About sasphd

sasphd · ‎01-26-2015

ods output ResidSummary

sasphd · ‎01-26-2015

I perform a GMM in proc model and I want to keep the R-square of the regression. I keep the parameters estimated ods output ParameterEstimates I try to keep the R-square using ods output FitStatistics= but it does not work

sasphd · ‎11-26-2014

I reformulate my question. To be more clear In this link http://www.math.wpi.edu/saspdf/stat/chap18.pdf page404 Figure 18.2. Skeletal Box-and-Whisker Plot. They draw the box from 25th to 75 percentiles I want to do it from 10th to 90th percentiles

sasphd · ‎11-26-2014

Hello, In proc boxplot, how to draw the boxes from the 10th and the 90th percentiles in place of the distance from 25th and 75th percentiles (which is by default). In other words, I want the boxes to be lager?

sasphd · ‎11-24-2014

I want to join two tables in this way Table 1 A B 2 3 6 5 Table 2 C D 9 6 5 5 table want A B C D 2 3 9 6 6 5 5 5

sasphd · ‎11-19-2014

thanks for your help.

sasphd · ‎11-19-2014

thanks. I have generated the file with rolling window using your program. After that when I run my program (proc model) using by id grp, SAS makes the error message of unsufficient memory because my file is very huge like 17214480 lines. That is why I want to use macro.

sasphd · ‎11-19-2014

I am working on a research project and have trouble come up with a way to conduct a rolling window regression. In my proc model I include this macro to do my rolling window. %do fen = %eval(&dfen) %to 100; where %eval(&fen) le obs le %eval(36+&fen-1); However, my proc model is done by id and as you can see in this macro I suppose that the number of observations is 100 for each id but this is not true I have a different number of observation for each id. In my database I add a column which indicates the number of total number of observation for each id (nb). How can I change the fixed number 100 to a changing variables called nb? I try to do it like this : %do fen = %eval(&dfen) %to %eval(&nb); where %eval(&fen) le obs le %eval(36+&fen-1); but I have this error ARNING: Apparent symbolic reference NB not resolved. ERROR: The text expression &NB contains a recursive reference to the macro variable NB. The macro variable will be assigned the null value.

sasphd · ‎11-19-2014

can you please help me in doing this directly in proc model to save time ?? I am working on a research project and have trouble come up with a way to conduct a rolling window regression. In my proc model I include this macro to do my rolling window. %do fen = %eval(&dfen) %to 100; where %eval(&fen) le obs le %eval(36+&fen-1); However, my proc model is done by id and as you can see in this macro I suppose that the number of observations is 100 for each id but this is not true I have a different number of observation for each id. In my database I add a column which indicates the number of total number of observation for each id (nb). How can I change the fixed number 100 to a changing variables called nb? I try to do it like this : %do fen = %eval(&dfen) %to %eval(&nb); where %eval(&fen) le obs le %eval(36+&fen-1); but I have this error ARNING: Apparent symbolic reference NB not resolved. ERROR: The text expression &NB contains a recursive reference to the macro variable NB. The macro variable will be assigned the null value.

sasphd · ‎11-19-2014

However I have a lot of variables in my table not only a and b. So writing the program of xia will be long also.

sasphd · ‎11-19-2014

I want to estimate the volatility of a variable which I already estimate with proc model. I know that I can save my variable and calculate its volatility with proc means but I want to estimate its volatility in proc model to test for its equality with another variable. I try to do that to test for the equality of standard deviation of variables A and B. test std(A)=std(B); but it does not work. I have this message. ERROR: The function STD requires at least 2 arguments. There are too few arguments for the function STD.

sasphd · ‎11-19-2014

I am working on a research project and have trouble come up with a way to conduct a rolling window regression. In my proc model I include this macro to do my rolling window. %do fen = %eval(&dfen) %to 100; where %eval(&fen) le obs le %eval(36+&fen-1); However, my proc model is done by id and as you can see in this macro I suppose that the number of observations is 100 for each id but this is not true I have a different number of observation for each id. In my database I add a column which indicates the number of total number of observation for each id (nb). How can I change the fixed number 100 to a changing variables called nb? I try to do it like this : %do fen = %eval(&dfen) %to %eval(&nb); where %eval(&fen) le obs le %eval(36+&fen-1); but I have this error ARNING: Apparent symbolic reference NB not resolved. ERROR: The text expression &NB contains a recursive reference to the macro variable NB. The macro variable will be assigned the null value.

sasphd · ‎11-18-2014

thanks a lot

sasphd · ‎11-18-2014

But the order of observations is very important for me?????????????

sasphd · ‎11-18-2014

Hello, I try to do a rolling window. I have this program. data rolling(keep=grp id a b) / view=rolling; do grp = 0 to nbid-9; do j = 1 + grp to 9 + grp; set test nobs=nbid point=j; output; end; end; stop; run; My data have the form id a b 1 1 8,00 1 2 6,00 1 3 5,00 1 4 3,33 1 5 1,83 1 6 0,33 1 7 -1,17 1 8 -2,67 1 9 -4,17 1 10 -5,67 I want to create a rolling window with 9 obsevations by id. Result id a b 1 1 8,00 1 2 6,00 1 3 5,00 1 4 3,33 1 5 1,83 1 6 0,33 1 7 -1,17 1 8 -2,67 1 9 -4,17 1 2 6,00 1 3 5,00 1 4 3,33 1 5 1,83 1 6 0,33 1 7 -1,17 1 8 -2,67 1 9 -4,17 1 10 -5,67 In attachement you can find the data. My program do not work well with different id. It work well when I have just one id. I need help?

Online Status	Offline
Date Last Visited	‎11-08-2024 11:07 PM

how to get Residuals Standard Deviation in output proc model

change date format from Best12. / informat 12. to yymmn6.

create dummy by ticker and year

Re: change date format from $10.

change date format from $10.

select variables

Re: select the last observation by id and date

select the last observation by id and date

Re: date difference in year between two date YYMMDDN8.

Re: date difference in year between two date YYMMDDN8.

Re: change date format from Best12. / informat 12. to yymmn6.

Re: change date format from Best12. / informat 12. to yymmn6.

Re: change date format from Best12. / informat 12. to yymmn6.

Re: create dummy by ticker and year

Re: change date format from $10.

add day to format date

Re: change format form char $28 to numeric

Re: Proc model and R_square

Proc model and R_square

Re: proc boxplot

proc boxplot

join two table

Re: macro for a rolling window regression

Re: rolling window

macro for a rolling window regression

Re: rolling window

Re: rolling window

Testing the equality of std of two prameters

macro for a rolling window regression

Re: rolling window

Re: rolling window

rolling window