Cumulative Abnormal Returns for IPO

[Tom Smith]

Hi Friends

I'm trying to calculate Cumulative Abnormal Return for IPO firms during 3 year post listing time period.
I went through multiple guides on CAR, but all of them cover event studies which include estimation window. But as estimation windows is not available for IPO firms, I am confused how to calculate CAR. I have attached the formulas which I am considering to use.

Can you please help me to calculate CAR?
Thank you in advance

[Tom Smith]

Formulas

[Tom Smith]

.

[Nick Cox]

There is no Stata content so far to this thread, specifically no indication of what your variables and observations are or your general data structure. But in general cumulative sums are yielded by the sum() function.

You have a choice: you can direct your question only to the small fraction of Statalist users who deal with this kind of data or you can explain from the beginning what you want to calculate, in which case many people fluent in Stata might understand your question.

[Tom Smith]

Thanks for the Advice Nick. I am looking to replicate the CAR methodology used in the Ritter (1991).

My data structures as follows.

Dataset 1: This is the dataset for the IPO listing date.

FIRM_ID Lising Date

1111 5/2/1980
1112 5/12/1980

Dataset 2 : This consists the trading data of IPO firms.

FIRM_ID Date Closing_Price

1111 5/2/1980 10
1111 6/2/1980 10.4
1111 7/2/1980 10.6
1111 8/2/1980 10.8


Dataset 3 : This consists the CRSP index data.

Date Index
1/2/1980 130.1
1/3/1980 131.3
1/4/1980 130.8

Following Ritter (1991), I want to calculate CAR using the following steps.

1. Calculate the monthly benchmark-adjusted return for each stock.
2. Calculate the average benchmark-adjusted return on a portfolio of n stocks for event month
3. Cumulative benchmark-adjusted aftermarket performance from event month 1 to event month 36

Can some one suggest me a method to calculate this.

Thanks

[Louis Brt]

Hi Tom,
I am currently working on my Master Thesis, and I am trying to compute IPO returns just as you wanted to do. Basically, I have a list of IPOs and I have computed their returns for a 36 months perdiod, comparing their 1st day return with their return at 6 month, 12 month, etc. Did you manage to compute the CAR for your data set?