ah there it is 9.2M1 ... View more

Hi: This is not really an ODS GRAPHICS or SAS/GRAPH question. It should be posted in the ODS and Base Reporting forum: http://support.sas.com/forums/forum.jspa?forumID=6 Or, since your question involves EG, you might want to post this in the EG forum -- I believe there is a task in EG to copy files back and forth, if needed. For more help with the FILE= option and the PATH= option (which you may need to use in this instance), you might want to open a track with SAS Tech Support or refer to this Tech Support note: http://support.sas.com/kb/23/638.html http://support.sas.com/kb/12/119.html cynthia ... View more

Hi: I do not believe that you can control the page-breaking with SAS -- once the stored process got to Excel -- every person who runs that stored process could set different page layout and printing options that would impact the place where Excel put page breaks. Is there anyway to make your BY groups "smaller" by adding more BY variables into the BY statement??? Also, this is one of those instances where it might be useful to see your stored process code and for you to explain how you populate the multiple tabs (whether the stored process does it automatically or whether you are creating new sheets by selecting "New Sheet" in the popup window for the SAS Add-in for Microsoft Office.) cynthia ... View more

Have a look at AMO (Add on for Microsoft Office) and stored processes ... View more

You can use INTCK to count weeks based on a "date" and a "year start date". Scott Barry SBBWorks, Inc. Suggested Google advanced search argument, this topic / post: week interval site:sas.com Also, SAS Language DOC on topic: About Date and Time Intervals http://support.sas.com/documentation/cdl/en/lrcon/62955/HTML/default/viewer.htm#a000990883.htm ... View more

Hi: You might want to look at the documentation http://support.sas.com/documentation/cdl/en/statug/63033/HTML/default/viewer.htm#/documentation/cdl/en/statug/63033/HTML/default/statug_surveyselect_sect007.htm and see whether the METHOD= option offers you a method closer to your liking (by my count, there are at least 10 or 11 methods to try). As it says on the above page: "If you do not specify the METHOD= option, by default, PROC SURVEYSELECT uses simple random sampling (METHOD=SRS) " and the doc for the SRS method explains that SRS is simple random sampling, which is selection with equal probability and without replacement. And for more information about simple random sampling, you are further referred to: http://support.sas.com/documentation/cdl/en/statug/63033/HTML/default/viewer.htm#/documentation/cdl/en/statug/63033/HTML/default/statug_surveyselect_a0000000153.htm cynthia ... View more

I think this is all you need to keep. You might have to set the XPIXELS and YPIXELS to something other than 0 for the graph to work properly. OPTIONS DEV=ACTIVEX; GOPTIONS XPIXELS=0 YPIXELS=0; data QUERY2; set QUERY; run; proc freq data=QUERY2; table size*error/nocol nocum nofreq nopercent; PROC SQL; CREATE VIEW WORK.SORT AS SELECT T.mean_error, T.mean_sample_error, T.size, t.error FROM WORK.QUERY2 as T order by t.size ; QUIT; SYMBOL1 INTERPOL=NONE HEIGHT=10pt VALUE=CIRCLE LINE=1 WIDTH=2 ; Axis1 STYLE=1 WIDTH=1 MINOR=NONE order= -10 to 10 by 1 ; Axis2 STYLE=1 WIDTH=1 MINOR=NONE; TITLE; TITLE1 "Scatter Plot"; FOOTNOTE; PROC GPLOT DATA=WORK.SORT ; by size; PLOT mean_sample_error * mean_error=error / vref=(-.5 .5) VAXIS=AXIS1 HAXIS=AXIS2 FRAME ; RUN; QUIT; TITLE; FOOTNOTE; Message was edited by: Adrian Mc ... View more

