If you already know how to generate the X and Y variables in the plot from the data and the location of the dashed line, then you can create the plot as follows:   title "Mean excess plot"; proc sgplot data=Have; scatter x=X y=Y; refline 20 / axis=x lineattrs=(pattern=dash); run; If your question is not about how to CREATE the plot but how to COMPUTE the values for the plot, then we'll need a reference and an explanation of the two quantities in the graph. A "reference" mensa a link to a paper or web site that explains the details that are required to understand how to generate the plot. ... View more

In the CLASS statement you can add an option to change the parameterization of your model to the EFFECT, this may be what you are looking for.   class mfg/param=effect; but please note the resulting model is the same, and the predictions are the same, just the way the model is parameterized has changed.     In this situation, you may be more interested in the LSMEANS, which sound like what you really want to look at here instead of the model effects, and the LSMEANS don't change depending on the parameterization of the model. ... View more

Its quite complicated to explain exactly how the statistics are calculated and how they should be used. I will recommend you to read the documentation which are very will written for this topic. SAS documentation   Shortly speaken, the scaled deviance is the deviance/dispersion. This statistic is in many model approximately chi-square distributed with n-p degrees of freedom. ... View more

There is an example I wrote before. But it is for Logistic Regression.   /****** K-Fold CV ****/ %macro k_fold_cv(k=10); ods select none; proc surveyselect data=sashelp.heart group=&k out=have; run; %do i=1 %to &k ; data training; set have(where=(groupid ne &i)) ; run; data test; set have(where=(groupid eq &i)); run; ods output Association=native(keep=label2 nvalue2 rename=(nvalue2=native) where=(label2='c')) ScoreFitStat=true(keep=dataset freq auc rename=(auc=true)); proc logistic data=training outest=est(keep=_status_ _name_) ; class sex; model status(event='Alive')=sex height weight; score data=test fitstat; run; data score&i; merge true native est; retain id &i ; optimism=native-true; run; %end; data k_fold_cv; set score1-score&k; run; ods select all; %mend; %k_fold_cv(k=10) /*************************************/ %macro k_fold_cv_rep(r=1,k=10); ods select none; %do r=1 %to &r; proc surveyselect data=sashelp.heart group=&k out=have; run; %do i=1 %to &k ; data training; set have(where=(groupid ne &i)) ; run; data test; set have(where=(groupid eq &i)); run; ods output Association=native(keep=label2 nvalue2 rename=(nvalue2=native) where=(label2='c')) ScoreFitStat=true(keep=dataset freq auc rename=(auc=true)); proc logistic data=training outest=est(keep=_status_ _name_) ; class sex; model status(event='Alive')=sex height weight; score data=test fitstat; run; data score_r&r._&i; merge true native est; retain rep &r id &i; optimism=native-true; run; %end; %end; data k_fold_cv_rep; set score_r:; run; ods select all; %mend; %k_fold_cv_rep(r=20,k=10); /********************/ data all; set k_fold_cv k_fold_cv_rep indsname=indsn; length indsname $ 32; indsname=indsn; run; proc summary data=all nway; class indsname; var optimism; output out=want mean=mean lclm=lclm uclm=uclm; run; ... View more

Given that you have the PROC FREQ counts stored as a second SAS data set,  you could use:   data want; merge have1 have2 (rename=(count=number)); by id; output; number = .; run;     ... View more

You can do it like this   data have; input ID $ NAME $ BEGIN END; informat BEGIN END DDMMYY10.; format BEGIN END DDMMYY10.; datalines; 191080 John 25/04/2016 01/05/2016 191080 John 08/06/2016 10/06/2016 191080 John 21/06/2016 24/06/2016 191141 Alex 16/01/2017 17/01/2017 191141 Alex 22/02/2017 29/04/2017 ; proc sort data = have; by ID; run; data want; set have; by ID; lag_END = lag1(END); if not first.ID then RESULT = abs(intck('day', BEGIN, lag_END)); drop lag_end; run;   NOTE: Just edited the above, didn't realize about the whole lag-thing 🙂  ... View more

data want; set have; if nb = 2 then do; money = money / number; nb = nb / 2; c = class; class = substr(c,1,4); output; class = substr(c,6,4); output; end; else output; drop number c; run; ... View more

Use the SCORE statement to score the test data with the model and then use the output provided to calculate the Mean Square Error. ... View more

If JOB is not contnuous (it's a character variable), you can't fit a spline through it. That is a meaningless idea. ... View more