About whs278

whs278 · ‎08-03-2020

Hi, This is a stats/PROC SURVEYREG question related to fixed effects models. I am using PROC SURVEYREG to estimate graduation rates. The model includes fixed effects for schools and a continuous running variable called RANK, which is a number that schools assign students based on their middle school GPA and test scores. What I want to know is how do I calculate an estimated overall average graduation rate for a particular value of RANK. Currently, I know that intercept actually represents one of the school indicator variables that was dropped due to multicollinearity. Here is an example of the code. PROC SURVEYREG DATA = HAVE; CLASS SCHOOL; MODEL GRADUATION = SCHOOL + RANK / SOLUTION; RUN: What I want to know is, for example, what would be the overall average graduation rate for a given value of RANK such as RANK = 10. Thanks for any help. Please let me know if there is any additional information I can provide. Sincerely, Bill

whs278 · ‎07-13-2020

Hi @CaseySmith , Thank you for your response. Has there been any improvements on this issue in the past three years? I have had a couple instances in the past few months where I had to contact our data manager in order to stop an out of control SAS process because I couldn't stop it client side. Sincerely, Bill Spagnola

whs278 · ‎07-08-2020

Hi, I have a complicated process flow in a SAS EG project (SEE IMAGE BELOW). What I want to be able to do is to run one of the programs at then end of the process tree that would automatically run all the previous workflows without running any program in another node. For example, I would like to run the APPENDIX_PLOTS program and PREPARE_DATA without running TABLES or APPENDIX_ TABLES. This is because APPENDIX_TABLES needs the CTEREP_STU dataset which is created by PREPARE_DATA. However, I don't need to run TABLES or APPENDIX_TABLES again for awhile and both programs take a long time to run. I know I could individually select PREPARE_DATA and APPENDIX_PLOTS and then click run. However, I was wondering if there is a way to select an end node and then automatically run all the programs that the end node depends on. I also know I could click PREPARE_DATA and click "run branch". However, this will also run TABLES and APPENDIX_TABLES, which again I do not want to rerun. Thanks for any help on this topic. Thank you so much. Sincerely, Bill

whs278 · ‎06-02-2020

I noticed that if I run the following code in SAS EG.... ODS _ALL_ CLOSE; ODS LISTING; I am able to shut down the ODS HTML output and keep the ODS LISTING output. However, the next time I run something interactively in SAS EG, it automatically goes back to the default results output. Is there a way to use code in SAS EG to close ODS results for a given session until I explicitly reopen them? Thank you very much. -Bill P.S. I know how to change the Results settings by selecting Tools / Options in the menu bar, but I was wondering if there was a way to explicitly control outputs in code.

whs278 · ‎05-18-2020

Thanks. Yeah, I admit that it is probably not a typical request and will probably not make much sense, even if I try to explain it. Anyway, here is my explanation. I actually don't want to create an output file. I just want to have a file that I can quickly reference located in the Process Flow window. I guess it would make sense to follow ballard's advice and use only one output that allows graphics instead of using ODS listing plus ODS html. However, there is a few reasons why I would like to use ODS listing plus another output that supports graphs. First, I find the table formats created by ODS listing to be more visually appealing. Second, using two different formats will help me remember which programs do what in a given EGP.

whs278 · ‎05-18-2020

Thanks for the tip, Reeza. Is there a way to do this using code? For example, I have a project with several programs. Some of them produce tables and others produce graphs such as histograms. I was wondering if there was a way to run code that would only produce HTML output for the programs that produce graphs and only produce LISTING output for the programs that produce tables.

whs278 · ‎05-18-2020

I'm using EG. I noticed that ODS _ALL CLOSE; ODS LISTING; works for the first output I produce but HTML is produced for all subsequent output.

whs278 · ‎05-18-2020

Hi, I would like to use code to suppress HTML output while keep the LISTING output. I tried running ODS HTML CLOSE; ODS LISTING; However, I still get an html output along with the listing output. Thanks for the help. Sincerely, William Spagnola

whs278 · ‎04-22-2020

Him I would like to be able to pass a numeric range such as 2013:2017 into a macro and then iterate over it through it with a do loop. It would look something like what I have below. I have wrote ....... where I am not sure of what to do. %some_macro(year); %do ......... ; %let year_i = ............ ; %put year_I; %end; %mend some_macro; I would like it to work with a range. %some_macro(2013:2017); But I also would like it to work with a single number. %some_macro(2013); Or with a list of numbers. %some_macro(2013 2015 2018) Not sure if this is possible or practical SAS, but i thought it would be interesting to try. Thanks for the help. -Bill

