gvkey date RET 10001 19940131 -0.04762 10001 19940228 0 10001 19940331 -0.00429 10001 19940429 -0.14493 10001 19940531 0.067797 10001 19940630 0.107302 10001 19940729 0.072464 10001 19940831 -0.02703 10001 19940930 0.038333 10001 19941031 -0.05405 10001 19941130 -0.04286 10001 19941230 -0.03343 10001 19950131 -0.03125 10001 19950228 -0.02621 10001 19950331 0.006377 10001 19950428 0 10001 19950531 0.05 10001 19950630 0.060317 10001 19950731 0 10001 19950831 -0.0303 10001 19950929 0.04375 10001 19951031 -0.0303 10001 19951130 0.09375 10001 19951229 0.082857   I have a large data set with many gvkey and monthly return(ret) like the above To calculate the annual return from monthly return, I have used the following code.    Data annual_returns; set return; return1= 1+ret; if first.date then return2= return1; else return2= return1*(lag(return2)); annual_return=return2-1; by gvkey date; run;   But I am not getting the expected result. I tried to use the codes available in the forum but none is giving me the expected result. The formula is given below. APY = (1+r1)*(1+r2) *(1+r3) *(1+r4) *(1+r5) *(1+r6) *(1+r7) *(1+r8) *(1+r9) *(1+r10) *(1+r11) *(1+r12) – 1 Let’s say the twelve monthly returns are 2%, 2.2%, 2.1%, -1.5%, 2%, 2.4%, 1%, -1.2%, -0.5%, 0.7%, 1%, and 1.5%. Using the above monthly returns, we can calculate the annualized returns as follows: APY = (1.02)(1.022)(1.021)(0.985)(1.02)(1.024)(1.01)(0.988)(0.995)(1.007)(1.01)(1.015) – 1 Annualized return = 0.1223 or 12.23%   What mistake am I making? What should be the correct code?  ... View more

gvkey fy TA 1700 1995 3311.662 1700 1995 1599.234 1700 1995 564.76 1700 1995 560.047 1700 1995 656.226 1700 1996 577.841 1700 1996 1696.431 1700 1996 1081.963 1700 1996 1727.069 1700 1996 4182.832 1700 1996 2068.554 1700 1996 841.204 1700 1996 . 84578 1995 1312.852 84578 1995 1131.176 84578 1995 3700.925 84578 1995 1099.786 84578 1995 848.657 84578 1995 1067.566 The above is my data and I want to get the following result.  gvkey fy TA Sum 1700 1995 3311.662 6691.929 1700 1995 1599.234 6691.929 1700 1995 656.226 6691.929 1700 1995 564.76 6691.929 1700 1995 560.047 6691.929 1700 1996 4182.832 10756.85 1700 1996 2068.554 10756.85 1700 1996 1727.069 10756.85 1700 1996 1696.431 10756.85 1700 1996 1081.963 10756.85 1700 1996 841.204 . 1700 1996 577.841 . 1700 1996 . . 84578 1995 3700.925 8312.305 84578 1995 1312.852 8312.305 84578 1995 1131.176 8312.305 84578 1995 1099.786 8312.305 84578 1995 1067.566 8312.305 84578 1995 848.657 .   I want to get the sum of the first 5 highest observations. I have used the following code.    proc sort data= have; by gvkey fy decending TA; run; Proc sql; create table want  as select *,sum(TA) as sum from have group by gvkey, fy; quit;   I get the sum but if I have more than 5 observations in the TA column, I get sum for all of the observations. I want the sum for only the first 5 highest observations. And most importantly I don't want to lose any other rows also. I need to have all the rows in my output. Can anyone please help? ... View more

Hi,   I want to calculate the customer arrival rate. A customer arrives in the store in how many minutes. For example, from our data, we may get that a customer arrives at the store in every 7 min.    if we have two columns, one for "minute" and the other for "no of the customer", what would be the SAS code? This is a Poisson distribution. Please help   Minute  "Customer of customers" 5                    2 10                 6 7                   3 6                   1 4                   2 9                   5 11                 4 2                  3 8                  5   So, I want to get " In every how many minutes a customer come?". This is the property of Poisson distribution. The above is just an example. The answer could be " a customer comes in every 1.5 min".      ... View more

SIC Year share Dummy 5080 2010 1489.499   5080 2010 68.57   5080 2011 1193.963   5080 2011 427.454   5080 2012 134.285   5080 2012 1151.153   5080 2012 0   5080 2012 157.123   5080 2012 62.593   4512 2010 2455.718   4512 2010 873.324   4512 2011 403.31   4512 2011 0   4512 2011 357.093   4512 2011 243.378   4512 2012 724.538   4512 2012 421.442   4512 2012 198.51   3670 2010 34.59   3670 2010 32.13   3670 2010 143.4   3670 2010 15.883   3670 2010 0.522     Hi, I want to create a dummy variable from the column "share". if the share is above the median then 1 else 0. Median is calculated by SIC 2, 3, and 4 digits and by year. I can solve it step by step procedure. It will take multiple steps. Is there any procedure by which I can do the above in one step?  ... View more

Rank TDC1 GVKEY Year Percentage of TDC1 1 5237.743 1004 2010 0.4265 2 2554.467 1004 2010   3 1578.104 1004 2010   5 1314.079 1004 2010   4 1596.902 1004 2010   1 5786.4 1004 2011   2 2781.156 1004 2011   4 1696.431 1004 2011   3 1727.069 1004 2011   1 4182.832 1004 2012 0.4386 2 2068.554 1004 2012   5 841.204 1004 2012   3 1312.852 1004 2012   4 1131.176 1004 2012   1 3700.925 1013 2010 0.4832 2 1099.786 1013 2010   5 848.657 1013 2010   3 1067.566 1013 2010   4 941.748 1013 2010   1 5231.393 1045 2010 0.3532 4 2372.14 1045 2010   5 1776.069 1045 2010   3 2288.908 1045 2010   2 3142.082 1045 2010     Hi, I need help for the following. 1. The ranks in the above data are created based on the TDC1. There should be 5 TDC1 observations based on each year. But if you look at 2011, it misses one observation. So, I want to delete all the observations in that year. I have a huge data set. In that data set, if I have less than 5 TDC1 observations in each year or GVKEY, I have to remove all the observations for that particular year and GVKEY. I want to be consistent throughout so that I will have 5 TDC1 observations for each year for different GVKEY. Can anyone please help me by giving me SAS code for that?   2. I need to find the percentage of TDC1 for each year and for Rank 1. An example is given in the last column above.  the percentage for the first row is (5237.743/(5237.743+2554.467+1578.104+1314.079+1596.902).  Please give me SAS code for this too.      ... View more