About SASstudent2013

SASstudent2013 · ‎06-21-2013

Hello, I need to compare means before and after study entry to see if there is a statistically significant difference between the two, and am wondering what the best way would be to evaluate this? I wanted to do logistic regression; however am unsure how to set this up. I need to do this for three separate models: ER visits, Hospital visits and Jail visits - and need to see if the average visits is different before and after study entry (in order to assess impact of treatment/counseling on these visits). Here is how the means are setup: proc means data=CostDrivers; var ERDAYS_PRE_4 ERDAYS_PRE_3 ERDAYS_3 ERDAYS_4; var HOSPDAYS_PRE_4 HOSPDAYS_PRE_3 HOSPDAYS_3 HOSPDAYS_4; var JAILDAYS_PRE_4 JAILDAYS_PRE_3 JAILDAYS_3 JAILDAYS_4; run; ERDAYS_PRE_4 = 12 months before study entry whereas ERDAYS_4 = 12 months POST study entry. Any ideas? Thanks!

SASstudent2013 · ‎06-10-2013

Yes a boxplot would be great. When I updated it that way the only values that show up with the boxplot are for timepoint 6. For the y-axis, I want it to be at x=0 so that the timepoints -12 and -6 are to the left of the y axis. Code: symbol1 interpol=boxcti color=red; symbol2 interpol=boxcti color=blue; symbol3 interpol=boxcti color=green; symbol4 interpol=boxcti color=black; axis1 order=(-12 to 12 by 1) offset=(0,0) label=none minor=none; axis2 order=(0 to 70 by 10) offset=(0,0) label=none minor=none; proc gplot data=CostDrivers; plot ERDAYS_PRE_3*time_6=3 ERDAYS_PRE_4*time_12=4 ERDAYS_4*time12=1 ERDAYS_3*time6=2 / overlay haxis=axis1 vaxis=axis2; run; quit; Here's the updated graph:

SASstudent2013 · ‎06-10-2013

I've attached the plot that I have right now and my code is at the bottom of this question screen. Here's what I still need to do with it/some questions: Add means as bars on the graph to designate the average of each of the four variables (ERDAYS_PRE_3 ERDAYS_PRE_4 ERDAYS_3 ERDAYS_4) Move the y-axis so that it is at 0 Add in values for ERDAYS_3 - for some reason they don't show up on the graph? CODE: /*Setup plot for ER cost driver data*/ symbol1 value=dot interpol=none color=red; symbol2 value=dot interpol=none color=blue; symbol3 value=dot interpol=none color=green; symbol4 value=dot interpol=none color=black; axis1 order=(-12 to 12 by 1) offset=(0,12) label=none minor=none; axis2 order=(0 to 100 by 10) offset=(0,0) label=none minor=none; proc gplot data=CostDrivers; plot ERDAYS_PRE_3*time_6=3 ERDAYS_PRE_4*time_12=4 ERDAYS_4*time12=1 ERDAYS_3*time6=2 / overlay haxis=axis1 vaxis=axis2; run; Thanks for your help!

SASstudent2013 · ‎06-10-2013

Thanks that works! How do I get the x and y axis to join at 0 so that -12 and -6 month timepoints are to the left of the y axis?

SASstudent2013 · ‎06-10-2013

Thanks, that works. How do I get the plot to not join lines between the datapoints? I just want to show the datapoints on the graph but do not want the points joined in any way.

SASstudent2013 · ‎06-10-2013

Thanks for the info... the range of values on the y-axis is the same for all, so won't be necessary to use 2nd axis I don't think. How would I set this up in Proc Gplot?

SASstudent2013 · ‎06-10-2013

Hello, I am looking to create a graph with the following characteristics: X-Axis: Timepoint (months) -12, -6, 0, 6, 12 *Note: the - refers to that many months before study entry Y-Axis: Days in Hospital at 12 months before study entry (coincides with -12 m timepoint) Y-Axis: Days in Hospital at 6 months before study entry (coincides with -6 m timepoint) Y-Axis: Days in Hospital at 6 months post study entry (coincides with 6 m timepoint) Days in Hospital at 12 months post study entry (coincides with 12 m timepoint) Each of those y-axis variables is one variable in the dataset. I want to create a scatterplot in a series format and then have the mean display on the graph. I tried using ODS graphics designer and am only able to create a scatter for one y-axis variable. Is it possible to do a series for this with the graphics editor? If not, how could I go about doing this? Thanks!

SASstudent2013 · ‎03-25-2013

Thanks everyone for your replies. I've updated the code based on your feedback and it worked perfectly. One issue is that I had 231 as the number of variables when it should have been 232.

