About trich12

trich12 · ‎08-14-2015

Hi all. I'm trying to create a random sample with some conditions. I have two datasets: Dataset 1 is 450 merger observations with variables: Acquirer ID, Target ID, Year of Merger, Target Industry Dataset 2 is 24,000 firm observations with variables: ID, Year, Industry For each Acquirer in Dataset 1, I want to draw a random sample from Dataset 2 with the same year of merger and the same industry as the actual target. I need to repeat this random sampling 500 times so that I have 500 pairings of the actual acquirer with random targets. Let me know if I need to clarify anything. Thank you for your help!

trich12 · ‎12-13-2013

Hai.kuo that worked well. Thanks!

trich12 · ‎12-13-2013

Hi everyone, I have a merging question. I have two datasets that I want to merge using an identifier and year. But I need to include a condition that if the year is not present in the second dataset, I would like to use the previous year's data entry. Here are examples of the data: Data 1: Firm Year 1004 1996 1160 1996 1235 1996 Data 2: Firm Year RepMeasure 1004 1995 0.36 1004 1996 0.42 1160 1995 0.11 1235 1995 0.78 1235 1996 0.69 For Firms 1004 and 1235, merging by firm and year is fine. For firm 1160 though, I don't have 1996 data so I need to use the 1995 RepMeasure. Let me know if I need to provide any more info. Thanks for your help!

trich12 · ‎10-04-2013

That worked perfectly! Thank you so, so much!

trich12 · ‎10-04-2013

Hi all! I have a dataset with county voting records for presidential elections. For example, County State Democrat_1992 Republican_1992 Democrat_1996 Republican_1996 Autauga AL 4819 8715 5015 9519 Baldwin AL 12195 26270 12776 29476 I want to transform this data so I can work with it more easily by having years as a column. I actually will need to linearly interpolate the data between the years, so ideally I need: County State Year Democrat Republican Autauga AL 1992 4819 8715 Autauga AL 1993 . . Autauga AL 1994 . . Autauga AL 1995 . . Autauga AL 1996 5015 9519 Baldwin AL 1992 12195 26270 Baldwin AL 1993 . . Baldwin AL 1994 . . Baldwin AL 1995 . . Baldwin AL 1996 12776 29476 So that I can then linearly interpolate for the years with missing data. I would really appreciate any help with this!! Thank you!

trich12 · ‎09-18-2013

Thanks for responding! The "event date" is the date the merger was announced, so there are two separate firms at this event time, but I'm only interested in the acquirers' returns. There are multiple events for some of the firms, and they can occur within this time frame of another later event. Some firms are involved in a merger every year for several years in a row. That's why I'm having trouble with this. I need to treat each merger as a single and separate event, get the returns for the acquirer's stock from day -205 to -6 before the announcement date, and then take the standard deviation of those returns. Does this help explain the data? I can attach the merger data if that will help, but obviously the daily stock return data is too large to attach.

trich12 · ‎09-18-2013

Hi all! I have one dataset with event dates of firm mergers and another dataset with the firm's daily stock returns for several years before and after the event. I'm trying to get the standard deviation of the stock returns from days -205 to -6 before the event. The two datasets share a firm identifier, permno. I can't figure out how to get the standard deviation for only that time period before the merger event. Any help will be appreciated! Thank you!

trich12 · ‎05-28-2013

I've been trying to run a proc sql and get a sort execution failure every time. Here is the code: proc sql; create table _temp (drop=evtdate) as select a.*, a.evtdate as _edate format date9., b.* from _temp a left join _caldates (drop=time) b on b.evtdate-a.evtdate>=0 group by a.evtdate having (b.evtdate-a.evtdate)=min(b.evtdate-a.evtdate); quit; And the error message: NOTE: SAS threaded sort was used. ERROR: Sort execution failure. 1247 quit; NOTE: The SAS System stopped processing this step because of errors. NOTE: PROCEDURE SQL used (Total process time): real time 1:08:58.65 user cpu time 2:08.34 system cpu time 11:55.76 Memory 68343k OS Memory 78456k Timestamp 5/22/2013 12:20:47 PM The dataset _temp has 9468 observations and 222 variables. The dataset _caldates has 9351 observations and 6 variables. I would not expect these datasets to be too large to cause this problem from what I've seen about the sort execution failure. Any help would be so appreciated! Thanks!

trich12 · ‎04-16-2013

This was perfect. Thank you!

trich12 · ‎04-04-2013

Thanks Patrick! I just attached 2 files with a few observations from my data. The file eventex contains the firm id (gvkey) and the date of the merger. The file prcex contains the firm id (gvkey) and the date and price for each month. My ideal result would be this for the first observation: gvkey __Date_Announced -14monthdate -14monthprice -3monthdate -3monthdate 1034 26JUL2004 20030531 21.02 20040430 21.73 I don't know if it's possible to do this with these two files, but thank you in advance if you can help at all!

trich12 · ‎04-02-2013

I have a file that contains merger events and monthly stock closing prices for several years around the event. I would like to extract the monthly closing prices for two specific months, month -14 before the event and -3 before the event. The variables are: merger date = __Date_Announced identifier = gvkey monthly closing price = PRCCM date for prices = datadate (which is in format yyyymmdd) I think I will need to extract the month from datadate, then get the prices for the -14 month and -3 month for each merger event. I just don't know the code to do this. Any help would be so appreciated! Let me know if I need to provide any more information. Thanks!

trich12 · ‎02-25-2013

Hi I have data in groups by specific dates and would like to duplicate the last line of observations for each group. For example, the first group has 10 observations for a certain date, and I would like the 11th line to be an exact duplicate of the 10th line. And I would like to do this for every group. Thank you for your help!

trich12 · ‎02-08-2013

Hi PG. I was just re-running this code and I'm getting several duplicate cnum matches. Do you know of any way to add into the code that I want 5 unique cnum matches? Thanks!

trich12 · ‎02-08-2013

Hi EdvinasS. I'm trying to use your code for matches since I'm looking for several matches for each event firm. I'm getting an error message that "year_event could not be found in the table/view identified with the correlation name S1". I get this error for year, industry, and size after the line "on s1.year_event = s2.year_control and ..." I've followed the code closely so I'm not sure what could be going wrong. Do you have any idea? Thanks for your help!

trich12 · ‎10-15-2012

I had used the original version, but the edited version was perfect. Thanks! Sorry to ask you to walk me through all this, but I've tried to get this on my own and couldn't do it. Now that I have one dataset with actual targets and their 5 closest matches, and another for actual acquirers and their closest matches, I want to merge those. I basically want 11 observations for every merger, where one is the actual acquirer and target, 5 are the close matches for the target paired with the actual acquirer, and 5 are the matches for the acquirer paired with the actual target. I have fewer targets than acquirers, so I'll need to make sure that I'm using only mergers where I have matches for both the actual target and actual acquirer. I hope this makes sense. I can't wrap my head around how to merge these datasets of matches with the actual mergers. I will really appreciate any help you can give!

Online Status	Offline
Date Last Visited	‎09-01-2015 07:11 AM

Random Sample

Re: merging with a condition

merging with a condition

Re: Data transformation

Data transformation

Re: Standard deviation of returns before event

Standard deviation of returns before event

sort execution failure

Re: event window

Re: event window

Random Sample

Re: merging with a condition

merging with a condition

Re: Data transformation

Data transformation

Re: Standard deviation of returns before event

Standard deviation of returns before event

sort execution failure

Re: event window

Re: event window

event window

How to duplicate a line

Re: Matching firms on industry and size

Re: help with sas code to match event companies with control companies...

Re: Matching firms on industry and size