Re: st: Event-Study Cumulative Abnormal Return(CAR)

[Nick Cox <njcoxstata@gmail.com>]

Your calculations seem to require

egen sum_for_each_day = total(abnormal_return), by(dif)

We can't comment on what you tried and don't show us.

Nick

On Mon, Feb 25, 2013 at 9:08 PM, Künzel Sven
<s.kuenzel@tu-braunschweig.de> wrote:

> I was wondering if you can help me. I am trying to analyse my datasample by
> using an Event-Study. Now I would like to get a cumulative sum of the
> abnormal return for each day around the event-date. At the End I would like
> to have a variable where I can see the sum for each day around the event. My
> data looks like this:
>
>
>
> new variable I need
> countrynam spreads  group_id    datum      event_date    dif event_window
> abnormal_return    sum_for_each_day
>
> Portugal     0.30     1       21dec2010     23dec2010    -2      0
> 0.5
> Portugal     0.33     1       22dec2010     23dec2010    -1      1
> 0.6                1.75=0.6+0.05+1.1
> Portugal     0.32     1       23dec2010     23dec2010     0      1
> 0.5                1.80=0.5+0.10+1.2
> Portugal     0.33     1       27dec2010     23dec2010     1      1
> 0.6                2.05=0.6+0.15+1.3
> Portugal     0.35     1       28dec2010     23dec2010     2      0
> 0.4
>
> Ireland      0.20     2       20oct2009     22oct2009    -2      0
> 0.1
> Ireland      0.21     2       21oct2009     22oct2009    -1      1
> 0.05
> Ireland      0.20     2       22oct2009     22oct2009     0      1
> 0.1
> Ireland      0.19     2       23oct2009     22oct2009     1      1
> 0.15
> Ireland      0.24     2       24oct2009     22oct2009     2      0
> 0.2
>
> Italy        0.26     3       04oct2010     06oct2010    -2      0
> 1.2
> Italy        0.29     3       05oct2010     06oct2010    -1      1
> 1.1
> Italy        0.31     3       06oct2010     06oct2010     0      1
> 1.2
> Italy        0.26     3       07oct2010     06oct2010     1      1
> 1.3
> Italy        0.25     3       08oct2010     06oct2010     2      1
> 1.1
>
>
> I tried different things but couldn´t find any fitting syntax. Can you help
> me?

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/