About kthartma

Rick_SAS · ‎10-18-2019

As ChrisNZ shows, you can sort the data by your 'Volume group' variable and use a BY statement if you want to create separate ROC curves, You do not state how you obtained the predicted values, but because your volume appears to be a covariate, you might instead choose to incorporate that information into the model. Then the Predictor variable would use the volume as part of the predictive model. Lastly, since you already have the Predictor variable and you just want the ROC curve, you should add the NOFIT option to the MODEL statement and use an ROC statement to get the plot: ROC 'My Curve' pred=Predictor;

cheenaChuks · ‎03-30-2019

How would you use a class statement for two datasets? Please could you include a short example. I looked at the links but there were only examples with the by statement.

ballardw · ‎04-19-2018

@kthartma wrote: Hi there, I am doing a boxplot and I am having issues differentiating vertical line colours. It seems like I can't get each line (2 of them...at 12 and at 5) to be different colours. Please see code below. proc boxplot data=eval.pop; plot latest_reg*seclatest_reg_cat/ vref=12 5 vreflabels= "90th percentile" "Target" cvref= red green; inset min mean max stddev/ header = "Overall statistics" pos= tm; insetgroup min max/ header = "Extremes by performance"; label latest_ref= "Last reported reg rate"; label seclatest_ref_cat ="Performance based on second last reg rate"; run; You don't do yourself favors by not posting the errors generated by your code. CVREF is going to allow a single color for all the reference lines. If you want to have different colors either go to annotate data set, probably not the best way, or move to SGPLOT with the VBOX or HBOX plot and as many REFLINE statements as needed. If you need all of the inset/ header/post options then you may have to settle for single color reference lines or go with annotate.

PaigeMiller · ‎03-25-2018

@kthartma wrote: Tot_2009 Tot_2010 Tot_2011 Tot_2012 Female Male If that makes sense. Let me know. Actually, it doesn't make any sense to me. This is just words without description or meaning in the context of correlation of matrices. The only thing that makes sense to me in the context of correlation matrices is to produce a correlation matrix for males and a different correlation matrix for females. If that's the case, sort by male/female, and then put a BY statement into your PROC CORR. If that's NOT what you mean, please describe this in detail, instead of the rather brief descriptions you have given so far. Show us an example of what you want. As long as we're discussing this, I don't see any reason to correlate rate2009 with tot_2016, for example, I can't image how this correlation of data 7 years apart would be meaningful.

kthartma · ‎03-24-2018

Thanks so much! I ended up using proc glm.

kthartma · ‎03-14-2018

Thanks so much. Best, Krystal

Online Status	Offline
Date Last Visited	‎10-17-2019 08:45 PM

Multiple roc curve

CVREF box plot

Re: Correlation Matrix

Correlation Matrix

Re: Creating dummy variable

Creating dummy variable

Re: Proc means to determine missing value

Proc means to determine missing value

Re: how do I use proc means for multiple data sets

Re: how do I use proc means for multiple data sets

Re: Creating dummy variable

Re: Multiple roc curve

Re: how do I use proc means for multiple data sets

Re: CVREF box plot

Re: Correlation Matrix

Re: Creating dummy variable

Re: Proc means to determine missing value