Date of submission: April 11, 2022; date of acceptance: November 21, 2022. * Contact information: nisarg@nisargjoshi.com, Institute of Management, Nir- ma University Ahmedabad – 382481, Gujarat, India, phone: 9723500052; ORCID ID: https://orcid.org/0000-0002-2417-4158. Copernican Journal of Finance & Accounting e-ISSN 2300-3065 p-ISSN 2300-12402022, volume 11, issue 4 Joshi, N.A. (2022). Impact of COVID-19 on Performance on Indian Stock Indices: A Study for NSE Composite and Sectoral Indices. Copernican Journal of Finance & Accounting, 11(4), 125–146. http://dx.doi.org/10.12775/CJFA.2022.022 nisarG a. joshi* Nirma University impact of covid-19 on performance on indian stock indices: a study for nse composite and sectoral indices Keywords: COVID-19, volatility, index returns, NSE, sectoral indices, post-COVID-19 J E L Classification: C32, C41, F21, G01, G11. Abstract: Purpose/Objective: The objective of the paper was to scrutinize the impact of COVID-19 on the performance of composite and sectoral indices of National Stock Exchange (NSE) of India. Methodology and Approach: The study included sample daily closing prices from July 2019 to December 2020 for two composite indices and nine sectoral indices of NSE. The sample was divided into three sub-samples to check the impact before, during and after (after the lockdown was lifted) the pandemic on the volatility of returns. The vola- tility measures were regressed using a dummy variable for COVID-19. Findings: The results showed that there was an increase in the volatility of re- turns of the indices during COVID-19 as compared to post-lockdown period. It was also found that the skewness of returns of the indices have become more negative in the post-COVID-19 (post-lockdown) period. Practical Implications/Conclusion: The findings of the study have significant impli- cations and impacts regarding the decision making for equity analysts, portfolio man- agement firms, investors and traders for assessing their investment in a better way and http://dx.doi.org/10.12775/CJFA.2022.022 Nisarg A. Joshi126126 deciding their investments. The author believed that these results would magnify the volatility relations.  Introduction Introduction The stock prices have plunged significantly due to COVID-19, which has led to unexpected downward pressure on global indices like never before. In this context, there are recent and relevant studies which had studied the effect of COVID-19 on performance of stock indices, volatility, stability of stock indices etc., which were supported by other empirical studies. Such signal of panic trad- ing and augmented volatility in various markets across the globe was recog- nized by certain studies such as Al-Awadhi, Al-Saifi, Al-Awadhi and Alhamadi, 2020; Baker, Bloom, Davis, Kost, Sammon and Viratyosin, 2020; Kartal, Depren and Kılıç Depren, 2020; Phan and Narayan, 2020; Harif, Aloui, and Yarovaya, 2020. Baker et al. (2020) estimated that the way the market was showing the volatility during the month of March; 2020 would be much greater than the his- torical crisis such as Black Monday triggered by DJIA decline of 22% in one day in 1987 or the monetary crisis at the global level which was prompted by sub- prime crisis of 2008 or the Great Depression of 1930. This was experienced by the Indian stock indices as the NSE and BSE paused the trading amid trigger- ing the lower circuit threshold of 10% twice in two weeks during March 2020. The Indian stock market started having major shocks in the first quarter of the year 2020 prejudiced by the global meltdown and COVID-19 which was cen- tered in China initially. The first crash in Indian market was seen on February 1, 2020 when Nifty crashed by 3% and Sensex crashed by 2% in one day. This was just the beginning as the stock market crash risk became significant amid WHO’s announcement of COVID-19 as a potential epidemic. In the last week of February 2020, both Sensex and Nifty plunged for entire week resulted in the worst weekly fall in more than a decade. The stock market crash became severe in the month of March when in the first week of March markets went down by 1,000 points. On March 9, 2020, Sensex went down by 1,941.67 points and Nif- ty went down by 538 points amid the havoc created by COVID-19 outbreak. On 12th March, WHO acknowledged COVID-19 as universal epidemic and Sensex closed at 33 months low and crashed by 8.18% and Nifty crashed by 8.30%. During the next week, Sensex plunged continuously for 4 trading days where the highest single day crash was 8%. The biggest crash in one day in the Indi- an markets was seen next week when COVID-19 led to lockdown in India along imPaCt of Covid-19 on PErformanCE on indian stoCK indiCEs… 127127 with other countries and the markets crashed in the fear of recession where Sensex crashed by 13.15% and Nifty reduced by 12.98%. Mazur, Dang and Vega (2020) studied the crash of stock market amid COVID-19 and found a signifi- cant volatility. This paper emphasizes the impact of COVID-19 on performance of stock in- dices in India. This study quantifies the performance of Indian stock indices by measuring the volatility of index returns. The purpose of the study is to aug- ment the argument of response of the stock market to unforeseen events for as- sessing the risk and making the decisions. This study tries to focus on checking the variables used for predicting the performance of the stock indices such as standard deviation, skewness and kurtosis. For last couple of years, many researchers have worked on checking the ef- fects of coronavirus on different factors like economic performance, liberal policies announced by the government, health sector, tourism and hospitality, migration and contrary, stock indices etc. Most of the studies done on the stock markets have used composite indices of the markets and majorly from the eco- nomically advanced economies. There are also a few studies available which have worked on the similar line for the developing economies using the com- posite indices but there is very little work done on all the sectoral indices pre- sent in a particular market. There was one study done in the context of Indian market, which has used pre-COVID-19 and during-COVID-19 period for their event study (Chaudhary, Bakhshi & Gupta, 2020). This study focuses on study- ing the impact of COVID-19 on Indian market using the composite index along with the sectoral indices. Literature ReviewLiterature Review Stock market returns are affected by major events happening in a country as well as in the world and these returns are the true mirror of the economic situ- ation of any country. Previous studies show the impact of news on the stock re- turns (Li, 2018). Pendell and Cho (2013) studied the impact of foot-and-mouth disease outbreaks on the performance of stock returns. Al-Awadhi et al. (2020) found that the number of cases and deaths due to COVID-19 resulted in negative returns in the stock listed in China. Loh (2006) studied the impact of another pandemic of SARS on the aviation sector stocks of various countries and found that aviation sector was more sen- Nisarg A. Joshi128128 sitive to the information of pandemic as compared to other industries. These results were reinforced by another