j**********e 发帖数: 442 | 1 各位高手,我有个数据库只有cusip和公司名没有permno,大家有什么办法能给它们找到
permno? (公司名和crsp的公司名不完全一致) 多谢! |
|
j**********e 发帖数: 442 | 2 各位高手,我有个数据库只有cusip和公司名没有permno,大家有什么办法能给它们找到
permno? (公司名和crsp的公司名不完全一致) 多谢! |
|
b*****x 发帖数: 44 | 3 请问SDC里面的cusip是history 还是 current的?
跟 crsp 的cusip match的话,如何算是正确?
现在用 crsp 跟 compustat merged数据获得老的 cusip sic permno 等,然后跟
compustat 匹配找到accounting data.然后 用 cusip 日期去匹配sdc 的event数据。
看起来丢失不少。有点怀疑sdc的cusip. |
|
b*****x 发帖数: 44 | 4 请问SDC里面的cusip是history 还是 current的?
跟 crsp 的cusip match的话,如何算是正确?
现在用 crsp 跟 compustat merged数据获得老的 cusip sic permno 等,然后跟
compustat
匹配找到accounting data.然后 用 cusip 日期去匹配sdc 的event数据。看起来丢失
不少。有
点怀疑sdc的cusip. |
|
f********t 发帖数: 117 | 5 permno is crsp specific, other dbs dont have it.
crsp also has 8 digit cusip. so you need to make sure cusip in your db is
also 8 digit to match it. there wont be perfect match. |
|
s****d 发帖数: 244 | 6 各位大神,我用下面的代码合并两个数据库,但是合并后的数据库中prices都为
missing value。请教是怎么回事啊?谢谢!
data bm;
set bm;
rename standard_and_poor_s_identifier=gvkey
historical_CRSP_permno_link_to_C=permno
data_date=date
company_name=cname
common_shares_used_to_calculate=cshr
var7=eps
Market_Value___Total=market;
format date ddmmyy10.;
cyear=year(date);
quarter=qtr(date);
run;
data mylib.prices;
set mylib.prices;
format date date9.;
cyear=year(date);
quarter=qtr(date);
run;
proc sql;
cr... 阅读全帖 |
|
a*****e 发帖数: 159 | 7 on a.permno=b.permno and intck('month',a.date, b.date)=0 |
|
l*********g 发帖数: 177 | 8 先上2个代码
代码1:
proc sql;
create table temp1
as select distinct a.permno, b.*
from DivEvents a, caldates b
where b.evt_date-a.date =0
;
quit;
代码2:
proc sql;
create table temp1
as select distinct a.permno, b.*
from DivEvents a, caldates b
where b.evt_date=a.date
;
quit;
按我的理解,这2个代码照理应该是得到同样的结果。但是我发现结果居然极为不同,
其中代码1只生成了6000个observation,而代码2生成了210000个observation。代码2
是我要的结果,但是我不明白为什么代码1会有不同结果,我开始担心我是否其他code
里有出现相关的bug了。请大家指点一下怎么回事把?为什么不同结果呢?非常谢谢! |
|
|
|
D*****a 发帖数: 2847 | 11 用ftp软件例如filezilla上 sftp://Y****[email protected]
/wrds/crsp/sasdata/sd 下面有个stocknames的SAS数据
里面就是这种对应的信息 |
|
s***r 发帖数: 1121 | 12 use crsp.cstlink
This is very standard way. |
|
v*******y 发帖数: 5530 | 13 多种方法
但是先搞清楚cusip是historical cusip还是current cusip |
|
j**********e 发帖数: 442 | 14 多谢!不好意思,如何使用filezilla啊? |
|
m********5 发帖数: 619 | 15 SDC里面的cusip是historical cusip
应该和CRSP里面的 NCUSIP match |
|
s***r 发帖数: 1121 | 16 Check WRDS sample SAS code. |
|
s***r 发帖数: 1121 | 17 Check WRDS sample SAS code. |
|
j**********e 发帖数: 442 | 18 Does anybody know how to find permno for a list of companies in CRSP? Thanks
a lot! |
|
s*******e 发帖数: 226 | 19 Below is my SAS code for the problem. As you said, u_i would be
estimated as u_i~N(a,simga)if the intercept is specified as u_i (random)
only, then the coefficient of covariates should not change no matter a
is included or not. But it is not the case in my results.
"
proc mixed data=temp method=reml covtest ;
class permno year;
model loggev= lagq2 compiii softyr hardyr compiii*lagq2 softyr*lagq2
hardyr*lagq2 log_market_value diver pcsale_ratio
stockindexrt/ solution noint;
*noint is specified |
|
m**********r 发帖数: 122 | 20 正在看 data merge, 有个例子是这样得
data newdata;
merge yourdata (in=a) otherdata (in=b);
by permno date;
请问这里的(in=a) 和(in=b)是什么意思。 |
|
e****o 发帖数: 690 | 21 data input;
seed = 1245;
do id = 10000 to 99009 by 52;
do year = 2001 to 2008;
do i = 1 to 300 ;
return = abs(34.45 + rannor(seed*4)*5)/100 - rannor(seed*100)/5.05;;
if id < 50000 then datadate = mdy(12, 31, year) ; else datadate = mdy(6, 30
, year);
trade_date = datadate + i ;
output ;end; end; end;
drop seed i;
format datadate trade_date date9. ;
run ;
proc sort data = input; by permno trade_date ; run ;
%macro daily_return;
proc expand data = input out = i2 ;
id trade_date ;
by id ;
%do i = ... 阅读全帖 |
|