## You are here

Question #30: Multiple grouping variables

For my master thesis, I need to execute an event study with 2 moderators: one is the strategy used for the event (three possible strategies) and one is the sector of the brand of the event (two possible sectors). Would I use two grouping variables to model this? Or is there another method to do this?

If you have two or more grouping variables that each have different values, you can apply two approaches, you can do the following: 1) Perform a full enumeration of the individual cases you have and set this as a new grouping variable. In your case, this would give you 6 values for the new grouping variable, with each value describing a distinct strategy-sector combination. 2) If you need to make statements about either of your grouping variables, re-run the analysis with only this grouping variable. In your example, combining both approaches will let you make statements about the strategies as such, the sectors as such, and as per the combination of both.
Question #29: Event Window

In my Anlaysis report, I get "The event window seems to include an unexpected number of days the firm's stock has not been traded on" for some of my events. Could you please tell me what exactly this means?

The message suggests that your price data holds more gaps than one would expect - meaning, there are more nontrading days than weekends. Ultimately, there might be two reasons for this: either there were several public holidays at this stock market or your data has gaps.
Question #28: EventStudy- Multiple events and firms

I have two sub-sets of events, "good news" (15 events) and "bad news" (17 events), which I wish to see their effect of different sectors of the FTSE. Could you guide me into how I can test for these subsets of events on a specific sector at once?

That's simple. Please use the grouping variable in the request file and label those lines that represent good news with "good" and those that represent bad news with "bad". Note: When you download the sample data, you will find the grouping variable to hold "addition" as a value since the sample data represents an excerpt of an index reconstitution study - unluckily, I only picked additions and missed out to pick a single deletion.
Question #27: Event Window

I'm encountering difficulty with the estimation window. Most research papers I have found take a [-120;-11] estimation window with a [-1;1] event window. But in the app when I try to put in that estimation window I get an "Event Data import" error. I have seen you answer this question before saying that the estimation window needs to have one positive number. How can I use the [-120;-11] window with the app?

The request file should have the following structure: Event ID; Firm ID; Market ID; Event Date; Grouping Variable; Start Event Window; End Event Window; End of Estimation Window; Estimation Window Length. This means that for your estimation window, you should have -11, 120 in the two very right columns of the CSV/XLS file.
Question #26: Multiple Events for one company

I'm trying to do an event study to look at the CAAR of stock prices during an M&A announcement. Some companies have had multiple announcements for different transactions. How can I put that in my data? It come back saying "Duplicate entry in event data" if I put the company name in twice. Do I need to change the name of the company? Delete duplicates? Would that not affect my results?

Each transaction is to be considered as an individual event. And each line in your request file has to have a unique ID as a reference in the first column. The error message you received suggests that you have used multiple times the same number/ID in this column. The company name is only used to retrieve the corresponding closing price data from the firm data file. Thus, if one firm has multiple events/lines in the request file, you should also list the company name multiple times.
Question #25: Generating AAR CAAR AND T-TEST

Can I conduct a complete event study using your app?

Yes, the research apps on this website will give you ARs, AARs, CARs, CAARs, and all test statistics at the respective levels of analysis - probably one of the most complete sets of statistics any solution will provide to you.
Question #24: Multiple Events which all affect the same Companies in one Study

Hello,

I'm doing my Thesis right now and I have to test if certain events at single firms do have an effect on a group of other firms all in the same market. How would you recommend me doing this? All Events seperate? I got about 200 single Events and 50 firms spread globally

You have to fully enumerate the events per each company. Your request file will thus hold a larger number of lines. You can use the grouping variable to create meaningful subsets from this overall universe of events.
Question #23: can not calculate event window before event day

I can not calculate event window before event day like -7, -1. System force me to write the last day of event window bigger than 0.

Yes, for technical reasons, we need to enforce that the event date needs to be in your event window. You can conceptually circumvent this requirement by changing the calendar date of your event accordingly.
Question #22: length of event window

I am working on a study of biopharma stock prices's responses to receiving "breakthrough therapy designation" (BTD) from the FDA. Our hypothesis is that pre-commercial biotechs will experience a transient stock bump, but excess returns will dissipate by ~90 days. My question relates to the appropriate / maximum length of the event window. What's the maximum or optimal length of the event window, and what factors might dictate the appropriateness of a longer vs. shorter one? We have seen papers with 5-30 day windows, but have not seen a good discussion of how to select the length.

The appropriate length of the event window is driven by your research assumptions on how the capital market is processing the information that is released by the event studied. From what you wrote I assume you have the following assumptions: (1) Prior to the BTD release, there is no information leakage (2) You are studying companies in the US, which means that we should assume semi-strong market efficiency (3) You have the hypothesis that during the 90 days subsequent to the BTD release, abnormal returns are negative and undo the positive effect surrounding the BTD release This will give you the following type of parameters to your event study: + Short event window around the BTD date to capture the positive effect: [0,2] if you are certain that there is no information leakage or [-2,2] if you assume some leakage. You choose the second number based on how opaque the news might be to the capital markets. BTD releases sound quite clear, so you wouldn't assume the US capital market to take more than 2 days to price it in. Note: the smaller your companies, the less coverage they have, the long it may take... + Then, for your 90 day hypothesis you obviously will take a 90 day event window. Most likely, you would ground the calculation on the same estimation window as your [-2,2] window, meaning on the period prior to the BTD event - this will ensure twofold: one, your second analysis uses the same presumed relationship of your firms to the stock markets, and two, you overrule the effect of the BTD event on the stock market-company relationship, which you factually negate given your hypothesis (meaning, this choice is in line with your hypothesis)
Question #21: VOLUME EVENT STUDY

I would like to use EventStudyTools for volume eventstudy.

The market data required "mean of log percentage of trading volume of index".

Could you advise me how to derived the value from raw data "volume of index".

thank you