study by (Chen, Jang & Kim, 2007; Brown & Smith, 2008) who concluded that along with aviation sector, other industries like hotels, tourism, FMCG, etc. also had a significant negative impact caused by SARS. Wang and Kutan (2013) concluded that there was a significant posi- tive return of the stock of biotechnology and pharmaceutical companies of Tai- wan amid pandemic. In this line, another study was conducted by Del Giudice and Paltrinieri (2017) with respect to another pandemic in the African region named Ebola and its impact on stock returns. Nageri (2019) studied the volatility persistence of stock returns for Nigeri- an stock index during pre- and post-sub-prime crisis using GARCH model with three error distribution and found that the volatility in the Nigerian market was low before the sub-prime crisis and was very high after sub-prime crisis. He also concluded that the traders who short their positions to make abnormal profits by spreading rumors should be monitored, regulated and restricted to avoid high volatility persistence. Fernandes (2020) stated that the COVID-19 pandemic could not be com- pared with previous epidemic as it made a more severe impact on economies of the globe and were not restricted to specific region or economies of the world. COVID-19 had a massive impact on the stock indices across the world like never before because along with the downfall in the economic activities, other factors like investor sentimentality, fear, uncertainty, etc. also affected the markets negatively. The global stock markets were affected by COVID-19 in the most dangerous manner as compared to other pandemics in the history of mankind (Goodell, 2020; Okorie & Lin, 2021; David, Inácio & Tenreiro Machado, 2021). Asian markets were affected more by COVID-19 as compared to developing indices in the European region (Topcu & Gulal, 2020). The impact of COVID-19 in India was far more severe as compared to other economic events such as demon- etization of the year 2016 or the implementation of Goods and Services Tax in the later year (Mishra & Mishra, 2020). There were numerous studies conducted in the recent past to how the stock markets have responded to COVID-19 based on various samples like regions, developing economies, most affected econo- mies, etc. (Zaremba, Kizys, Aharon & Demir, 2020; Siddiqui, Ahmed & Naushad, 2020; Okorie & Lin, 2020; Ali, Alam & Rizvi, 2020; Izzeldin, Muradoğlu, Pappas & Sivaprasad, 2021; Aslam, Ferreira, Mughal & Bashir, 2021). Liu, Manzoor, Wang, Zhang and Manzoor (2020) used event study to check the effect of COVID-19 on the stock returns of the economies which were affect- imPaCt of Covid-19 on PErformanCE on indian stoCK indiCEs… 129129 ed the most by the pandemic and found that the stock indices reacted negative- ly to the outbreak of the pandemic which resulted in a fall in the returns. In the same line, Mishra and Mishra (2020) studied effect of COVID-19 on the Asian economies neighboring China using the same method and found the results which were consistent with Liu et al. (2020). Singh, Dhall, Narang and Rawat (2020) used an event study with panel regression to check the stock market re- sponses amid COVID-19. International financial markets became unpredictable and the risk has also elevated due to unprecedented pandemic situations (Zhang, Hu & Ji, 2020). Ac- cording to Albulescu (2020), the volatility index of China and other countries nearby and estimated that the volatility in the market will increase with in- crease in the spread of COVID-19. Ahmar and Val (2020) studied the short-run impact of coronavirus on Spain’s stock market index and found that SutteARI- MA was a better method to estimate the effect of COVID-19 on the index. MethodsMethods Data SamplingData Sampling The market returns were obtained from the official website of National Stock Exchange by taking the daily closing prices of two composite indices of the Ex- change, namely Nifty 50 and Nifty 500 and nine sectoral indices, i.e., Bank Nif- ty, Nifty Auto, Nifty Realty, Nifty Financial Services, Nifty FMCG, Nifty IT, Nifty Media, Nifty Metal and Nifty Pharma. The closing prices were taken for the pe- riod from January 1, 2019 to December 31, 2020 and from July 2019 to Decem- ber 2020. Table 1 shows the descriptive statistics for the entire sample separat- ed into three sub-samples for the pre-COVID-19 period (July 2019 to December 2019), during COVID-19 lockdown period (January 2020 to June 2020) and post-COVID-19 lockdown period (July 2020 to December 2020). MethodologyMethodology Daily returns of the composite indices and the sectoral indices were calculated using the natural logarithm of the daily price changes. The daily returns were calculated using the following equation where Rt is the return on index, Pt is the price on index, and Pt-1 is the price on index at the end of the previous day. Nisarg A. Joshi130130 resulted as a fall in the returns. In the same line, Mishra and Mishra (2020) studied effect of Covid-19 on the Asian economies neighboring China using the same method and found the results which were consistent with Liu et al. (2020). Singh, Dhall, Narang and Rawat (2020) used an event study with panel regression to check the stock market responses amid Covid-19. International financial markets became unpredictable and the risk has also elevated due to unprecedented pandemic situations (Zhang, Hu & Ji, 2020). According to Albulescu (2020), the volatility index of China and other countries nearby and estimated that the volatility in the market will increase with increase in the spread of Covid-19. Ahmar and Val (2020) studied the short-run impact of coronavirus on Spain stock market index and found that SutteARIMA was a better method to estimate the effect of Covid-19 on the index. Methods Data Sampling The market returns were obtained from the official website of National Stock Exchange by taking the daily closing prices of two composite indices of the Exchange namely Nifty 50 and Nifty 500 and nine sectoral indices, i.e., Bank Nifty, Nifty Auto, Nifty Realty, Nifty Financial Services, Nifty FMCG, Nifty IT, Nifty Media, Nifty Metal and Nifty Pharma. The closing prices were taken for the period from January 1, 2019 to December 31, 2020.from July 2019 to December 2020. Table – 1 shows the descriptive statistics for the entire sample separated in to three sub-samples for the pre-covid period (July – 2019 to December – 2019), during-covid lockdown period (January -2020 to June – 2020) and post-covid lockdown period (July – 2020 to December – 2020). Methodology Daily returns of the composite indices and the sectoral indices were calculated using the natural logarithm of the daily price changes. The daily returns were calculated using the following equation where, Rt is the return on index, Pt is the price on index, and Pt-1 is the price on index at the end of previous day. 