cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Search instead for 
Did you mean: 
greveam
‎11-28-2023
  • 49 Posts
  • 6 Likes Given
  • 1 Solutions
  • 0 Likes Received

Re: proc pls variable importance output to proc mianalyze

by Quartz | Level 8 in SAS Programming
‎12-14-2018 06:55 AM
‎12-14-2018 06:55 AM
1. Thanks I found the macro.   2. The documentation states that the definition of parameter estimates is: "...also called coefficients, are the change in the response associated with a one-unit change of the predictor, all other predictors being held constant."    So when you say VIP is not a parameter estimate, is that correct? The way I read the SAS documentation, VIP is a scaled model estimate of how much the Y changes for a standardized change in predictor variables (i.e. a parameter estimate that can be rank the "importance" of both continuous and class variables)? The problem for proc mianalyze is that there is no associated standarderror with the VIP estimate - maybe it could be bootstrapped?   Cheers, Anders     ... View more

Re: proc pls variable importance output to proc mianalyze

by Quartz | Level 8 in SAS Programming
‎12-14-2018 01:02 AM
‎12-14-2018 01:02 AM
Both questions. Thanks, Anders ... View more

proc pls variable importance output to proc mianalyze

by Quartz | Level 8 in SAS Programming
‎12-13-2018 03:53 PM
‎12-13-2018 03:53 PM
Hi, I have a dataset with some imputed variables using proc mi. Now I want to determine which explanatory variables are most important an exposure of interest (SBP). My idea was to use proc pls and rank the variables by their calculated variable importance score. However, I am not sure how I can output that to a format that can be used by proc mianalyze to account for the imputed values? Any help would be greatly appreciated. Thanks!   Here is the code I've tried:   proc pls data=have nfac=4 method=pls (algorithm=nipals maxiter=300) plot=XLoadingProfiles details CENSCALE outmodel=est1 cv=one varss plot=(ParmProfiles VIP); class female; model sbp = age female bmi dbp gfr / solution; output out=plsscored XSCORE=xscore STDY=STDY STDX=STDX; id subject; by _imputation_; run;   proc mianalyze parms(classvar=full)=want; modeleffects intercept "VIP"; ods output ParameterEstimates=info; run; ... View more

BESTDw.p format in proc iml

by Quartz | Level 8 in SAS Programming
‎12-11-2018 09:32 AM
‎12-11-2018 09:32 AM
Hi, I want to format p in the macro below so that I can report the exact p-value. I tried using the bestd32.31 format but still get a p rounded as 0. Any help would be much appreciated. Thanks!   %macro combchi(df=,chi=); proc iml; df=&df; g2={&chi}; m=ncol(g2); g=sqrt(g2); mg2=sum(g2)/m; r=(1+1/m)*(ssq(g)-(sum(g)**2)/m)/(m-1); f=(mg2/df - r*(m-1)/(m+1))/(1+r); ddf=(m-1)*(1+1/r)**2/df**(3/m); p=1-probf(f,df,ddf); print f df ddf; print p[format=bestd32.31]; quit; %mend combchi;   %combchi(df=2,chi=102.997006 108.592438 105.224443 111.206028 106.644927)   SAS Output: The SAS System f df ddf 52.009228 2 3641.6389 p 0 ... View more

Re: Obtaining calculcated percentage from proc miananalyze

by Quartz | Level 8 in Statistical Procedures
‎12-07-2018 04:04 AM
‎12-07-2018 04:04 AM
Thanks. But SAS won't estimate calculated percentages because there are no standard error estimates on the reference group. Proc freq might be a solution using something like this:   ods trace on; proc freq data=DAIMP; table treatment*group / CROSSLIST(STDRES); by _Imputation_; run; ods trace off;   But how can I get the calculated #observations and percentages of treatment*group from proc mianalyze? ... View more

