Thanks for the explanation. I want to ask if such approach can be used for inspecting the impact of news of Pfizer's vaccine efficiency (for example, November 9th, 2020, when Pfizer reported 90% vaccine efficiency) on stock prices?
Yes, you can. This would be a single event, for one company (so you don't need "event time"), but you would need to estimate the Abnormal Returns (and cumulate these) around the event date.
Dear Dr. Ward, this is really detailed explain. I want to ask if such approach can be used for inspecting the impact of covid-19 on stock prices or market reaction in particular?
Not really. The impact of COVID-19 can easily be seen simply by looking at the chart of market index itself. Typically, event studies a specific event (say a buy-back announcement), which occurs at different dates, to various shares in "event time" and calculates "abnormal returns" vs the index for each share etc. COVID was a market event, impacting all shares (although differently, as Amazon did well (say) vs AirBnB (badly)) and the (event) effect can be seen in the market index itself. Same would apply to the 9/11 event in the USA, which was a market event.
Thank you author for making this vedio.. Can you make a Vedio on IPOs event.. In the IPO event there will be no estimation windy.. How to calculate T test.. Please suggest
Hi. For my research I am conducting an event study for a sample of Pharmaceutical firms partaking in M&A in the U.S. Specifically, I want to include whether the event being a horzontal or vertical acquisition plays a part in the returns. However, I wanted to focus on a longer horizon, say, 1-year, 2-year and 3-years out from the event. Is this method still applicable? If not, how should I go about this? Thank you so much
Hi Matthew, many would argue that event studies are only valid over an event window of a few days (say -10 to +10 around the actual event dates). But, this will depend on how good your forecast methodology is of abnormal returns (if you have a good model to predict abnormal returns, you can lengthen the window - and there are ways of testing this). However, for a long horizon such as you plan, I would suggest Style Analysis (also known as "Buy and Hold" portfolio analysis). In your example, you would compare the performance of just two portfolios (horizontal and vertical acquisitions) over three years. Here's a link to our video on our "Style Engine" which explains more: ua-cam.com/video/6iTK784XAqE/v-deo.html
Hi Sir, The impact of COVID-19 shutdowns on the stock prices of major banks (G-SIBs & D-SIBs) operating in the US. I have 101 banks to analyze what would you advice me?
Of course COVID affected all listed shares, including banks. The easiest way to see the abnormal returns (which are the essence of event studies) for the banking sector would be to simply calculate the cumulative ARs for the banking sector index versus the market (S&P500) and plot these.
@@MichaelWardFinance how can I do it sir? It’s about my master thesis. Where can I find that banking sector index? So basically the banking sector index will give me a macro view about how lockdown impacted the stock price of banks but then I would like also to separately see the effect of both type of banks the G-sibs and the D-sibs. However, I have 81 D-sibs and 19 G-sibs banks. So how should I do it? And can you maybe tell me where can I download the adjusted close price of the banking sector index and how it’s called?
We only use trading days, so an event on a weekend or holiday is the return (not price) on the first trading day that follows. So, eg for a weekend, return=ln (Price Monday / Price Friday). This measures the return from the closing price on Friday to the closing price on Monday and includes any event within the period.
@@rarararawr9931 t0 is always the day the "news" of the even hits the market. t+1 is the next trading day. So, if for example, the event was on Monday (t0) then the next trading day (t+1) would be Tuesday (unless Tuesday and Wednesday were public holidays?)
@@MichaelWardFinance sorry, yes i meant was Tuesday. So lemme confirm again, if the event day supposed to be on December 31, 2020 but it's on holiday. Is it true that t0 would be on Jan 4, 2021; t+1 Jan 5, 2021 and so on?
Thanks for the explanation. I want to ask if such approach can be used for inspecting the impact of news of Pfizer's vaccine efficiency (for example, November 9th, 2020, when Pfizer reported 90% vaccine efficiency) on stock prices?