𝑅𝑅� � ��� 𝑃𝑃�� 𝑃𝑃�,���� A regression framework was developed to examine the impact of COVID-19 on volatility of the index returns. The regression framework was constructed to measure the impact using different measures of variability such as stand- ard deviation (SD), skewness (SKEW) and kurtosis (KUR). For this purpose, COVID-19 was added as a dummy variable in the equation as a binary variable with ‘0’ for the pre-COVID-19 period and ‘1’ for the during COVID-19 (lockdown period) and post-COVID-19 (post-lockdown) period. For the purpose of the study, post-lockdown period was considered as post-COVID-19 period. Though the pandemic did not end in India in June 2020, once the lockdown was lifted and the phase of wise unlock was implemented by the government, the eco- nomic activities restarted and the impact of the removal of restrictions on the volatility was investigated as post-COVID-19 period. The analysis was done in two parts to check the impact of COV ID -19 on the performance of the Indian indices. The first regression analysis was done for the period before COVID-19 (July 2019 to December 2019) and during COVID-19 lockdown (January 2020 to June 2020). The second regression analysis was done for the period before COVID-19 (July 2019 to December 2019) and for the period after COVID-19 lock- down was lifted (July 2020 to December 2020). The impact of COVID-19 on volatility of returns is captured by a variety of factors such as increase in number of COVID-19 positive cases, increase in number of deaths due to COVID-19, the impact of the interaction between number of cases and deaths, increase in number of cases and deaths global- ly, etc. These factors will lead to change in the investors’ mentality regarding investment during the pandemic. The investors will be hesitant to invest in the capital markets which will lead to increase in fear of index/volatility in- dex. Such fear will in turn lead to increased volatility in the market and will result in the market crash due to such pandemic. The objective of the paper is to measure such impact of COVID-19 on variability of returns by taking a bi- nary dummy variable as mentioned above. In the first part of the regression analysis, the impact of COVID-19 on volatility of the index returns was meas- ured as the combined effect of β0 + β1 as the impact of COVID-19 was cap- tured by the dummy variable shown as β1. Similarly, the impact of removal of lockdown (post-COVID period) on volatility of index returns was captured by imPaCt of Covid-19 on PErformanCE on indian stoCK indiCEs… 131131 β0 + β1 as the impact of post-COVID-19 period was captured by the dummy variable shown as β1. This study was conducted using the regression framework under the as- sumptions of Generalized Least Squares (GLS) method rather than OLS regres- sion considering heteroscedasticity and autocorrelation of the data. For the purpose of this analysis, all the dependent variables were calculated using the rolling data for one month. These models had taken SD, SKEW and KUR as the dependent variables for each composite and sectoral index in the sample and the impact of COVID-19 was checked using a binary dummy variable. The value of dummy variable was considered as ‘0’ for the period prior to the pandemic (July 2019 to December 2019) and was considered ‘1’ for the period during the pandemic (January 2020 to June 2020) and after the lockdown was lifted (July 2020 to December 2020). heteroscedasticity and autocorrelation of the data. For the purpose of this analysis, all the dependent variables were calculated using the rolling data for one month. These models had taken SD, SKEW and KUR as the dependent variables for each composite and sectoral index in the sample and the impact of covid-19 was checked using a binary dummy variable. The value of dummy variable was considered as ‘0’ for the period prior to the pandemic (July – 2019 to December – 2019) and was considered ‘1’ for the period during the pandemic (January – 2020 to June – 2020) and after the lockdown was lifted (July – 2020 to December – 2020). 𝑆𝑆𝑆𝑆� � �� � ��𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝑆𝑆� � 𝜀𝜀� Where SDt was the standard deviation for the index at time t, and Covid-19 was a dummy variable equal ‘0’ for the period before covid and 1 for the period during and after Covid-19 lockdown (i.e., from January 2020 to June 2020, and from July 2020 to December 2020) and 𝜀𝜀� is the error term at time t. 𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆� � �� � ��𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝑆𝑆� � 𝜀𝜀� Where SKEWt was the skewness for the index at time t, and Covid-19 was a dummy variable equal ‘0’ for the period before covid and 1 for the period during and after Covid-19 lockdown (i.e., from January 2020 to June 2020, and from July 2020 to December 2020) and 𝜀𝜀� is the error term at time t. 𝑆𝑆𝐾𝐾𝐾𝐾� � �� � ��𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝑆𝑆� � 𝜀𝜀� Where KURt was the kurtosis for the index at time t, and Covid-19 was a dummy variable equal ‘0’ for the period before covid and 1 for the period during and after Covid-19 lockdown (i.e., from January 2020 to June 2020, and from July 2020 to December 2020) and 𝜀𝜀� is the error term at time t. Results and Discussion The results of the descriptive statistics are shown in next three tables. The descriptive statistics have been shown for three periods, before the pandemic (July – December 2019) and during the pandemic lockdown (January – June 2020) and after the pandemic lockdown (July 2020 – December 2020) after keeping in mind for comparable time-frame for the sub-samples. The mean returns of the pre-covid period and post-covid period (post lockdown) were found to be positive for all indices whereas the mean returns were negative for the covid period except the Where SDt was the standard deviation for the index at time t, and COVID-19 was a dummy variable equal ‘0’ for the period before COVID-19 and 1 for the period during and after COVID-19 lockdown (i.e., from January 2020 to June 2020, and from July 2020 to December 2020) and εt is the error term at time t. heteroscedasticity and autocorrelation of the data. For the purpose of this analysis, all the dependent variables were calculated using the rolling data for one month. These models had taken SD, SKEW and KUR as the dependent variables for each composite and sectoral index in the sample and the impact of covid-19 was checked using a binary dummy variable. The value of dummy variable was considered as ‘0’ for the period prior to the pandemic (July – 2019 to December – 2019) and was considered ‘1’ for the period during the pandemic (January – 2020 to June – 2020) and after the lockdown was lifted (July – 2020 to December – 2020). 𝑆𝑆𝑆𝑆� � �� � ��𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝑆𝑆� � 𝜀𝜀� Where SDt was the standard deviation for the index at time t, and Covid-19 was a dummy variable equal ‘0’ for the period before covid and 1 for the period during and after Covid-19 lockdown (i.e., from January 2020 to June 2020, and from July 2020 to December 2020) and 𝜀𝜀� is the error term at time t. 𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆� � �� � ��𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝑆𝑆� � 𝜀𝜀� Where SKEWt was the skewness for the index at time t, and Covid-19 was a dummy variable equal ‘0’ for the period before covid and 1 for the period during and after Covid-19 lockdown (i.e., from January 2020 to June 2020, and from July 2020 to December 2020) and 𝜀𝜀� is the error term at time t. 