Obtaining calculcated percentage from proc miananalyze

by Quartz | Level 8 in Statistical Procedures
‎12-06-2018 02:56 PM
‎12-06-2018 02:56 PM
Hi, I have a dataset with 5 groups where I needed to impute some missing observations. I want to make a contingency table (on all subjects with and without imputed values) giving the distribution in absolute number and percentage of some variables of interest by group (proc freq table with chisq test if I had no missing data).   So far, I have been able to get a test for between group differences and groupwise estimates for difference from the reference group using the code below. But how can I get an estimate of the calculated percentages from proc mianalyze in each group?   I tried to ask for lsmeans in proc logistic but get the error:   WARNING: The model does not have a GLM parameterization. This parameterization is required for the LSMEANS, LSMESTIMATE, and SLICE statement. These statements are ignored   Any help would be much appreciated. Thanks!   Here is my full code:   proc surveyimpute data=have method=hotdeck(selection=abb) ndonors=5 seed=773269; var x1 x2 x3 x4 x5; cells imputecell; output out=ABB; id id; run;   data DAIMP; set ABB; if (ImpIndex = 0) then do; do _Imputation_=1 to 5; output; end; end; else do;  _Imputation_ = ImpIndex; output; end; proc sort data=DAIMP; by _Imputation_ ImpIndex; run;   ods select none; proc surveylogistic data=DAIMP; by _imputation_; class treatment group; model treatment=group / covb; ods output parameterestimates=Estimates covb=Covariances; run; ods select all; proc mianalyze parms(classvar=classval)=Estimates covb(effectvar=stacking)=Covariances edf=25; class group; modeleffects Intercept group; ods output parameterestimates=ABBLogisticAnalysis; run; ods select none; proc logistic data=DAIMP; class group(order=internal); model treatment(event='1')= group / covb; /* this gives at test for between group differences in treatment with  by _Imputation_; ods output ParameterEstimates=lgsparms; run; ods select all;   proc mianalyze parms(classvar=classval)=lgsparms; modeleffects group; run;   ... View more

Re: Proc lifetest : how to make assumptions about when the population ...

by Quartz | Level 8 in Statistical Procedures
‎05-18-2018 05:05 AM
‎05-18-2018 05:05 AM
You can use the delayed entry function to restrict comparisons to 25-35 years:   https://support.sas.com/documentation/onlinedoc/stat/ex_code/141/phrcpa1.html   However, when you are using parity as the outcome, you should also account for pertinent competing risks (at least all-cause mortality):   https://support.sas.com/rnd/app/stat/papers/2014/competingrisk2014.pdf ... View more

Re: overlay in proc sgplot

by Quartz | Level 8 in Graphics Programming
‎05-16-2018 09:47 AM
‎05-16-2018 09:47 AM
Thanks ... View more

overlay in proc sgplot

by Quartz | Level 8 in Graphics Programming
‎05-16-2018 08:04 AM
‎05-16-2018 08:04 AM
Hi,   I want to overlay two plots using proc sgplot. I've tried the code below but get the error message:   "ERROR: Attempting to overlay incompatible plot or chart types"   Code:   proc sgplot data=estimates NOAUTOLEGEND Noborder; Series y=ExpEstimate x=var / LINEATTRS=(THICKNESS=4); band upper=UpperExp lower=LowerExp x=var / transparency=.5; REFLINE 1 / Axis=Y LINEATTRS=(pattern=ThinDot color=Black THICKNESS=1); yaxis Values=(0.25 0.5 1 1.5 2 3 4 5 6) Label="Hazard Ratio" Type=LOG LABELATTRS=(weight=BOLD style=normal size=11); xaxis min=0 VALUES=(0 to 85 by 5) Label="Units" LABELATTRS=(weight=BOLD style=normal size=11); density var; run;   Attached is a copy of the graph I'm trying to create.   Any help would be greatly appreciated.   Thanks, Anders (SAS9.4M2) ... View more

Re: Testing Nonproportaionlity Assumption of Survival Analysis Using ...

by Quartz | Level 8 in Statistical Procedures
‎05-07-2018 03:01 AM
‎05-07-2018 03:01 AM
use the zph option.   Thanks, Anders ... View more

stb for proc phreg

by Quartz | Level 8 in Statistical Procedures
‎05-05-2018 03:03 AM
‎05-05-2018 03:03 AM
Hi,   In proc logistic it is possible to get an estimate of the relative covariate strength using the stb option. Does anyone know if there is a similar metric for proc phreg? Thanks, Anders ... View more

Re: proc sgplot

by Quartz | Level 8 in Graphics Programming
‎04-24-2018 11:26 AM
‎04-24-2018 11:26 AM
No that is not the problem. I searched the web some more and found that the problem is that proc sgplot requires the data to be sorted by female and age before plotting. Thanks anyway.     ... View more