Why do you specify that you want the regression line to pass through each point and that the line segment between each point should be a straight line. If that is what you really want, then no regression function is needed. But be advised that you are treating the response variable as being measured without error. Is that what you really want to assume? Is it defensible to assume that the response should have no error term? Also, can it be assumed that the values of the response variable are all positive? If the response is positive and the response is subject to some measurement error, then I would consider fitting a regression model in which the expectation is modeled as    E[Y | X] = exp(b0 + b1*x) where b1 is negative. If the residual error variance is not constant but is proportional to E[Y | X]^2, then the proper way to model this would be to model log(Y). With only 6 data points, you might not be able to determine whether the variance is constant or whether the variance is proportional to E[Y | X]^2. However, it is generally the case that the variance increases with the expectation making the log transformation the appropriate model. You can add some flexibility to the above model by including higher order terms such as x^2. Thus, you could model the expectation function as:    E[Y | X] = exp(b0 + b1*x + b2*x^2) With only 6 observations (per subject or whatever unit you need to loop over), I would not go above a quadratic term when expressing the expectation function. One more question. What do the 2000 sets represent? Might it be reasonable to assume that the regression function should be represented as    E[Y | X] = exp(b0+g0{i} + (b1+g1{i})*x) where g0{i} and g1{i} are random effects which represent offsets from the intercept and slope for the i-th subject? Be sure that a lot more questions could be asked in order to provide a proper solution to your problem. Have you considered consulting with a statistician that you can talk with directly. You would probably get a better result by talking in person with someone who can ask appropriate questions as your full problem unfolds. ... View more

Yes there is a way. Key words: READPHASES= and READINDEXES= You may have to use these options in the code, I don't recall them being in an EG task. Conceptually you willl have two sets of control limits, one for phase one and another for phase two, etc. of the data. This link will / should take you to the on-line documenation and an example: http://support.sas.com/documentation/cdl/en/qcug/63922/HTML/default/viewer.htm#/documentation/cdl/en/qcug/63922/HTML/default/qcug_shewhart_a0000003894.htm ... View more

Hi, In answer to your initial post, it should be real easy to get the cumulative average: data have;   attrib month format=$20. month_id value format=best.;   infile datalines delimiter=",";   input month $ month_id value; datalines; jan,1,45 feb,2,32 mar,3,67 apr,4,34 ; run; proc sql;   create table WANT as   select  A.*,           (select SUM(VALUE) from WORK.HAVE where MONTH_ID <= A.MONTH_ID) / (select COUNT(MONTH) from WORK.HAVE where MONTH_ID <= A.MONTH_ID) as CUMULATIVE_AVG   from    HAVE A; quit; In answer to your latest post (which I just posted on the other post), with the groupings: data have;   attrib id time_period income format=best.;   infile datalines delimiter=",";   input id time_period income; datalines; 1,1,45 1,2,32 1,3,67 1,4,34 2,1,23 2,2,89 2,3,78 2,4,10 ; run; proc sql;   create table WANT as   select  A.*,           (select SUM(INCOME) from WORK.HAVE where ID=A.ID and TIME_PERIOD <= A.TIME_PERIOD) as TOTAL,           CALCULATED TOTAL / (select COUNT(ID) from WORK.HAVE where ID=A.ID and TIME_PERIOD <= A.TIME_PERIOD) as CUMULATIVE_AVG   from    HAVE A; quit; ... View more

Richard, In EG 4.3, would this be how/why you would use File => New => Report? Regards, Don H ... View more

In the past I have often written sas code which runs on our unix server and uses ftp to get a list of the files in a directory on a Windows server (assuming the windows server is accepting ftp connections). Assuming the spreadsheets are all in the same format, I would use the Import Data task in EG once, to set up the code to create the output table. Then I take the list of files I got above and ftp the files one by one (in sas code) from a windows server. I use my import data code to read the file into a data table and then insert that into a final table, which has the data for all the files. If that's of some use to you I could send on some sample code? ... View more

If you don't specify an "order={min} to {max} by {something}" in your axis statements, then the plot and plot2 axes will each auto-scale based on the data that's being plotted against that axis. One alternative to plotting the 2 lines via plot and plot2 is to plot them both with the plot statement (using the 'overlay' option). You will only get an axis on the left side, and you are guaranteed that axis is auto-scaled the same for both lines (ie, because it *is* the same axis 🙂 ... View more

It's true that all compute processing takes place on the server. However, if you reference local data sources (SAS data sets, Excel files, etc), these must be read and moved to the server for processing, and that can consume resources on your PC. I'd suggest working with SAS Technical Support to diagnose the situation. They will probably ask for a sample project and log that shows the symptoms you're seeing, and might be able to advise how to optimize it. Chris ... View more