𝑆𝑆𝐾𝐾𝐾𝐾� � �� � ��𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝑆𝑆� � 𝜀𝜀� Where KURt was the kurtosis for the index at time t, and Covid-19 was a dummy variable equal ‘0’ for the period before covid and 1 for the period during and after Covid-19 lockdown (i.e., from January 2020 to June 2020, and from July 2020 to December 2020) and 𝜀𝜀� is the error term at time t. Results and Discussion The results of the descriptive statistics are shown in next three tables. The descriptive statistics have been shown for three periods, before the pandemic (July – December 2019) and during the pandemic lockdown (January – June 2020) and after the pandemic lockdown (July 2020 – December 2020) after keeping in mind for comparable time-frame for the sub-samples. The mean returns of the pre-covid period and post-covid period (post lockdown) were found to be positive for all indices whereas the mean returns were negative for the covid period except the Where SKEWt was the skewness for the index at time t, and COVID-19 was a dummy variable equal ‘0’ for the period before COVID-19 and 1 for the period during and after COVID-19 lockdown (i.e., from January 2020 to June 2020, and from July 2020 to December 2020) and εt is the error term at time t. heteroscedasticity and autocorrelation of the data. For the purpose of this analysis, all the dependent variables were calculated using the rolling data for one month. These models had taken SD, SKEW and KUR as the dependent variables for each composite and sectoral index in the sample and the impact of covid-19 was checked using a binary dummy variable. The value of dummy variable was considered as ‘0’ for the period prior to the pandemic (July – 2019 to December – 2019) and was considered ‘1’ for the period during the pandemic (January – 2020 to June – 2020) and after the lockdown was lifted (July – 2020 to December – 2020). 𝑆𝑆𝑆𝑆� � �� � ��𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝑆𝑆� � 𝜀𝜀� Where SDt was the standard deviation for the index at time t, and Covid-19 was a dummy variable equal ‘0’ for the period before covid and 1 for the period during and after Covid-19 lockdown (i.e., from January 2020 to June 2020, and from July 2020 to December 2020) and 𝜀𝜀� is the error term at time t. 𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆� � �� � ��𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝑆𝑆� � 𝜀𝜀� Where SKEWt was the skewness for the index at time t, and Covid-19 was a dummy variable equal ‘0’ for the period before covid and 1 for the period during and after Covid-19 lockdown (i.e., from January 2020 to June 2020, and from July 2020 to December 2020) and 𝜀𝜀� is the error term at time t. 𝑆𝑆𝐾𝐾𝐾𝐾� � �� � ��𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝑆𝑆� � 𝜀𝜀� Where KURt was the kurtosis for the index at time t, and Covid-19 was a dummy variable equal ‘0’ for the period before covid and 1 for the period during and after Covid-19 lockdown (i.e., from January 2020 to June 2020, and from July 2020 to December 2020) and 𝜀𝜀� is the error term at time t. Results and Discussion The results of the descriptive statistics are shown in next three tables. The descriptive statistics have been shown for three periods, before the pandemic (July – December 2019) and during the pandemic lockdown (January – June 2020) and after the pandemic lockdown (July 2020 – December 2020) after keeping in mind for comparable time-frame for the sub-samples. The mean returns of the pre-covid period and post-covid period (post lockdown) were found to be positive for all indices whereas the mean returns were negative for the covid period except the Where KURt was the kurtosis for the index at time t, and COVID-19 was a dum- my variable equal ‘0’ for the period before COVID-19 and 1 for the period during and after COVID-19 lockdown (i.e., from January 2020 to June 2020, and from July 2020 to December 2020) and εt is the error term at time t. Nisarg A. Joshi132132 Results and DiscussionResults and Discussion The results of the descriptive statistics are shown in next three tables. The de- scriptive statistics have been shown for three periods, before the pandemic (July 2019 – December 2019) and during the pandemic lockdown (January 2020 – June 2020) and after the pandemic lockdown (July 2020 – December 2020) af- ter keeping in mind a comparable time-frame for the sub-samples. The mean returns of the pre-COVID-19 period and post-COVID-19 period (post-lockdown) were found to be positive for all indices whereas the mean returns were neg- ative for the COVID-19 period except the returns of the pharma sector index which were found to be positive during the COVID-19 period. The mean returns of indices in the pre-COVID-19 period were found to be positive except four sec- toral indices like information technology sector, media, metal and pharmaceu- tical sector. Three out of these four sectors’ returns plunged further during the COVID-19 period majorly after the lockdown was imposed by the government and all other indices’ returns were also turned into negative except pharma which performed well due to pandemic. Once the lockdown was lifted and the economy had started gaining its momentum, all the indices have shown posi- tive returns in the period of July to December 2020. The market was found to be more volatile during the COVID-19 period. The standard deviation of returns was very high during the COVID-19 period due to investor sentimentality towards fear due to pandemic and the supply pressure in the market. The highest volatility was found in sectoral indices like banks, financial services, metal sector and realty sector as compared to composite in- dices. The volatility in the post-COVID-19 period was similar to the volatility experienced by the indices in the time period before COVID-19. imPaCt of Covid-19 on PErformanCE on indian stoCK indiCEs… 133133 T ab le 1 . D es cr ip ti ve S ta ti st ic s fo r Pr e- CO V ID P er io d (J ul y 20 19 – D ec em be r 20 19 ) N if ty 5 0 N if ty 5 00 B an k N if ty N if ty A ut o N if ty R ea lt y N if ty Fi n. S er . N if ty FM CG N if ty IT N if ty M ed ia N if ty M et al N if ty Ph ar m a M ea n 0. 00 03 0. 00 02 0. 00 02 0. 00 03 0. 00 04 0. 00 06 0. 00 02 -0 .0 00 2 -0 .0 01 0 -0 .0 00 5 -2 .5 E- 05 M ed ia n 0. 00 08 0. 00 12 0. 00 08 -0 .0 01 2 0. 00 19 0. 00 11 -0 .0 00 1 0. 00 06 -0 .0 01 0 -0 .0 01 1 -3 .7 E- 05 M ax 0. 05 18 0. 05 15 0. 07 98 0. 09 44 0. 04 05 0. 06 90 0. 04 31 0. 02 81 0. 07 44 0. 05 52 0. 03 21 M in -0 .0 21 6 -0 .0 21 9 -0 .0 28 0 -0 .0 40 2 -0 .0 63 6 -0 .0 30 2 -0 .0 19 7 -0 .0 47 9 -0 .0 46 3 -0 .0 38 2 -0 .0 34 0 St d. D ev . 0. 00 94 0. 00 94 0. 01 46 0. 01 76 0. 01 63 0. 01 33 0. 00 88 0. 01 06 0. 01 99 0. 01 85 0. 01 15 Sk ew ne ss 1. 29 44 1. 21 27 1. 47 82 1. 03 48 -0 .5 57 2 1. 34 46 1. 56 02 -0 .7 97 9 0. 26 65 0. 16 46 -0 .0 11 4 Ku rt os is 9. 60 65 9. 48 84 10 .1 31 8. 78 63 4. 52 94 9. 88 53 10 .2 88 5. 73 46 4. 01 00 2. 68 31 3. 04 07 JB S ta ti st ic 25 8. 03 24 5. 91 30 5. 45 19 3. 54 18 .3 5 28 0. 03 32 2. 17 51 .3 7 6. 68 51 1. 07 04 0. 01 11 Pr ob . 0. 00 00 0. 00 00 0. 00 00 0. 00 00 0. 00 01 0. 00 00 0. 00 00 0. 00 00 0. 03 53 0. 58 55 0. 99 44 Su m 0. 03 17 0. 02 19 0. 03 34 0. 03 96 0. 04 71 0. 07 12 0. 01 92 -0 .0 17 9 -0 .1 23 0 -0 .0 61 9 -0 .0 03 1 Su m S q. D ev . 0. 