whs278 · ‎03-31-2020

What is the best way to transport a macro across projects in SAS Enterprise Guide? I know you can write an %include statement, but this seems to require saving a files as .sas instead of .egp. I was wondering if there was a more efficient way to do this in SAS EG? Thanks, Bill

whs278 · ‎03-10-2020

I'm not sure how the solution below provides an answer on how to write a PROC GLM step that would jointly test a set of parameters using a partial f-test. ------------------------------------------------------ Y = B0 + B1*Asian + B2*Black + B3*White + B4*X + B5*X*Asian + B6*X*Black + B7*X*White + e The CLASS RACE statement creates dummy variables (Asian, Black, White) with values (1,0,0) for RACE="Asian", (0,1,0) for RACE="Black" and (0,0,1) for RACE="White". SAS will force parameters B3 and B7 to zero because they are redundant, so that the linear equations are: Asian : Y = (B0+B1) + (B4+B5)*X Black : Y = (B0+B2) + (B4+B6)*X White : Y = B0 + B4*X The F test for effect RACE*X tests the hypothesis B5=B6=B7=0 which, if true, would mean that all slopes are equal. hth PG Message was edited by: PG corrected typo reported by Steve Denham. PG View solution

whs278 · ‎03-10-2020

This is not the answer

whs278 · ‎03-10-2020

Hi, I know you can do a partial F-test with PROC REG to jointly test a set of parameters. For example, PROC REG DATA = dataset MODEL y = x1 x2 x3; TEST x2=x3=0; RUN; Which gives me output that looks like this. I would like to know if there is a way to perform the same the test using PROC GLM. Thank you very much. Sincerely, Bill

whs278 · ‎03-10-2020

Thank you. Running the ODS _ALL_ CLOSE statement before the ODS OUTPUT statement did the trick.

whs278 · ‎03-04-2020

Okay, I realize that for this program i used proc reg, so i can use an output statement to save the parameter estimates into a dataset without using ODS. However, I have a similar program where I use proc surveyreg instead. As far as I know, there is no way to save the parameter estimates from proc survey reg without using ODS OUTPUT. However, I don't want to actually print anything or create any html files, hence the ODS exclude statement. All I want to do is save the parameter estimates into a dataset. The problem is that even when using the ODS exclude statement, a blank html file is still created. I want to know if there is any way to use the ODS OUTPUT statement without creating an html file, or, at the very least, if there is a way to delete the html file after it is created using some SAS procedure.

Online Status	Offline
Date Last Visited	‎11-20-2023 06:04 PM

Re: Use different markers for groups in a scatter plot

Re: Output all rows from PROC SGPANEL into single PNG file

Output all rows from PROC SGPANEL into single PNG file

Re: Is there a SAS style guide

Re: Looking for Non-SAS Data within a directory

Looking for Non-SAS Data within a directory

Re: Division Function Not returning exact decimal place.

Division Function Not returning exact decimal place.

Re: Using PROC MIXED to estimate PSM treatment effects that vary at sc...

Using PROC MIXED to estimate PSM treatment effects that vary at school...

Re: SGPLOT VBOX Change Category Color

Re: SGPLOT VBOX Change Category Color

Re: Use different markers for groups in a scatter plot

Re: Output all rows from PROC SGPANEL into single PNG file

Re: ODS output with an extra 1 at the end of the image name

Re: Partial F-Test in PROC GLM

Partial F-Test in PROC GLM

Re: Partial F-Test in PROC GLM

Re: Using PROC MIXED to estimate PSM treatment effects that vary at sc...

Re: %PUT STATEMENT WONT PRINT TO LOG

PROC SURVEYREG: Find Grand Mean at certain value of X when you have fi...

Re: Why doesn't EG stop when I click Stop???

Running Process Flows; Run all programs that an end node depends on

Suppress ODS and keep it suppressed when working with Enterprise Guid...

Re: Using ODS Listing while suppressing ODS HTML

Re: Using ODS Listing while suppressing ODS HTML

Re: Using ODS Listing while suppressing ODS HTML

Using ODS Listing while suppressing ODS HTML

How pass a numeric range or list into a macro and then create a do loo...

What is the best way to transport macros across projects in SAS Enterp...

Re: Partial F-Test in PROC GLM

Re: Partial F-Test in PROC GLM

Partial F-Test in PROC GLM

Re: Delete HTMLfile and SAS Report using SAS code

Re: Delete HTMLfile and SAS Report using SAS code