To install StudyMoose App tap and then “Add to Home Screen”
Save to my list
Remove from my list
To estimate the conditional market volatility based on the financial market using an appropriate multiple linear regression model.
Specific Objectives:
Hypotheses:
This research is focused largely on secondary data obtained from the database held by the developing and developed countries. The details are taken from the websites of the stock exchanges and from blogs such as www.yahoofinance.com. The analysis analyzes the daily stock price return results for the above duration from Bangladesh, China, India, the United Kingdom and the United States of America. Wherever details are incomplete, the previous day and next day estimates are taken. The report analyzed the stock indexes of developing and emerging countries over a three-month period.
Verified writer
Proficient in: Science
4.7 (348)
“ Amazing as always, gave her a week to finish a big assignment and came through way ahead of time. ”
The calculated daytime closing value was used. Regular stock market returns (Rt) based on individual indices of emerging and developing countries is determined by the change in the logarithmic gap in stock indices of emerging and developed countries i.e.
R_t=ln(I_t/I_(t-1) )× 100
Whereas, I_t and I_(t-1) are the closing value of daily emerging and developed countries stock indices at the time “t” and “t-1” respectively. I_t is the present indices value and I_(t-1) is the previous day’s indices value.
The following tools and techniques have been used to test the hypotheses:
Unit Root Test:
To verify whether the series is stationary or not, the Augmented Dickey-Fuller unit root test was applied to analyze the stationarity of the research time series and to determine the order of integration between them.
The ADF unit root test was carried out by estimating regression:
∆Yt = α0 + α1 Yt-1 + ∑ γj ∆Yt-j + εt
The ADF unit root test unit is based on the null hypothesis H0: Yt isn't I (0). If the ADF figures measured are less than the critical value otherwise the null hypothesis will be rejected; otherwise accepted. The stationarity of the data is tested through the Augmented Dickey-Fuller (ADF) method to prevent spurious regression. Maximum Akaike Data Criteria are used to assess lag counts.
Analysis of regression is a group of mathematical techniques used to approximate relations between a dependent variable and one or more independent variables.
Multiple linear regressions:
Y = a+β1X1+β2X2+β3X3+β4X4+β5X5+β6X6+β7X7+β8X8+β9X9+β10X10+β11X11+u
Where:
Y = COVID-19 infected cases worldwide.
a = the intercept.
β = the slope.
X1 = DSE Returns
X2 = CSE Returns
X3 = NSE Returns
X4 = BSE Returns
X5 = S&P 500 Returns
X6 = SSE Returns
X7 = NASDAQ Returns
X8 = FTAS Returns
X9 = Crude Oil Returns
X10 = Gold Returns
X11 = Silver Returns
u = the regression residual.
It can be used to determine the strength of the relationship between variables and to model their future relationship.
The estimate of the Augmented Dickey-Fuller test (ADF): To test whether or not a given time series is stationary, we conduct an indirect test of the presence of a unit base. Augmented Dickey-Fuller (ADF), and Kwiatkowski – Phillips – Schmidt – Shin (KPSS) are the two common unit root measures. The ADF method uses a deterministic (and squared) pattern, enabling a pattern-stationary cycle to take place.