01 08 0. 01 07 0. 02 62 0. 03 78 0. 03 25 0. 02 15 0. 00 94 0. 01 39 0. 04 84 0. 04 19 0. 01 61 O bs . 12 3 12 3 12 3 12 3 12 3 12 3 12 3 12 3 12 3 12 3 12 3 S o u r c e : a ut ho r’ s ca lc ul at io n. Nisarg A. Joshi134134 T ab le 2 . D es cr ip ti ve S ta ti st ic s fo r du ri ng C O V ID P er io d (J an ua ry 2 02 0 to Ju ne 2 02 0) N if ty 5 0 N if ty 5 00 B an k N if ty N if ty A ut o N if ty R ea lt y N if ty Fi n. S er . N if ty FM CG N if ty IT N if ty M ed ia N if ty M et al N if ty Ph ar m a M ea n -0 .0 01 3 -0 .0 01 2 -0 .0 03 3 -0 .0 01 6 -0 .0 03 1 -0 .0 02 6 -1 .6 E- 05 -0 .0 00 5 -0 .0 02 4 -0 .0 02 7 0. 00 17 M ed ia n -0 .0 00 5 0. 00 11 -0 .0 00 8 0. 00 12 -0 .0 00 5 0. 00 13 0. 00 10 0. 00 12 0. 00 03 0. 00 03 0. 00 08 M ax 0. 08 40 0. 07 40 0. 09 99 0. 09 89 0. 06 19 0. 08 91 0. 07 99 0. 08 64 0. 06 44 0. 07 59 0. 09 86 M in -0 .1 39 0 -0 .1 37 0 -0 .1 83 1 -0 .1 49 0 -0 .1 20 5 -0 .1 73 6 -0 .1 11 9 -0 .1 00 6 -0 .1 08 9 -0 .1 23 3 -0 .0 93 5 St d. D ev . 0. 02 67 0. 02 51 0. 03 51 0. 02 98 0. 02 99 0. 03 43 0. 02 19 0. 02 57 0. 02 88 0. 03 18 0. 02 24 Sk ew ne ss -1 .2 68 -1 .5 74 4 -1 .1 52 6 -0 .7 96 5 -1 .0 93 9 -1 .1 81 5 -0 .5 85 1 -0 .6 97 6 -0 .9 36 2 -0 .7 36 9 -0 .1 35 7 Ku rt os is 9. 52 13 10 .5 48 2 8. 54 50 8. 66 49 5. 57 69 7. 86 // 62 10 .8 88 7. 17 65 4. 85 96 5. 23 48 8. 23 99 JB S ta ti st ic 25 0. 95 34 2. 79 18 4. 81 17 7. 47 58 .5 6 14 9. 98 32 5. 95 99 .3 75 35 .6 95 36 .7 29 14 1. 09 Pr ob . 0. 00 00 0. 00 00 0. 00 00 0. 00 00 0. 00 00 0. 00 00 0. 00 00 0. 00 00 0. 00 00 0. 00 00 0. 00 00 Su m -0 .1 66 4 -0 .1 52 6 -0 .4 08 7 -0 .2 05 0 -0 .3 85 7 -0 .3 20 8 -0 .0 01 9 -0 .0 59 0 -0 .2 94 6 -0 .3 41 1 0. 21 66 Su m S q. D ev . 0. 08 71 0. 07 72 0. 15 04 0. 10 89 0. 10 96 0. 14 38 0. 05 88 0. 08 10 0. 10 15 0. 12 38 0. 06 16 O bs . 12 3 12 3 12 3 12 3 12 3 12 3 12 3 12 3 12 3 12 3 12 3 S o u r c e : a ut ho r’ s ca lc ul at io n. imPaCt of Covid-19 on PErformanCE on indian stoCK indiCEs… 135135 T ab le 3 . D es cr ip ti ve S ta ti st ic s fo r Po st -C O V ID P er io d (J ul y 20 20 to D ec em be r 20 20 ) N if ty 5 0 N if ty 5 00 B an k N if ty N if ty A ut o N if ty R ea lt y N if ty Fi n. S er . N if ty FM CG N if ty IT N if ty M ed ia N if ty M et al N if ty Ph ar m a M ea n 0. 00 23 0. 00 23 0. 00 29 0. 00 24 0. 00 33 0. 00 28 0. 00 09 0. 00 38 0. 00 15 0. 00 38 0. 00 19 M ed ia n 0. 00 33 0. 00 36 0. 00 44 0. 00 31 0. 00 51 0. 00 38 0. 00 13 0. 00 31 0. 00 24 0. 00 44 0. 00 26 M ax 0. 02 23 0. 02 33 0. 04 06 0. 03 32 0. 06 20 0. 04 02 0. 02 76 0. 05 10 0. 05 22 0. 04 30 0. 05 22 M in -0 .0 31 9 -0 .0 35 0 -0 .0 41 8 -0 .0 47 3 -0 .0 58 1 -0 .0 33 2 -0 .0 30 6 -0 .0 42 9 -0 .0 64 0 -0 .0 57 0 -0 .0 47 8 St d. D ev . 0. 00 97 0. 00 94 0. 01 72 0. 01 37 0. 01 92 0. 01 50 0. 00 87 0. 01 39 0. 01 87 0. 01 71 0. 01 59 Sk ew ne ss -1 .0 79 5 -1 .3 54 4 -0 .2 89 4 -0 .7 41 6 -0 .1 06 9 -0 .1 84 5 -0 .4 30 0 0. 20 58 -0 .3 41 2 -0 .7 33 4 -0 .1 52 2 Ku rt os is 4. 54 36 5. 76 56 2. 83 62 4. 88 33 3. 91 27 2. 71 01 4. 69 69 4. 94 53 4. 39 69 4. 69 42 4. 62 49 JB S ta ti st ic 37 .8 6 80 .5 5 1. 94 30 .8 9 4. 72 40 1. 18 41 19 .4 5 21 .2 5 12 .9 92 26 .9 94 14 .6 91 Pr ob . 0. 00 00 0. 00 00 0. 37 81 0. 00 00 0. 09 42 0. 55 31 0. 00 00 0. 00 00 0. 00 15 0. 00 00 0. 00 06 Su m 0. 30 54 0. 30 68 0. 38 04 0. 31 35 0. 43 74 0. 36 45 0. 12 82 0. 49 69 0. 20 49 0. 49 12 0. 25 73 Su m S q. D ev . 0. 01 21 0. 01 14 0. 03 82 0. 02 42 0. 04 75 0. 02 89 0. 00 98 0. 02 49 0. 04 51 0. 03 76 0. 03 24 O bs . 12 9 12 9 12 9 12 9 12 9 12 9 12 9 12 9 12 9 12 9 12 9 S o u r c e : a ut ho r’ s ca lc ul at io n. Nisarg A. Joshi136136 The skewness values of all the indices were found to be negative during the COVID-19 period and post-COVID-19 period as compared to positively skewed values before COVID-19 except realty and IT sector. These two sectors had neg- ative skewness values for all the three sub-sample time frames. The returns were following leptokurtic distribution based on the high kurtosis values for all the indices for entire time frame. The results of JB statistic showed that ma- jority of the indices did not follow normal distribution during the entire time period except metal and pharma sectors which were found to have normal dis- tribution in pre-COVID-19 period whereas bank sector and financial services sector were having normal distribution in the post-COVID-19 period. The correlation results show that the correlation among indices have in- creased during the pandemic. For the post-COVID-19 period, the correlation had decreased among the indices. These findings are in consistent with Akter and Nobi (2018) who found that the returns of the indices were less dispersed during the pandemic. The results of the regression analysis are shown in table 4, 5 and 6. This first analysis shows the impact of COVID-19 on indices volatility before COVID-19 and during COVID-19, including the lockdown period. The results show that there is a significant positive relationship between the pandemic and the volatility of all the indices in the sample. These findings are in line with Yousef (2020) who also con- cluded that the volatility of Indian market had increased amid COVID-19. Table 4. Regression Results for Model 1 for Pre-COVID and during COVID-19 (July 2019 to June 2020) Index Constant (β0) P value (β1) P value Adjusted R 2 Nifty 50 0.0090 (9.4204) 0.0000*** 0.0129 (9.5818) 0.0000*** 0.2704 Nifty 500 0.00896 (10.0271) 0.0000*** 0.0116 (9.1902) 0.0000*** 0.2541 Nifty Bank 0.013595 (11.3632) 0.0000*** 0.015528 (9.1772) 0.0000*** 0.2536 Nifty Auto 0.016768 (16.7816) 0.0000*** 0.008558 (6.0559) 0.0000*** 0.1271 Nifty Reality 0.016174 (21.78458) 0.0000*** 0.009688 (9.2270) 0.0000*** 0.2556 Nifty Financial Services 0.012364 (10.54431) 0.0000*** 0.016253 (9.8011) 0.0000*** 0.2795 imPaCt of Covid-19 on PErformanCE on indian stoCK indiCEs… 137137 Index Constant (β0) P value (β1) P value Adjusted R 2 Nifty FMCG 0.008376 (10.39899) 0.0000*** 0.009675 (8.4938) 0.0000*** 0.2250 Nifty IT 0.010451 (11.8971) 0.0000*** 0.010877 (8.7553) 0.0000*** 0.2359 Nifty Media 0.019580 (29.86678) 0.0000*** 0.006062 (6.5389) 0.0000*** 0.1456 Nifty Metal 0.018221 (22.2939) 0.0000*** 0.010303 (8.9137) 0.0000*** 0.2426 Nifty Pharma 0.011979 (16.8907) 0.0000*** 0.007053 (7.0319) 0.0000*** 0.1651 S o u r c e : author’s calculation, *** Significant at 1% level, ** Significant at 5% level. The results in table 4 show that Nifty 50 had the highest value of co-efficient among composite indices which can be inferred as the blue-chip companies (Large Cap.) are more volatile than small and mid-cap companies. It can also be seen in the results as the co-efficient of Nifty 50 was higher than Nifty 500 in- dex. Among the sectoral indices, finance sector was found to have highest vol- atility (0.016253) followed by the bank sector (0.015528). These sectors had experienced higher volatility than all the composite indices. These results in- dicate that investor sentimentality was against the financial sector during the pandemic time considering the increase in NPAs amid extended lockdown and financial relaxations. The health care sector was found to have the least volatil- ity during COVID-19 and shown upward trend. The results show the impact of COVID-19 on volatility of returns. The