## Expert Dialog

Question #35: Patell z test with Mean-Adjusted Model

Dear Mr Müller,

from my point of view using the Patell z test in combination with the mean-adjusted model seems counter-intuitive, since the S(ARi,t,) includes data from a market index (R(m,t)), which are not relevant for the calculation of mean-adjusted AR's. Still your event study engine is calculating it. Would you please elaborate whether you agree with me here, or respectively, why you don't?

Basically, I am using both the mean-adjusted and the market model and I would like to compare the two models' results, which is obviously not possible when using different significance tests. (Due to several adjustments I have made, I am using your engine solely for robustness checks.)

Best regards,
Mark

Dear Mark, for the mean-adjusted model, we use a different formula: s^2_ar = s^2_ar * (1+ 1 / M_i). Best, Simon
Question #34: long term event study analysis

I want to measure long term performance (after 1 year, 3 years and 5 years) of IPO for 400 companies between 2000 to 2010. I want to use BHAR to measure the performance. but I don't know how prepare input data to be used in STATA. I have data in table format in excel as follows:
1. daily market return between 2000 to 2010
2. daily company return between 2000 to 2010
3. IPO listing for each company.

the questions is:
1. how can I prepare my data as you suggested using Comma-separate-value because I have up to 400 companies to go one by one?
2. how can I start my analysis?

You may use the reshape procedure in STATA. You find an example ont the idre UCLA site: http://www.ats.ucla.edu/stat/stata/modules/reshapel.htm
Question #33: Event Study on CDS

Hi everyone,

I want to analyze abnormal Returns of daily CDS Prices over the past 10 years, especially at certain Events. The CDS are still collected via Bloomberg (different maturities, Senior and Sub CDS, for nearly 100 European Banks). For the estimated return I'd take an iTraxx CDS index.

Would you consider to analyze analogous to your stock return Event study examples? I doubt, that the market model will fit?

Maybe I can upload the dataset for analyzing?

Sascha

Question #32: What is exactly M?

Dear Mr. Müller,

Regarding the parametric T-test for one sample Event: Could you explain me the size M (matched returns), please?

My event window is +/- seven days surrounding the announcement day of an acquisition. So L2 is 15 in my analysis, right? Is M also 15?

You can also answer me in german.

Best wishes,

Tim Rothermel

Hi Mr. Rothermel,you are correct.Best,Simon Müller
Question #31: Grouping Variable

I am trying to run an even study test by event study tool. I found a column called grouping variable in the "request file", and in the sample file it is given as "addition". I am not quite sure what grouping variable is and what "addition" indicates. Could you kindly instruct me?

The purpose of the grouping variable is described as folows: "For generating the 'average' values in your analysis (i.e., AAR and CAAR values as produced by aARC), you need to specify the 'grouping variable'. If you use only one value in the grouping variable, which is the default case, AXC will calculate the average values across all events in your request file; if you choose more than one value (e.g., 'acquisition' and 'divestiture' in a boundary choise study), AXC will produce average values across the events grouped by these values." (http://www.eventstudytools.com/instructions-axc)'Addition' was a value we used in the context of a study that investigated index changes in the S&P500 index. As index changes, we considered 'additions' and 'deletions' from the index.
Question #30: Competitor Portfolio

I am examining an individual event. According to your recommendations a parametric t-test (Nr. 1 on the website) is applicable. Besides the effects this event has on the stock returns of the company responsible for the event, I'd also like to examine the effects on the firm's competitors. Treating individual competitor stocks as independet is almost surely inappropriate, since I would expect a fair amount of correlation among competitor retruns. To adjust for this possibility, I create a portfolio composed of all relevant competitors and calculated the abnormal returns of this portfolio.
1.) Can I apply the same test statistic to test for significant AR of the competitor portfolio as I do for the individual focal firm?
2.) Is there a way to avoid portfolio creation that still yields statistically meaningfull/ unbiased results? Which test would be applicable in that case?

Since you do a "single event"-event study, you can use the grouping variable available in our research app to group all competitors and keep the other firm separate. The tests statistics will consider the grouping as described in the test statistics section.
Question #29: Single-Day Event Study

I am currently working on a single-day event study. I came across the paper by Kolari and Pynnönen (2010), which proposes two test statistics that can handle cross-sectional correlation: ADJ-BMP and ADJ-PATELL. Is there a way to correct for cross-sectional correlation using the "Event Study Engine"?

Yes, you may choose Adjusted Patell or Adjusted BMP test (see http://www.eventstudytools.com/significance-tests [5] and [7]) in our Event Study Engine. Please select there Adjusted Patell Z and Adjusted StdCSect Z.
Question #28: Standard Deviation and Variance of CAR

When looking to your excellent summary of event study statistics , I've something that I am not quite sure is correct. When you present the formulas for the Standard deviation of the CAR in the BMP test, I think you mean that the equation in question is for the variance of CAR and not the Standard Deviation, meaning that a square is missing in the Market Model, Comparison Period Mean Adjusted Model and the Market Adjusted Model left side of the equation. Maybe I am missing something but I want to be sure.

Thank you for that hint. You are correct the square on the left side of the equation is missing.
Question #27: Difference in mean - pre/post financial regulation

If you are conducting a study where you test AAR/CAAR in association with corporate credit rating changes before and after a financial regulation (ie. test if the effect on the stock market from a credit rating change (Moody's) is more/less extreme after the regulation), how would you test for the difference in mean?

I have looked at multivariate regression models but i don't quite understand it. Could you be so kind to elaborate on how you would test for the difference in post/pre AAR/CAAR.

Just a short note: I guess there is a sort of small typo within the R code example provided within the 'local tools for event studies'-section. When calculating the simple returns, the variable filled should not be called firmSub$firmSub but rather firmSub$firmReturn.Otherwise it will not be found within the OLS estimation and further on.