Re: proc sgplot

by Quartz | Level 8 in Graphics Programming
‎04-24-2018 10:45 AM
‎04-24-2018 10:45 AM
Sorry. Thought you only wanted an example of the data. There are 10.000+ observations so it is not convenient to list all here. I copied the first 100 observations below. Also, just to make sure we are talking about the same thing. My question is how to get rid of the extra lines that SAS adds to the graph (see picture in my original post). I want 2 lines corresponding to the spline estimates (solid lines) for each sex with upper and lower 95% clm (dashed lines).   data WORK.DATA; infile datalines dsd truncover; input age:32. female:32. p:32. lower:32. upper:32.; datalines4;   40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 40,0,0.3222241319,0.3188327688,0.325615495 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 40,0,0.3222241319,0.3188327688,0.325615495 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 29,0,0.3178219885,0.31102658,0.3246173969 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 40,0,0.3222241319,0.3188327688,0.325615495 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 40,0,0.3222241319,0.3188327688,0.325615495 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 32,0,0.3190284679,0.3132385942,0.3248183416 32,0,0.3190284679,0.3132385942,0.3248183416 38,0,0.3214412539,0.3175171465,0.3253653613 32,0,0.3190284679,0.3132385942,0.3248183416 41,0,0.322588596,0.3194323886,0.3257448035 31,0,0.3186263081,0.3125046405,0.3247479757 40,0,0.3222241319,0.3188327688,0.325615495 33,0,0.3194306277,0.3139683391,0.3248929164 26,0,0.3166155091,0.3087906933,0.3244403248 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 38,0,0.3214412539,0.3175171465,0.3253653613 39,0,0.3218389179,0.3181901864,0.3254876493 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 22,0,0.3150068698,0.3057862116,0.324227528 33,0,0.3194306277,0.3139683391,0.3248929164 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 31,0,0.3186263081,0.3125046405,0.3247479757 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 39,0,0.3218389179,0.3181901864,0.3254876493 41,0,0.322588596,0.3194323886,0.3257448035 40,0,0.3222241319,0.3188327688,0.325615495 38,0,0.3214412539,0.3175171465,0.3253653613 40,0,0.3222241319,0.3188327688,0.325615495 41,0,0.322588596,0.3194323886,0.3257448035 27,0,0.3170176689,0.3095380376,0.3244973001 41,0,0.322588596,0.3194323886,0.3257448035 39,0,0.3218389179,0.3181901864,0.3254876493 41,0,0.322588596,0.3194323886,0.3257448035 41,0,0.322588596,0.3194323886,0.3257448035 27,0,0.3170176689,0.3095380376,0.3244973001 23,0,0.3154090296,0.3065392419,0.3242788174 41,0,0.322588596,0.3194323886,0.3257448035 ;;;;   ... View more

Re: proc sgplot

by Quartz | Level 8 in Graphics Programming
‎04-24-2018 09:13 AM
‎04-24-2018 09:13 AM
data WORK.TTR_PRED; infile datalines dsd truncover; input female:32. p:32. lower:32. upper:32. age_years:32.; datalines4;   0,0.3222241319,0.3188327688,0.325615495,40 0,0.322588596,0.3194323886,0.3257448035,41 0,0.3222241319,0.3188327688,0.325615495,40 0,0.322588596,0.3194323886,0.3257448035,41 0,0.322588596,0.3194323886,0.3257448035,41 ;;;;   ... View more

proc sgplot

by Quartz | Level 8 in Graphics Programming
‎04-24-2018 08:11 AM
‎04-24-2018 08:11 AM
I want to make a graph depicting the association of age with variable Y for males and females using a spline function (see code below). However, when I try to use SGPLOT to make the graph with dashed 95% clm SAS adds lines to the graph that I did not request (see Figure below). Does anyone know how to suppress these extra lines so that only the spline curve with 95% clm is visible? Thanks, Anders   proc orthoreg data=data; class female; effect spl=spline(age / naturalcubic details); model y = spl|female / noint; effectplot / noobs clm; test spl|female; store spline; run;   proc plm source=spline; score data=data out=pred predicted=p lclm=lower uclm=upper; run;   proc sgplot data=pred NOAUTOLEGEND Noborder; series y=p x=age / group=female LINEATTRS=(THICKNESS=1) name="Female"; series y=lower x=age / group=female LINEATTRS=(pattern=shortdash color=Black THICKNESS=1); series y=upper x=age / group=female LINEATTRS=(pattern=shortdash color=Black THICKNESS=1);  keylegend "Female" / title="Female"; yaxis Label="Y" Type=Linear LABELATTRS=(weight=BOLD style=normal size=11); xaxis Label="Age" LABELATTRS=(weight=BOLD style=normal size=11); run;           ... View more
Contact Me
Online Status
Offline
Date Last Visited
‎11-28-2023 12:06 PM
Group Hubs for greveam
View All
Likes given to
Quick links