHSG
t-Statistic
Prob.
*
Augmented Dickey-Fuller test statistic
-11.97451
0.0000
Test critical values:
1% level
-3.470427
Peni Rahmadani, Adler Haymans Manurung
Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 11, November 2024 4822
5% level
-2.879045
10% level
-2.576182
Source: Eviews 2010
From the table above, it can be seen that the JCI Return has been stationary at the
level level. The probability value of JCI Return is 0.0000 < 0.05, which is significant to
the real level of 5%.
While the premium risk data shows stationary at the First Difference level, here
is the ADF test on premium risk data:
Table 4. Test Augmented Dickey-Fuller (ADF) Data Risk Premium
t-Statistic
Prob.
*
Augmented Dickey-Fuller test statistic
-6.428832
0.0000
Test critical values:
1% level
-3.470679
5% level
-2.879155
10% level
-2.576241
Source: Eviews 2010
Dari table 4 di atas dapat dilihat bahwasanya data risk premium stasioner pada
first difference, dimana probabilitas risk premium sebesar 0.0000 < 0.05 yang signifikan
terhadap taraf nyata 5%.
GARCH Analysis (1.1)
Before estimating the GARCH model, there is a need to determine whether the
ARCH effect in the risk premium and JCI return characterizes the series. (Engle, 1982)
has introduced the concept that variance depends on the square of the error of the period
left by one period. The volatility of the data indicates that the estimated results are affected
by the symptoms of the ARCH effect. The following are the results of the JCI risk
premium and return heteroscedasticity test:
Table 5. ARCH Heteroscedasticity Test
Heteroskedasticity Test: ARCH
F-statistic
0.002019
Prob. F(1,161)
0.9642
Obs*R-Squared
0.002045
Prob. Chi-Square (1)
0,9639
Source: Eviews 2010
Using the ARCH LM Test, Prob was obtained. With a Chi-Square of 0.9639 >
0.05 at a confidence level of 5%, it can be said that the model does not have an ARCH
effect. Thus, the GARCH model estimation (1,1) can be used.
There is no ARCH effect after the JCI return data and risk premium are stationary
and the GARCH model (1,1). The GARCH (1,1) model can already be interpreted. The
following is a table of the results of the GARCH (1.1) model for JCI return data and risk
premium for the 2010-2023 period:
Comparative Analysis of Risk Premium and Stock Market Returns in Indonesia: A Case Study
of Normal and COVID-19 Pandemic Periods
Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 11, November 2024 4823
Table 6. GARCH Model Results (1.1) JCI Return Data and Premium Risk
Variable
Coefficient
Std. Error
z-Statistic
Prob.
C
0.004263
0.003036
1.403898
0.1603
D(RISK_PREMIUM)
0.038322
0.014643
2.616993
0.0089
(PANDEMI)
-0.080907
0.014014
-5.773494
0.0000
Variance Equation
C
8.16E-05
5.84E-05
1.396608
0.1625
RESID (-1)^2
0.063108
0.037987
1.661326
0.0966
GARCH (-1)
0.864729
0.062818
13.76555
0.0000
R-squared
0.118688
Mean dependent var
0.006798
Adjusted R-squared
0.107740
S.D. dependent var
0.040312
S.E. of regression
0.038079
Akaike info criterion
-3.724669
Sum squared resid
0.233449
Schwarz criterion
-3.611260
Log-likelihood
311.4229
Hannan-Quinn critter.
-3.678629
Durbin-Watson stat
1.906381
Source: Eviews 2010
Table 5 shows the GARCH model (1.1) with an R-squared of 0.118688 and an
AIC of -3.724669. The table shows that the risk premium variable has a positive and
significant effect on the JCI return with a coefficient of 0.038322 and a prob of 0.0089 <
0.05 with a confidence level of 5%. Meanwhile, the effect of the risk premium during the
COVID-19 pandemic on JCI returns had a negative and significant effect with a
coefficient of -0.080907 and a prob of 0.0000 < 0.05 with a confidence level of 5%. This
research aligns with several studies on the influence of premium risk on market returns.
(Banumathy & Azhagaiah, 2015) on the stock market in India (Lin, 2018) testing stock
volatility in China (Nghi & Kieu, 2021) on Japanese and Vietnamese stocks, Prameswari
and Manurung (2024) on the Indonesian stock market and (Ahmed Yahaya et al., 2023)
investigate on the volatility of stocks in Nigeria (NGX). Meanwhile, research on risk
premiums was carried out by (Morawakage et al., 2019) and (Yue et al., 2023).