re- sults show that the volatility of returns of Nifty 50 index in the pre-COVID-19 period was 0.9% which had increased to 2.19% during the pandemic. The high- est volatility of returns was found in the bank sector which had increased from 1.36% in the pre-COVID-19 period to 2.91% during the lockdown period fol- lowed by the financial services sector (2.86%). Pharma sector and FMCG sector had shown the resistance during the COVID-19 period as they had shown the least volatility of returns. The regression results regarding the impact of COVID-19 on indices volatility before COVID-19 and after COVID-19 lockdown are also shown in table 5. These re- sults show that, once the lockdown was lifted by the government and the economic Table 4. Regression… Nisarg A. Joshi138138 activities resumed, there was a mixed relationship between COVID-19 and volatil- ity of the indices. The co-efficient value of all indices from the sample have shown negative value. These results indicate that post-COVID-19, once the lockdown had lifted, there was a negative relationship between COVID-19 and volatility. Nifty pharma had shown the insignificant relationship between COVID-19 and volatility. Table 5. Regression Results for Model 1 for Pre-COVID-19 and Post-COVID-19 (July 2019 to December 2020 & July 2020 to December 2020) Index Constant (β0) P value (β1) P value Adjusted R 2 Nifty 50 0.356603 (5.6631) 0.0000*** -0.958746 (-10.7661) 0.0000*** 0.3193 Nifty 500 0.303785 (4.7878) 0.0000*** -1.082286 (-12.0613) 0.0000*** 0.3710 Nifty Bank 0.077353 (1.0739 0.2839 -0.645293 (-6.3346) 0.0000*** 0.1377 Nifty Auto 0.605246 (8.8857) 0.0000*** -1.126552 (-11.69489) 0.0000*** 0.3566 Nifty Reality -0.332747 (-5.9633) 0.0000*** -0.639902 (-8.1090) 0.0000*** 0.2091 Nifty Financial Services 0.096032 (1.3515) 0.1778 -0.835188 (-8.3115) 0.0000*** 0.2175 Nifty FMCG 0.227140 (2.9502) 0.0035*** -0.424732 (-3.9009) 0.0001*** 0.0549 Nifty IT -0.543955 (-7.5705) 0.0000*** 0.225583 (2.2199) 0.0273** 0.0158 Nifty Media 0.189601 (6.0433) 0.0000*** -0.8295 (-18.6962) 0.0000*** 0.5872 Nifty Metal 0.167234 (6.9002) 0.0000*** -0.558835 (-16.3044) 0.0000*** 0.5195 Nifty Pharma 0.168255 (2.7964) 0.0056*** -0.036558 (-0.4296) 0.6678 -0.0033 S o u r c e : author’s calculation, *** Significant at 1% level, ** Significant at 5% level. The results showing the impact of COVID-19 on skewness are shown in table 6 and table 7. The results of the first analysis depict that there is a mixed relation between COVID-19 and skewness of all the indices in the sample. Among com- posite indices, Nifty 500 (0.697574) has the highest positive co-efficient which imPaCt of Covid-19 on PErformanCE on indian stoCK indiCEs… 139139 can be inferred as the small and mid-cap stock have higher skewness as com- pared to stock which are included in Nifty 50. Nifty 50 index showed an insig- nificant positive relationship between COVID-19 and skewness. The sectoral indices which were found to have the highest negative co-efficient is Nifty IT (-1.170203), and highest positive co-efficient is Nifty Realty (2.089636). Nifty bank, Nifty auto, Nifty financial services and Nifty media have insignificant relationship between COVID-19 and skewness. The results of the analysis for the pre-COVID-19 and post-COVID-19 period also show mixed relation between COV- ID-19 and skewness of the indices. Nifty 500 index and Nifty FMCG index showed insignificant positive relationship between COVID-19 and skewness. Table 6. Regression Results for Model 2 for Pre-COVID-19 and during COVID-19 (July 2019 to June 2020) Index Constant (β0) P value (β1) P value Adjusted R 2 Nifty 50 1.270817 (8.3014) 0.0000*** 0.309386 (1.4289) 0.1543 0.0042 Nifty 500 1.147216 (7.0876) 0.0000*** 0.697574 (3.0474) 0.0026*** 0.0327 Nifty Bank 1.504908 (11.3424) 0.0000*** 0.008447 (0.0450) 0.9641 -0.005 Nifty Auto 1.818009 (9.6656) 0.0000*** -0.409359 (-1.5389) 0.1251 0.0056 Nifty Realty 0.464673 (1.9774) 0.0491** 2.089636 (6.2880) 0.0000*** 0.1359 Nifty Financial Services 1.792925 (13.5131) 0.0000*** -0.02242 (-0.1195) 0.9050 -0.004 Nifty FMCG 1.572924 (9.2106) 0.0000*** -0.355282 (-1.4711) 0.1426 0.0047 Nifty IT 2.288402 (10.7758) 0.0000*** -1.170203 (-3.8964) 0.0001*** 0.0547 Nifty Media 0.637226 (7.1181) 0.0000*** -0.000420 (-0.0033) 0.9974 -0.0041 Nifty Metal -0.433009 (-6.0955) 0.0000*** 0.911095 (9.0690) 0.0000*** 0.2490 Nifty Pharma 0.259024 (2.3996) 0.0172** 1.077574 (7.0587) 0.0000*** 0.1661 S o u r c e : author’s calculation, *** Significant at 1% level, ** Significant at 5% level. Nisarg A. Joshi140140 Table 7. Regression Results for Model 2 for Pre-COVID-19 and Post-COVID-19 (July 2019 to December 2020 & July 2020 to December 2020) Index Constant (β0) P value (β1) P value Adjusted R 2 Nifty 50 0.008977 (40.7533) 0.0000 0.001018 (3.3080) 0.0011 0.0381 Nifty 500 0.008962 (39.7758) 0.0000 0.000474 (1.5043) 0.1338 0.0050 Nifty Bank 0.013595 (34.5211) 0.0000 0.004555 (8.2760) 0.0000 0.2119 Nifty Auto 0.016768 (44.8521) 0.0000 -0.003162 (-6.0509) 0.0000 0.1243 Nifty Reality 0.016174 (45.6823) 0.0000 0.003266 (6.5993) 0.0000 0.1450 Nifty Financial Services 0.012364 (33.8803) 0.0000 0.003466 (6.7948) 0.0000 0.1525 Nifty FMCG 0.008376 (43.7738) 0.0000 6.90E-05 (0.2580) 0.7966 -0.0037 Nifty IT 0.010451 (56.5388) 00000 0.003620 (14.0138) 0.0000 0.4377 Nifty Media 0.019580 (60.1984) 0.0000 -0.001317 (-2.8963) 0.0041 0.0286 Nifty Metal 0.018221 (73.0026) 0.0000 -0.001500 (-4.2990) 0.0000 0.0651 Nifty Pharma 0.011979 (61.9221) 0.0000 0.003771 (13.9458) 0.0000 0.4353 S o u r c e : author’s calculation, *** Significant at 1% level, ** Significant at 5% level. The relationship between COVID-19 and kurtosis shows a negative relationship between COVID-19 and kurtosis. In the analysis of pre-COVID-19 and during COVID-19 period, Nifty 500 index was found to have highest negative relation- ship, which can be inferred as the small and mid-cap stocks have higher skew- ness as compared to stocks which are included in Nifty 50. The second analysis shows mixed relationship in the post-COVID-19 period where five indices out of the sample show positive relationship out of which only two indices’ results were significant. imPaCt of Covid-19 on PErformanCE on indian stoCK indiCEs… 141141 Table 8. Regression Results for Model 3 for Pre-COVID-19 and during COVID-19 (July 2019 to June 2020) Index Constant (β0) P value (β1) P value Adjusted R 2 Nifty 50 0.356603 (5.7856) 0.0000*** -1.174631 (-13.6350) 0.0000*** 0.4242 Nifty 500 0.303785 (4.5401) 0.0000*** -1.280558 (-13.6929) 0.0000*** 0.4263 Nifty Bank 0.077353 (1.1362) 0.2570 -0.402242 (-4.2273) 0.0000*** 0.0630 Nifty Auto 0.605246 (9.1783) 0.0000*** -1.034794 (-11.2274) 0.0000*** 0.3325 Nifty Reality -0.332747 (-8.2767) 0.0000*** 0.471542 (8.3918) 0.0000*** 0.2167 Nifty Financial Services 0.096032 (1.3958) 0.1640 -0.317783 (-3.3047) 0.0011*** 0.0380 Nifty FMCG 0.227140 (3.3005) 0.0011*** -0.417605 (-4.3416) 0.0000*** 0.0664 Nifty IT -0.543955 (-7.3702) 0.0000*** 0.7906 (7.6643) 0.0000*** 0.1870 Nifty Media 0.189601 (4.0336) 0.0001*** -0.176333 (-2.6840) 0.0078*** 0.0241 Nifty Metal 0.167234 (4.4952) 0.0000*** -0.4836 (-9.3009) 0.0000*** 0.2541 Nifty Pharma 0.168255 (3.1101) 0.0021*** -0.261170 (-3.4540) 0.0006*** 0.0417 S o u r c e : author’s