Yes, you can. This would be a single event, for one company (so you don't need "event time"), but you would need to estimate the Abnormal Returns (and cumulate these) around the event date.
Dear Dr. Ward, this is really detailed explain. I want to ask if such approach can be used for inspecting the impact of covid-19 on stock prices or market reaction in particular?
Not really. The impact of COVID-19 can easily be seen simply by looking at the chart of market index itself. Typically, event studies a specific event (say a buy-back announcement), which occurs at different dates, to various shares in "event time" and calculates "abnormal returns" vs the index for each share etc. COVID was a market event, impacting all shares (although differently, as Amazon did well (say) vs AirBnB (badly)) and the (event) effect can be seen in the market index itself. Same would apply to the 9/11 event in the USA, which was a market event.
@@MichaelWardFinance Thank you professor, really appreciate your response.
@ Dr Hasan, May I have your details, I’m doing something similar in my dissertation and I’d do with some input from you
Thank you author for making this vedio..
Can you make a Vedio on IPOs event..
In the IPO event there will be no estimation windy..
How to calculate T test..
Please suggest
Dr Ward, is it possible to share this data set for easy practice and follow along as you do this?
Hi. For my research I am conducting an event study for a sample of Pharmaceutical firms partaking in M&A in the U.S. Specifically, I want to include whether the event being a horzontal or vertical acquisition plays a part in the returns. However, I wanted to focus on a longer horizon, say, 1-year, 2-year and 3-years out from the event. Is this method still applicable? If not, how should I go about this? Thank you so much
Hi Matthew, many would argue that event studies are only valid over an event window of a few days (say -10 to +10 around the actual event dates). But, this will depend on how good your forecast methodology is of abnormal returns (if you have a good model to predict abnormal returns, you can lengthen the window - and there are ways of testing this). However, for a long horizon such as you plan, I would suggest Style Analysis (also known as "Buy and Hold" portfolio analysis). In your example, you would compare the performance of just two portfolios (horizontal and vertical acquisitions) over three years. Here's a link to our video on our "Style Engine" which explains more: ua-cam.com/video/6iTK784XAqE/v-deo.html
Hi Sir, The impact of COVID-19 shutdowns on the stock prices of major banks (G-SIBs & D-SIBs) operating in the US. I have 101 banks to analyze what would you advice me?
Of course COVID affected all listed shares, including banks. The easiest way to see the abnormal returns (which are the essence of event studies) for the banking sector would be to simply calculate the cumulative ARs for the banking sector index versus the market (S&P500) and plot these.
@@MichaelWardFinance how can I do it sir? It’s about my master thesis. Where can I find that banking sector index? So basically the banking sector index will give me a macro view about how lockdown impacted the stock price of banks but then I would like also to separately see the effect of both type of banks the G-sibs and the D-sibs. However, I have 81 D-sibs and 19 G-sibs banks. So how should I do it? And can you maybe tell me where can I download the adjusted close price of the banking sector index and how it’s called?
What price or return should I take for event day if event day is a holiday for exchange?
We only use trading days, so an event on a weekend or holiday is the return (not price) on the first trading day that follows. So, eg for a weekend, return=ln (Price Monday / Price Friday). This measures the return from the closing price on Friday to the closing price on Monday and includes any event within the period.
@@MichaelWardFinance thank you so much for your valuable suggestions.
@@MichaelWardFinance so the t0 would be monday and t+1 would be on thursday and so on?
(edited: i meant Tuesday)
@@rarararawr9931 t0 is always the day the "news" of the even hits the market. t+1 is the next trading day. So, if for example, the event was on Monday (t0) then the next trading day (t+1) would be Tuesday (unless Tuesday and Wednesday were public holidays?)
@@MichaelWardFinance sorry, yes i meant was Tuesday. So lemme confirm again, if the event day supposed to be on December 31, 2020 but it's on holiday. Is it true that t0 would be on Jan 4, 2021; t+1 Jan 5, 2021 and so on?