Unit Root Test for stock indices of emerging and developed countries
| Sr | Country | Indices | ADF Test Statistics Z(t) | 1% | 5% | 10% | p-value |
|---|---|---|---|---|---|---|---|
| 01 | Bangladesh | DSEX | -9.747 | -3.524 | -2.898 | -2.584 | 0.0000 |
| 01 | Bangladesh | CSEX | -7.512 | -3.524 | -2.898 | -2.584 | 0.0000 |
| 02 | India | CNX Nifty | -9.474 | -3.524 | -2.898 | -2.584 | 0.0000 |
| 02 | India | BSE Sensex | -9.385 | -3.524 | -2.898 | -2.584 | 0.0000 |
| 03 | USA | S&P 500 | -6.548 | -3.524 | -2.898 | -2.584 | 0.0000 |
| 03 | USA | NASDAQ | -6.641 | -3.524 | -2.898 | -2.584 | 0.0000 |
| 04 | UK | FTAS | -6.736 | -3.524 | -2.898 | -2.584 | 0.0000 |
| 05 | China | SSE Composite | -6.120 | -3.524 | -2.898 | -2.584 | 0.0000 |
The findings demonstrate that the unit-root is not present in all indices stages. In all indices cases the conditional p-value for Z(t) = 0.0000. Therefore, the null hypothesis of the presence of unit root is denied at the level suggesting stationary in data meaning equity stock indices of Bangladesh, India, China, UK, and USA are incorporated at the level only as we have taken Log natural returns of each index. The null hypothesis for the ADF test is; the data has a unit root. The calculated ADF statistics for Dhaka stock return (-9.747), Chittagong stock return (-7.512), National stock return (-9.474), Bombay stock return (-9.385), USA stock exchange (-6.548), New York stock exchange (-6.641), London stock exchange (-6.736) and Shanghai stock exchange (-6.120), which all are less than the critical value (-3.524, -2.898 and -2.584) at 1%, 5% and 10 %, respectively) therefore, the null hypotheses H01is rejected.
Regression analysis is a type of statistics that is inferential. The p-values help to determine if the interactions you find in your study are also present in the larger population. For each independent variable, the p-value measures the null hypothesis that there is no association between the variable and the dependent variable. If there is no correlation, the changes in the independent variable and the differences in the dependent variable are not related. In other words, inadequate data exist to suggest there is influence at the population level.
If the p-value for a statistic is smaller than the degree of importance, the results should provide adequate proof for the whole population to dismiss the null hypothesis. Changes in the independent variable are correlated with changes in population-level reaction. This attribute is statistically important, and therefore a helpful contribution to the model of regression. On the other hand, a p-value that is higher than the point of significance suggests that the study provides inadequate data to assume that a non-zero correlation occurs.
The regression coefficient sign indicates that a positive or negative correlation for each independent variable exists within the dependent variable. A positive correlation means that the mean of the dependent variable always tends to increase, as the average of the independent variable decreases. A negative coefficient suggests that the dependent variable tends to diminish as the independent variable increases.
The coefficient value means how much the mean of the dependent variable in the independent variable changes, provided a one-unit change while other variables are held steady in the model. This property of stabilizing the other variables is important because it allows you to evaluate the effect of each variable in isolation from the others.
This is the standard variance of the regression equation's error rate. The interval of confidence for mean can be built using the experimental mean and normal error. For instance, it's the set of values from which the mean will be by taking another typical selection of tests.
Degrees of Freedom (DF) suggest the degrees of freedom associated with variance sources. The full variance has N -1 degrees of freedom. A review of results contains a selection of tests for vintage wines in the data set. The instances are separate bits of information that can be used for parameter or uncertainty calculations. Each factor is measured (coefficient) costs one degree of freedom; the remainder is used for volatility estimation.
R-squared is a proportion of the level of vulnerability characterized by relapse. It is a number somewhere in the range of zero and one, and poor example is shown by the close to zero worth. Expanding extra autonomous variable in a numerous relapse will build the R-squared, without improving the genuine match. An adjusted R-squared is calculated, representing a more accurate comparison with multiple independent variables. The updated R-squared tests both the number of observations and the number of autonomous variables.
Because the pandemic causes both aggregate supply and demand shocks, it is very difficult to tackle the impacts using conventional macroeconomic instruments (Baldwin and di Mauro, 2020). Economists and policymakers believe that governments ought to step up a mix of well-targeted, serious, and new kinds of fiscal and monetary policy behavior that the world probably has never seen before (Letzing, 2020, March 18; OECD, 2020; Baldwin & di Mauro, 2020). In this sense, Baldwin & di Mauro (2020) outlines a number of tailored fiscal and monetary initiatives for businesses, families, hospitals, public trust, and finance and banking that can be adopted at the national level and by international cooperation (e.g., G7 level).