SASstudent2013 · ‎03-25-2013

Hi. I need to update about 231 variables in a dataset so that the response is either a 1 or 0 for a specific number of observations. Right now, the response is a 1 or missing. To do this, I was going to setup an array in SAS so that the responses for all of the 231 variables would update to 0 if the original response was missing and a second variable response is 1. The variables that I want to update are "check1_5" through "check42_5". Variable "fu24yes" is a variable that denotes whether or not that person was part of the 24month followup (so that's the restriction). Do you know what I might be doing wrong? Code: data NewVar; ARRAY MedZero (231) check1_5--check42_5; DO i = 1 TO 231; IF MedZero(i) = . AND fu24yes=1 THEN MedZero(i) = 0; end; run; Log: 41 data NewVar; 42 ARRAY MedZero (231) check1_5--check42_5; ERROR: Variable check1_5 cannot be found on the list of previously defined variables. ERROR: Too few variables defined for the dimension(s) specified for the array MedZero. 43 DO i = 1 TO 231; 45 IF MedZero(i) = . AND fu24yes=1 THEN MedZero(i) = 0; 46 end; 47 run;

SASstudent2013 · ‎03-23-2013

Thank you!

SASstudent2013 · ‎03-22-2013

Thanks for catching that. I'm not writing the real names of these datasets because of confidentiality, so I mistyped when I wrote dummy names in the forum. Is it correct that when using the set statement, set must be the name of the existing dataset and the data step is the name of the new set? I updated code to reflect this and am not getting any error from the set statement. However, I am getting an error for the new variable. Code: data analysis2; /*create new dataset called "analysis2*/ set final322; /*from existing dataset called final322*/ IF vari1=. THEN vari2=.; /*create new variable called "vari2" that has either . or 1*/ ELSE IF vari1=(1 OR 0) THEN vari2=1; run; Log: 185 data analysis2; 186 set final322; 188 IF vari1=. THEN vari2=.; -- 180 189 ELSE IF vari1=(1 OR 0) THEN vari2=1; -- 180 ERROR 180-322: Statement is not valid or it is used out of proper order. (vari2 is underlined in the log referencing this error)

SASstudent2013 · ‎03-22-2013

Thanks. I think there's an issue with my libname statement. I have a dataset named 'test' in the folder 'Data1' and want to first create a permanent library, then create a new variable via above code. Do you know what I'm doing wrong with the below? Code: libname anaysis 'X:\Proj Mgmt FOLDER\FINAL DATASET\My Data\SAS data\Data1'; data test; set analysis.test1; 104 libname anaysis 'X:\Proj Mgmt FOLDER\FINAL DATASET\My Data\SAS 104! data\Data1'; NOTE: Libref ANAYSIS was successfully assigned as follows: Engine: V9 Physical Name: X:\Proj Mgmt FOLDER\FINAL DATASET\My Data\SAS 104! data\Data1 105 data test; 106 set analysis.test1; ERROR: Libname ANALYSIS is not assigned. ERROR: File WORK.analysis.test1.DATA does not exist.

SASstudent2013 · ‎03-22-2013

Hi. I am trying to create a new variable ('vari2) based on responses to another variable. To do this, I was going to use the set statement and keep getting the same error. Code and error are below. Any help is appreciated! data test; set test1; IF vari1=. THEN vari2=.; ELSE IF vari1=(1 OR 0) THEN vari2=1; run; 19 data test; 20 set test1; ERROR: File WORK.test1.DATA does not exist.

SASstudent2013 · ‎03-19-2013

This is how I start my code (and I get an error with the libname statement): libname data1; proc import datafile="...hosp.xls" out=hosp_data1; ERROR: data1 is not a valid SAS name. So not sure if that will help?

SASstudent2013 · ‎03-19-2013

Thanks. When I try it the first way, I get an error message saying the set statement doesn't exist... Code: data hosp_data; set data_case2; if . < labor < 37 then delivery=1; else if labor >= 37 then delivery=2; run; LOG ERROR: ERROR: File WORK.DATA_CASE2.DATA does not exist. Do you know why I'm getting that error?

Online Status	Offline
Date Last Visited	‎09-01-2015 07:12 AM

Comparing means before and after study entry - need insight

Re: Help creating graph with multiple series

Re: Help creating graph with multiple series

Re: Help creating graph with multiple series

Re: Help creating graph with multiple series

Re: Help creating graph with multiple series

Help creating graph with multiple series

Re: Array error

Array error

Re: Understanding set statement error

Comparing means before and after study entry - need insight

Re: Help creating graph with multiple series

Re: Help creating graph with multiple series

Re: Help creating graph with multiple series

Re: Help creating graph with multiple series

Re: Help creating graph with multiple series

Help creating graph with multiple series

Re: Array error

Array error

Re: Understanding set statement error

Re: Understanding set statement error

Re: Understanding set statement error

Understanding set statement error

Re: Creating new variable but everything goes missing?

Re: Creating new variable but everything goes missing?