calculation, *** Significant at 1% level, ** Significant at 5% level. Nisarg A. Joshi142142 Table 9. Regression Results for Model 3 for Pre-COVID-19 and Post-COVID-19 (July 2019 to December 2020 & July 2020 to December 2020) Index Constant (β0) P value (β1) P value Adjusted R 2 Nifty 50 1.270817 (7.3182) 0.0000*** -0.394219 (-1.6242) 0.1000* 0.0065 Nifty 500 1.147216 (5.4005) 0.0000*** 0.353545 (1.1908) 0.2349 0.0017 Nifty Bank 1.504908 (13.3041) 0.0000*** -1.677408 (-10.6098) 0.0000*** 0.3077 Nifty Auto 1.818009 (9.4877) 0.0000*** -0.491157 (-1.8339) 0.0679* 0.0093 Nifty Reality 0.464673 (3.7878) 0.0002*** 0.215547 (1.2571) 0.2099 0.0023 Nifty Financial Services 1.792925 (17.4404) 0.0000*** -2.227391 (-15.5019) 0.0000*** 0.4881 Nifty FMCG 1.572924 (11.1982) 0.0000*** -0.858837 (-4.3747) 0.0000*** 0.0674 Nifty IT 2.288402 (11.9478) 0.0000*** -0.543323 (-2.0296) 0.0435** 0.0123 Nifty Media 0.637226 (5.6164) 0.0000*** 0.202065 (1.2742) 0.2038 0.0025 Nifty Metal -0.433009 (-4.5018) 0.0000*** 1.310607 (9.7489) 0.0000*** 0.2726 Nifty Pharma 0.259024 (2.8173) 0.0052*** 1.066053 (8.2959) 0.0000*** 0.2128 S o u r c e : author’s calculation, *** Significant at 1% level, ** Significant at 5% level, * Significant at 10% level.  Conclusion Conclusion The purpose of the study is to check the impact of COVID-19 on the variability of returns of composite and sectoral indices of the Indian market. This study fo- cuses on change in the returns of the sample during the pandemic and after the pandemic by measuring the forecasting variables of the indices’ performance. The findings show that the Indian indices have shown more volatility during COVID-19 as compared to pre-COVID-19 and post-COVID-19 period. The study prompts that investor sentimentality can be prevented against pessimistic behavior if the panic is being controlled. The findings of the study imPaCt of Covid-19 on PErformanCE on indian stoCK indiCEs… 143143 have shown that variability of returns in terms of standard deviation turned negative in the post-COVID-19 period. For the benchmark index of Nifty 50, the standard deviation of returns was found to be 2.19% during the COVID-19 pe- riod which had decreased to -0.60% in the post-COVID-19 period. This study has analyzed the relationship between COVID-19 and volatility of stock returns for two composite indices and nine sectoral indices using three measures, namely skewness, standard deviation and kurtosis. The study used the daily closing prices of all the indices for the period from July 2019 to De- cember 2020, where the sample was divided into three sub-samples, i.e., pre- COVID-19 period, during COVID-19 period and post-COVID-19 period. The ma- jor findings of the study indicate that the average returns of the indices to be negative during COVID-19 period. It is also evident that the indices in the sam- ple replicate a very high volatility during the pandemic period as compared to before COVID-19 and post-COVID-19 period. The results of generalized least squares regression show that there is a sig- nificant positive correlation between COVID-19 and standard deviation of the indices during COVID-19 period. The post-COVID-19 relationship shows that the volatility in the indices reduced during the period from July 2020 to Decem- ber 2020. The results of the impact of COVID-19 on skewness of index returns show that there is a mixed relationship between COVID-19 and skewness of re- turns of indices. The relationship between COVID-19 and kurtosis show nega- tive results during the pandemic as well as the post-pandemic period. The findings of the study have significant implications and impacts regard- ing the decision making for equity analysts, portfolio management firms, in- vestors and traders for assessing their investment in a better way and deciding their investments. Increase in volatility will resort to anxiety in the investors and traders which will motivate the participants to take lesser risk for the time- being. The results of this study have appropriate impact in relation to FDIs and FIIs in India and across the world. One of the major implications of this study is for the policymakers to study the changing aspects of the investor’s sentiments and the pandemic. This can help the policymakers to regulate and control the impact and intensity of the anxiety in the investors so that markets can be reinforced in a better way and volatility can be avoided to the maximum possible extent. The policymak- ers should be more careful regarding the crash risk of stock indices during COVID-19 because of upsurge in COVID-19 cases and deaths. Nisarg A. Joshi144144 The results of the study suggest that a rational investor should not invest in the stocks during the pandemic. It can be recommended to speculators that they can build a position at a low price when the market plunges and make a considerable profit in a short time period resulting from the recovery of the market. The investors who are interested in the investment over a long horizon should invest in the blue-chip stocks or the market indices to get exponential returns over a period of time. In the future, the researchers can take a cue from this study as this study is constructed using the composite indices and sectoral indices using daily closing prices. It does not include individual stocks which can be further investigated to check the impact of the pandemic on a particular stock’s performance. A study can be done using weekly or monthly data which can be used to study the season- ality effect along with COVID-19. The event study approach can be used by calcu- lating the average abnormal returns and cumulative average abnormal returns for the period before COVID-19 and after COVID-19. This study is limited only to composite and sectoral indices of National Stock Exchange. Similar kinds of study can be done using other indices of the various markets of India as well as of oth- er countries. Another methodology can be adopted such as robust regression by giving weights to the data points or panel regression or autoregressive distrib- uted lag regression to get different inferences. Further research can be done to check the structural changes before and after COVID-19.  References References Ahmar, A.S., & del Val, E.B. (2020). SutteARIMA: Short-term forecasting method, a case: COVID-19 and stock market in Spain. Science of The Total Environment, 729, 138883. http://dx.doi.org/10.1016/j.scitotenv.2020.138883. Akter, N., & Nobi, A. (2018). Investigation of the financial stability of S&P 500 using re- alized volatility and stock returns distribution. Journal of Risk and Financial Man- agement, 11(2), 22. http://dx.doi.org/10.3390/jrfm11020022. Al-Awadhi, A.M., Al-Saifi, K., Al-Awadhi, A., & Alhamadi, S. (2020). Death and contagious infectious diseases: Impact of the COVID-19 virus on stock market returns. Jour- nal of Behavioral and Experimental Finance, 27, 100326. http://dx.doi.org/10.1016/j. jbef.2020.100326. Albulescu, C.T. (2020). Coronavirus and financial volatility: 40 days of fasting and fear. Working Paper SSRN. http://dx.doi.org/10.2139/ssrn.3550630 Ali, M., Alam, N., & Rizvi, S.A.R. (2020). Coronavirus (COVID-19) – An epidemic or pan- demic for financial markets. Journal of Behavioral and Experimental Finance, 27, 100341. http://dx.doi.org/10.1016/j.jbef.2020.100341. imPaCt of Covid-19 on PErformanCE on indian stoCK indiCEs… 145145 Aslam, F., Ferreira, P., Mughal, K. S., & Bashir, B. (2021). Intraday volatility spillovers among european financial markets during COVID-19. International Journal of Finan- cial Studies, 9(1), 1–19. http://dx.doi.org/10.3390/ijfs9010005. Baker, S., Bloom, N., Davis, S.J., Kost, K., Sammon, M., & Viratyosin, T. (2020). The un- precedented stock market reaction to COVID-19. Hoover Institution Economics Working Paper, 20112, 1–22. https://www.hoover.org/sites/default/files/research/ docs/20112-davis.pdf. Brown, M.R., & Smith, R.D. (2008). The economic impact of SARS: How does the reality match the predictions?. Health Policy, 88(1), 110–120. http://dx.doi.org/10.1016/j. healthpol.2008.03.003. Chaudhary, R., Bakhshi, P., & Gupta, H. (2020). The performance of the Indian stock market during COVID-19. Investment Management and Financial Innovations, 17(3), 133–147. http://dx.doi.org/10.21511/imfi.17(3).2020.11. Chen, M.