Hi I need to find the median of the size variable for each country in my panel dataset and create a dummy variable:1 for values >median and 0 otherwise. I read and also realised while doing,that the median function does not work using Proc SQL.So,I tried the simple Proc Panel command: Having sorted the data by country,firm and year,I used the following steps: proc panel data=have; by country; new=median(size); run; The error that comes up is: Statement is not valid or it is used out of proper order. Can anybody advise about the median? ... View more

Hello Could anybody guide me on this merge task? Dataset 1(WB) Country         newyear                   Var1 A                     1995                   x1 A                     1996                   x2 A                     1997                   x3 B                     1995                   x4 B                     1996                   x5 Dataset 2(countries) Country          newyear                  Firm A                    1995                  y1 A                    1995                  y2 A                    1995                  y3 A                    1996                  y1 A                    1996                  y2 B                   1995                   z1 B                   1995                   z2 B                   1996                   z1    B                   1996                   z2 Now I need to merge these two datasets: basically assign each country's value for each year to each of the firms in that country for the corresponding year. It is a one-to-many merge. I used these codes. "DM 'log;clear;output;clear'; proc import out= work.WB datafile= "C:\Users\saikia\Desktop\WB.csv" DBMS = csv replace; Getnames= yes; run; data WB1; set WB; newyear=year*1;        /*Initially, an error popped up that v46 that represented the year was both numeric and alphanumeric and so I created the variable 'newyear' for both datasets'*/ run; proc sort data = work.WB1; by  newyear year; run; proc import out= work.countries datafile= "C:\Users\n\Desktop\country.csv" DBMS = csv replace; Getnames= yes; run; data countries1; set countries; newyear=v46*1; run; proc sort data = work.countries1; by  country newyear; run; data work.combined; merge work.WB1(in = in1) work.countries1(in = in2); by country newyear; if in1& in2; run;" The error that appears now is: ERROR: BY variables are not properly sorted on data set WORK.WB1. Could anybody please help me? Thanks! ... View more

Hello Could anybody tell me how to compute std dev of a variable in panel data?Is this right? data want; set have; by gvkey year; vol=std(variable); run; I tried this but the error is:   The STD function call does not have enough arguments. thanks. ... View more

I have created a dummy 0/1 against years prior to an event and after an event. I want to delete firms that have  dummy=0 less than 2 times and dummy=1 less than 3 times. Is it possible to combine both the conditions? The code below is wrong but what should be be corrected below? proc sql; create table want as select dummy,count(dummy=0) as count1 select dummy,count(dummy=1) as count2   from have    group by gvkey having calculated count1 gt 2 & count2 gt 3 ; quit; ... View more

I need to regress the monthly returns of each firm(180 obs for each firm) on the returns of a particular commodity for that period(180 observations). I have the data ready: one sheet containing returns of several companies and the commodity returns on the other hand. While regressing in SAS, do I paste the returns of the commodity against each firm manually on the worksheet or is there some code in SAS that can directly regress each firm's returns on the commodity returns? Right now,the data sheet looks like: date     firm       firmret     commodityret 1          a          10               100 2          a          11               200 3          a          12               300 1          b          16               2          b          17               3          b          18               1          c          10 2          c          8 3         .c          11 I need to regress firms' a,b,c....returns on commodityret.So,do i paste commodity returns  for each firm on the commodity ret column? If anybody can suggest the solution for Stata too,it is fine.         ... View more