Conclusion
This study aims to determine the effect of premium risk on market returns (JCI) and
also to examine how the effect of premium risk on JCI returns during the COVID-19
Pandemic. The method used in this study is GARCH (1,1). Based on the study's results,
there is a positive and significant influence between risk premium and JCI return with a
coefficient of 0.038322 and a prob of 0.0089 < 0.05 with a confidence level of 5%.
Meanwhile, during the Pandemic, the risk premium had a negative and significant effect
on the JCI return of -0.080907 and the prob of 0.0000 < 0.05 with a confidence level of
5%.
The following suggestion is that further research needs to be conducted to examine
the relationship between risk premium and JCI return by adding other variables that
influence JCI returns. Then, it is necessary to do the same using methods different from
Peni Rahmadani, Adler Haymans Manurung
Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 11, November 2024 4824
the author's. The researcher should compare several methods to see the influence of
various methods on the relationship between risk premium and JCI return.
Bibliography
Ahmed Yahaya, Stephen Alaba John, Ademola Adegoroye, & Oluwatosin Ayotomide
Olorunfemi. (2023). Stock market liquidity and volatility on the Nigerian Exchange
Limited (NGX). World Journal of Advanced Research and Reviews, 20(3), 147–156.
https://doi.org/10.30574/wjarr.2023.20.3.2333
Annin, M., & Dominic, F. (1998). Equity Risk Premium Article. IL: Ibbotson Associates.
Ibbotson Associates.
Banumathy, K., & Azhagaiah, R. (2015). Modelling Stock Market Volatility: Evidence
from India. Managing Global Transitions, 13(1), 27–42.
Black, F. (1976). Studies of Stock Price Volatility Changes. In Meeting of The Business
And Economic Statistics Section, 177–181. In Proceedings of the 1976 Meeting of
the Business and Economic Statistics Section (pp. 177–181). American Statistical
Association.
Bollerslev, et. al. (1986). ARCH Modelling in Finance: A Review of the Theory and
Empirical Evidence. Journal of Econometrics, 52, 5–59.
Engle, R. F. (1982). Autoregressive Conditional Heteroscedasticity with Estimates of the
Variance of United Kingdom Inflation,. Econometrica, 50(4), 987–1007.
Firmansyah. (2006). Analisis Volatilitas Harga Kopi Internasional. Usahawan.
IDX. (2020). Market Review 2020: Pandemic and Capital Market Resilience. Indonesia
Stock Exchange.
Lin, Z. (2018). Modelling and forecasting the stock market volatility of SSE Composite
Index using GARCH models. Future Generation Computer Systems, 79, 960–972.
https://doi.org/10.1016/j.future.2017.08.033
Manurung, A. H. (1997). Risk Premium And Volatility On The Jakarta Stock Exchange.
Morawakage, P. S., Nimal, P. D., & Kuruppuarachchi, D. (2019). Equity Risk Premium
Puzzle: Evidence from Indonesia and Sri Lanka. Bulletin of Indonesian Economic
Studies, 55(2), 239–248. https://doi.org/10.1080/00074918.2018.1529406
Mukmin, A., & Firmansyah, F. (2020). Analisis Perbandingan Volatilitas Indeks Harga
Saham IHSG dan JII. Jurnal Ekonomi Dan Perbankan Syariah, 3(1), 69–84.
https://doi.org/10.46899/jeps.v3i1.155
Comparative Analysis of Risk Premium and Stock Market Returns in Indonesia: A Case Study
of Normal and COVID-19 Pandemic Periods
Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 11, November 2024 4825
Nghi, L. D., & Kieu, N. M. (2021). Volatility spillover from the united states and japanese
stock markets to the vietnamese stock market: A frequency domain approach.
Panoeconomicus, 68(1), 35–52. https://doi.org/10.2298/PAN170428003N
Prameswari, S., & Manurung, A. H. (2024). Risk Premium and Volatility Analysis on
Indonesia Stock Exchange. Jurnal Indonesia Sosial Teknologi, 5(4), 1798–1805.
https://doi.org/10.59141/jist.v5i4.1035
Sharpe, W. F. (1964). Capital Asset Prices: A Theory of Market Equilibrium Under
Conditions of Risk. The Journal of Finance, 19(3), 425–442.
https://doi.org/10.1111/j.1540-6261.1964.tb02865.x
Yue, T., Ruan, X., Gehricke, S., & Zhang, J. E. (2023). The volatility index and volatility
risk premium in China. Quarterly Review of Economics and Finance, 91(May), 40–
55. https://doi.org/10.1016/j.qref.2023.07.004