-H., Jang, S., & Kim, W.G. (2007). The impact of the SARS outbreak on Taiwanese hotel stock performance: An event-study approach. International Journal of Hospi- tality Management, 26(1), 200–212. David, S.A., Inácio, C.M.C., & Tenreiro Machado, J.A. (2021). The recovery of global stock markets indices after impacts due to pandemics. Research in International Business and Finance, 55, 101335. http://dx.doi.org/10.1016/j.ribaf.2020.101335. Del Giudice, A., & Paltrinieri, A. (2017). The impact of the Arab spring and the Ebola out- break on African equity mutual fund investor decisions. Research in International Business & Finance, 41, 600–612. Fernandes, N. (2020). Economic effects of coronavirus outbreak (COVID-19) on the world economy. Barcelona: IESE Business School. https://edisciplinas.usp.br/plugin- file.php/5662406/mod_resource/content/1/FERNANDES_Economic%20Effects%20 of%20Coronavirus%20Outbreak%20%28COVID19%29%20on%20the%20World% 20Economy.pdf. Goodell, J.W. (2020). COVID-19 and finance: Agendas for future research. Finance Re- search Letters, 35, 101512. http://dx.doi.org/10.1016/j.frl.2020.101512. Harif, A., Aloui, C., & Yarovaya, L. (2020). COVID-19 Pandemic, Oil Prices, Stock Market and Policy Uncertainty Nexus in the US Economy: Fresh Evidence from the Wave- let-Based Approach. International Review of Financial Analysis, 70(C). http://dx.doi. org/10.2139/ssrn.3574699. Izzeldin, M., Muradoğlu, Y.G., Pappas, V., & Sivaprasad, S. (2021). The impact of COVID-19 on G7 stock markets volatility: Evidence from a ST-HAR model. International Review of Financial Analysis, 74, 101671. https://dx.doi.org/10.1016/j.irfa.2021.101671. Kartal, M.T., Depren, Ö., & Kılıç Depren, S. (2020). The Determinants of Main Stock Ex- change Index Changes in Emerging Countries: Evidence from Turkey in COVID-19 Pandemic Age. Quantitative Finance and Economics, 4(4), 526–541. https://doi. org/10.3934/qfe.2020025. Li, K. (2018). Reaction to news in the Chinese stock market: A study on Xiong’an new area strategy. Journal of Behavioral and Experimental Finance, 19, 36–38. https:// dx.doi.org/10.1016/j.jbef.2018.03.004. https://www.hoover.org/sites/default/files/research/docs/20112-davis.pdf https://www.hoover.org/sites/default/files/research/docs/20112-davis.pdf http://dx.doi.org/10.1016/j.ribaf.2020.101335 https://edisciplinas.usp.br/pluginfile.php/5662406/mod_resource/content/1/FERNANDES_Economic%20Effects%20of%20Coronavirus%20Outbreak%20%28COVID19%29%20on%20the%20World%20Economy.pdf https://edisciplinas.usp.br/pluginfile.php/5662406/mod_resource/content/1/FERNANDES_Economic%20Effects%20of%20Coronavirus%20Outbreak%20%28COVID19%29%20on%20the%20World%20Economy.pdf https://edisciplinas.usp.br/pluginfile.php/5662406/mod_resource/content/1/FERNANDES_Economic%20Effects%20of%20Coronavirus%20Outbreak%20%28COVID19%29%20on%20the%20World%20Economy.pdf https://edisciplinas.usp.br/pluginfile.php/5662406/mod_resource/content/1/FERNANDES_Economic%20Effects%20of%20Coronavirus%20Outbreak%20%28COVID19%29%20on%20the%20World%20Economy.pdf Nisarg A. Joshi146146 Liu, H., Manzoor, A., Wang, C., Zhang, L., & Manzoor, Z. (2020). The COVID-19 Outbreak and Affected Countries Stock Markets Response. International Journal of Environ- mental Research and Public Health, 17(8), 2800. https://dx.doi.org/10.3390/ijer- ph17082800. Loh, E. (2006). The impact of SARS on the performance and risk profile of airline stocks. International Journal of Transport Economics, 33(3), 401–422. Mazur, M., Dang, M., & Vega, M. (2020). COVID-19 and the march 2020 stock market crash. Evidence from S&P1500. Finance Research Letters, 38(1), 101690. http:// dx.doi.org/10.1016/j.frl.2020.101690. Mishra, P.K., & Mishra, S.K. (2020). Corona Pandemic and Stock Market Behaviour: Empirical Insights from Selected Asian Countries. Millennial Asia, 11(3), 341–365. http://dx.doi.org/10.1177/0976399620952354. Nageri, K.I. (2019). Evaluating volatility persistence of stock return in the pre and post 2008-2009 financial meltdown. Copernican Journal of Finance & Accounting, 8(3), 75–94. http://dx.doi.org/10.12775/CJFA.2019.013. Okorie, D.I., & Lin, B. (2021). Stock markets and the COVID-19 fractal contagion effects. Finance Research Letters, 38, 101640. http:/dx./doi.org/10.1016/j.frl.2020.101640 Pendell, D.L., & Cho, C. (2013). Stock market reactions to contagious animal disease out- breaks: An event study in Korean foot-and-mouth disease outbreak. Agribusiness, 29(4), 455–468. Phan, D., & Narayan, P. (2020). Country Responses and the Reaction of the Stock Market to COVID-19: a Preliminary Exposition. Emerging Markets Finance and Trade, 56(10), 2138–2150. http://dx.doi.org/10.1080/1540496X.2020.1784719. Siddiqui, T.A., Ahmed, H., & Naushad, M. (2020). Diffusion of COVID-19 impact across se- lected stock markets: a wavelet coherency analysis. Investment Management and Fi- nancial Innovations, 17(4), 202–214. http://dx.doi.org/10.21511/imfi.17(4).2020.19. Singh, B., Dhall, R., Narang, S., & Rawat, S. (2020). The Outbreak of COVID-19 and Stock Market Responses: An Event Study and Panel Data Analysis for G-20 Countries. Global Business Review. http://dx.doi.org/10.1177/0972150920957274. Topcu, M., & Gulal, O.S. (2020). The impact of COVID-19 on emerging stock markets. Finance Research Letters, 36, 101691. http://dx.doi.org/10.1016/j.frl.2020.101691. Wang, L., & Kutan, A.M. (2013). The impact of natural disasters on stock markets: Evi- dence from Japan and the US. Comparative Economic Studies, 55(4), 672–686. Yousef, I. (2020). The Impact of Coronavirus on Stock Market Volatility. Interna- tional Journal of Psychosocial Rehabilitation, 24(6), 18069–18081. http://dx.doi. org/10.37200/IJPR/V24I6/PR261476. Zaremba, A., Kizys, R., Aharon, D.Y., & Demir, E. (2020). Infected Markets: Novel Coro- navirus, Government Interventions, and Stock Return Volatility around the Globe. Finance Research Letters, 35, 101597. http://dx.doi.org/10.1016/j.frl.2020.101597. Zhang, D., Hu, M., & Ji, Q. (2020). Financial markets under the global pandemic of COVID-19. Finance Research Letters, 36, 101528. http://dx.doi.org/10.1016/j. frl.2020.101528. https://doi.org/10.1016/j.frl.2020.101640 http://dx.doi.org/10.1016/j.frl.2020.101597