Here some sample code to build upon for what @Kurt_Bremser suggested. libname src xlsx "c:\temp\Example.xlsx"; proc datasets lib=src nolist; copy in=src out=work; run; quit; libname src clear; ... View more

Is it valid to create a small randomized sample of cases and controls and then do a smaller sample of 1:2 matching from these randomized smaller samples?  In fact that is what I would suggest. Create a dummy dataset like the one which you have with you. Write programme for this small dummy datasets of having some thousand records or so. Run the programme on this dummy dataset. Make modifications with the help of statisticians until you and they feel that the programme is accurate. Once the programme is accurate and is doing what it is intended to do, run the programme on 10% of this big dataset by limiting the number of observations by using obs = option. Only then run the programme for the whole big dataset.    Now when you are running the programme on big dataset and also modifying the programme at the same time, lot of time is getting wasted because to make even a small change and to see if the change has taken effect, you have to wait for long time.    Once the programme if perfect and it is run for the large dataset, relax and grab your coffee and do something else. Mostly the work will be done in due course of time. Even then if the programme is crashing then there is issue in the software.   Thank you.   - Dr. Abhijeet Safai  ... View more

I have moved your question / topic to the "Forecasting & Econometrics" - board.   Koen ... View more

Hello @MJAIN .  This would be a bit tricky.  The p-value is written using an ENTRY statement in GTL.  In order to italicize just the P in p-value you would need the entry statement to look something like: ENTRY textattrs=(style=italic) "p" textattrs=(style=normal) "-value:" ....; The parameter PVALHEADER is meant to be placed in directly as text in the ENTRY statement, but this can be used to our advantage to manipulate the ENTRY statement: %newsurv(data=sashelp.bmt,time=t,cens=status,class=group, pvalheader=Logrank" textattrs=(style=italic) " p" textattrs=(style=normal) "-value:) By using the double quotes in the parameter it will close off the text part of the ENTRY statement allowing for the textattrs to be applied to different pieces leading to the desired result:   ... View more

Thank you all for helping me out with this! ... View more

I have moved your post to the "SAS Forecasting and Econometrics"-board !   You should start doing this : Search the Communities (https://communities.sas.com/) for "interrupted time series" analysis Search https://www.lexjansen.com/ https://www.lexjansen.com/search/searchresults.php?q=%22interrupted%20time%20series%22%20analysis Search blogs.sas.com (https://blogs.sas.com/) and bump into this (for example):      Segmented regression models in SAS      By Rick Wicklin on The DO Loop December 14, 2020 https://blogs.sas.com/content/iml/2020/12/14/segmented-regression-sas.html Segmented regression models: This post shows how to create a segmented regression model in SAS. The breakpoints in the model are estimated from the data. Koen   ... View more

@sms1891 wrote: Can we get the 95% CIs for the bootstrapped sensitivity and specificity? Of course, you can! Look here and you will find out how to do so ...     Compute a bootstrap confidence interval in SAS     By Rick Wicklin on The DO Loop August 10, 2016 https://blogs.sas.com/content/iml/2016/08/10/bootstrap-confidence-interval-sas.html   Koen   ... View more

The excel sheet had ID variable, Outcome variable and scoring variable PIPE_Score. I want to get sensitivity and specificity calculation for Outcome prediction for PIPE_Score cutoffs of  7, 12 and 15. I also want to generate a bootstrapped cohort and calculate the sensitivity and specificity for Outcome prediction for the same PIPE_Score cutoffs of  7, 12 and 15. I have attached the excel sheet again. Thank you for your help! ... View more

Ah, yes - my mistake, there. The LOWCASE function in the line that detects "Other" is screwing things up. shared_othern=find(lowcase(Shared_services),"Other")>0; This would work as you described: data want; set have; managementn=find(lowcase(Shared_services),"management structure")>0; physical_infrastructuren=find(lowcase(Shared_services),"physical infrastructure")>0; personnel_responsibilitiesn=find(lowcase(Shared_services),"personnel responsibilities")>0; revenues_and_expensesn=find(lowcase(Shared_services),"revenues and expenses")>0; technical_infrastructuren=find(lowcase(Shared_services),"technical infrastructure")>0; care_managementn=find(lowcase(Shared_services),"care management")>0; social_needs_servicesn=find(lowcase(Shared_services),"social needs services")>0; best_practicesn=find(lowcase(Shared_services),"best practices")>0; shared_othern=find(Shared_services,"Other")>0; run; ... View more

Thank you for the response. Tried rowaxis label='Enrollment Year' labelattrs=(family=arial size=10 weight=bold color=black) values=(2017 to 2022 by 1) REVERSE ;     Still not working. ... View more

Ksharp: /*According to the example from URL, You need to change your data structure . Did you read it ? */ data have; input id x1 y1 x2 y2 x3 y3; output; datalines; 1 5.9 5.8 5.5 5.6 5.4 5.5 2 5.9 5.7 5.7 5.8 5.5 5.2 3 5.9 5.8 5.7 5.6 5.4 5.2 4 5.9 5.7 5.8 5.7 5.4 5.3 5 5.8 5.7 5.3 5.4 5.4 5.1 6 5.8 5.7 5.6 5.6 5.4 5.4 7 5.9 5.8 5.5 5.3 5.4 5.2 8 5.9 5.8 5.7 5.6 5.4 5.2 9 5.9 5.8 5.3 5.7 5.5 5.3 ; proc transpose data=have out=temp; by id; var x: y:; run; data want; set temp; by=compress(_name_,,'kd'); if _name_=:'x' then time=1; if _name_=:'y' then time=2; run; proc sort data=want; by by id time; run; proc nested data=want; by by; class id; var col1; run;   ... View more

Well, that would have been good to know earlier.  If you have homogeneity of variance across the time points, you can use PROC GEE or PROC GLIMMIX for the analysis.  If the variances are heterogeneous across time then GLIMMIX allows for the fitting of heterogeneous variance using a heterogeneous compound symmetry variance-covariance matrix or an unstructured covariance matrix. The following assumes heterogeneity by time.   proc glimmix data=yourdata plots=all; class time subjectid; model force = time; random time/subject=subjectid type=csh residual; lsmeans time/diff cl; run; This fits a model where the residuals are heterogeneous but normally distributed.  The plots will enable you to make a decision on whether this is a reasonable assumption.  The lsmeans statement will yield comparisons between all 10 timepoints. Note that this will involve 45 comparisons which are likely to not be independent.  Control for multiplicity can be added to the lsmeans statement.  For GLIMMIX, the adjust=simulate (seed=<pick a number>) usually provides the best control of Type I error, especially when combined with the stepdown option.     Since this is fitting an R-side variance-covariance matrix with no random effects, it could also be fit using PROC GEE. I will leave this for @StatDave to suggest some starting code.   SteveDenham   ... View more

Hello,   For modelling incidence rate and comparing between groups, have a look at the below !   Usage Note 24188: Modeling rates and estimating rates and rate ratios (with confidence intervals) https://support.sas.com/kb/24/188.html   Usage Note 37344: Estimating rate differences (with confidence interval) using a Poisson model https://support.sas.com/kb/37/344.html   You can also screen this webpage : Usage Note 30333: FASTats: Frequently Asked-For Statistics for the key-word "rate" or whatever other key-word you would like https://support.sas.com/kb/30/333.html   Koen ... View more

@sms1891 Thanks, that is much clearer now what you want. I don't have the time to work on this right now, maybe later. But you still need to provide a portion of your data as working SAS data step code (instructions). Other formats are not acceptable.  ... View more