The biggest obstacle in reacting to the pandemic is that the situation is entirely fresh, unparalleled, and the king of the modern, and not like a global crisis caused by established factors like the banking crisis or the financial crisis. The conventional method will not fit correctly, because it is special this time. Consequently, any policy steps to be taken in response to this crisis must be crafted taking into account the following main attributes:
Measures ought to be 'comprehensive' or as point by point as they can be instead of focusing on one explicit monetary substance, activity or territory. Measures need to be driven by ingenuity, as existing approaches will not be as successful as they need to be for certain countries (e.g. addressing pandemics under oversight in national health care systems).
To fight with a globalized pandemic, for example, COVID-19 that no country can handle all alone, cross-outskirt activities, for example, worldwide (e.g., Asia, Latin America), financial combination (e.g., EU, African Economic Union), and exchanging system (e.g., BRICS, NAFTA) or other association (e.g., G20, SAARC) rates must be facilitated;
By default, poor and most emerging countries have a weak economic environment with poor health infrastructure; supranational organizations such as the World Bank need to implement special economic and health programs and packages to help them recover during the pandemic and the post- era, and to order to help poor and developing economies survive the crisis, developed countries and international organizations such as the World Bank and the IMF may consider revising their current and potential funding requirements to reduce the external debt burden on the economies.
The present study analyzed the relationship between stock returns volatility of emerging and developed countries and the impact of COVID-19 including the world's recent financial crisis. COVID-19 puts economies at risk- matter how big or small, whether existing or emerging. The conclusion of the pandemic remains unknown as of today. The confusion is causing a worldwide loss of public trust. If consumer and producer confidence is lost and a powerful demand shock coupled with massive supply-side supports cannot be implemented in a timely manner, the macroeconomic impacts in any economy will likely worsen across economies. The results illustrate the growing influence of old market news and long-lasting memory.
This clearly shows the influence of the global financial crisis on emerging markets and improves stock returns except for mild effects on Bangladesh, Chinese, India, UK and US stock markets where stock market volatility has been influenced by the global crisis very little. In the event of a global financial crisis, the Indian stock market has taken some time to respond, which shows that the Indian economy appears to be exempt from this recession that could be due to the stringent banking sectors. This research has led to some significant consequences for politics. Our results indicated that emerging and developed countries 'volatility in stock market returns has been dramatically impacted over the entire period. Such results have significant consequences for investors looking to diversify their portfolios. For Foreign Institutional Investors (FIIs), and Domestic Institutional Investors (DIIs), this study may be important.
The fact that FIIs come for short-term returns is well known. They are drawn to a market with a high degree of volatility or FIIs are involved in causing uncertainty because the FIIs do not achieve any high return without uncertainty or speculations. The outcome will help the DIIs and the MFs evaluate the FIIs movement and its effect on emerging and developed countries' Indices and prepare their strategies as needed. It was seen when FIIs start buying up their stocks, DIIs and Mutual Funds. That means DIIs are investing in a falling market, trying to take advantage of the volatility of stock prices. Hence, uncertainty can be preserved in order to tone down the negative effects of FII withdrawal. In the present sense, recovery from the disease is key and financial crisis secondary. Nevertheless, as proof of economic adversities arises, it will be prudent to start planning and implementing constructive and disruptive policy measures from now on with a long-term outlook to avoid the looming.
Impact of COVID-19 on Market Volatility: A Regression Analysis. (2024, Feb 17). Retrieved from https://studymoose.com/document/impact-of-covid-19-on-market-volatility-a-regression-analysis
👋 Hi! I’m your smart assistant Amy!
Don’t know where to start? Type your requirements and I’ll connect you to an academic expert within 3 minutes.
get help with your assignment
