SAS Support Communities

There might indeed be a problem here. (??)   To be sure , can you make your ROC curve again using this technique? Create ROC curve for any predictive model - SAS Support Communities for more info , see : Create and compare ROC curves for any predictive model - The DO Loop   Take (from your Model Studio project) the dataset that contains target and prediction. Then do a PROC LOGISTIC with ROC statement. Your target should be the dependent variable and your prediction (predicted probability) should be the -- only -- independent variable (explanatory variable).   Then compare ...   BR, Koen ... View more

GAMSELECT is new in the 8.5 release of SAS Visual Statistics (which is a Viya product). Introducing the GAMSELECT Procedure for Generalized Additive Model Selection   How to Train Generalized Additive Models (GAMs) in Model Studio - SAS Support Communities   BR, Koen   ... View more

Hello , Is this a ROC (AUC) - curve you plot with a statistical graphics procedure (like SGPLOT)? Or is this a ROC (AUC) - curve that is in the results pane after running a statistical procedure (like LOGISTIC with a ROC statement)? Or is this a ROC (AUC) - curve that is displayed in Model Studio? Or is this a ROC (AUC) - curve that is displayed in SAS Visual Analytics (Visual Statistics)? Can you share that?   You can of course augment the number of interpolation points (i.e. more thresholds) ... but if the output of the model is very "discrete" (like with a 5-leaves decision tree) ... that will not help.   And with zig-zagged ... you probably mean step-function-like (as the ROC curve should be monotonically increasing from bottom-left to top-right).   Cheers, Koen ... View more

Hello ,   I think ... if you search these SAS communities for grandparent-parent-child hierarchy or for grandparent-parent-child relationships or for ancestor - descendent hierarchy ... that you will find what you are looking for.   Try f.e. (Google search) : grandparent parent child hierarchy site:communities.sas.com or  parent child hierarchy site:communities.sas.com BR, Koen ... View more

Hello ,   What's wrong with the F-test which is provided by default by the GLM procedure? It's a joint test to see whether the model has any value.   If you want additional F-tests , you can use the TEST statement in PROC GLM. Here's the doc: The GLM Procedure TEST Statement https://go.documentation.sas.com/doc/en/pgmsascdc/9.4_3.5/statug/statug_glm_syntax24.htm   BR, Koen ... View more

Your question makes me think about the one you have posted on 30-OCT last year. Autogerression direction of the AR estimate https://communities.sas.com/t5/SAS-Forecasting-and-Econometrics/Autogerression-direction-of-the-AR-estimate/m-p/949462   Do you have additional info since then?     Koen ... View more

Hello ,   See blog on Job flows (in SAS Viya 3.5) : https://communities.sas.com/t5/SAS-Communities-Library/Go-with-the-Job-Flow-in-SAS-Viya-3-5/ta-p/612925   If you have a job (in the flow) that is successful ... the return code = 0. If you have a job (in the flow) that contains a WARNING in the LOG ... the return code = 5710. You can specify (in the job dependencies) that the flow should continue in case of an exit code 5710. I wouldn't put "Ends with any exit code" (!) as event type on the connection ... because then the flow will also continue if the node fails with an ERROR. And in general ... you want the flow to go into abend (you want the flow to stop) if there’s an ERROR. A WARNING is not necessarily an obstacle, but an ERROR is.   The problem is when the node is sometimes returning 0 and sometimes 5710 , because you cannot specify 2 exit codes. (you have this f.e. when you are in the WARNING period with your license key). You can solve that with an OR-gate I believe. An OR-gate is if any of the inputs into it are successful, then the flow will continue, so if you can set the return codes as separate inputs into it, then that should work. The other option is to force the job (node) to return code 0 in the event of a warning. That way, anything other than a successful completion or a warning, stops the job flow. You can use this piece of code for it (to be used with caution ... use it well thought out!): %PUT &=syscc; /* SYSCC Automatic Macro Variable Contains the current condition code that SAS returns to your operating environment (the operating environment condition code). Behavior depends on ERRORCHECK=SAS system option. */ %IF &SYSCC.=4 %THEN %DO; %LET SYSCC=0; %END; %PUT &=syscc; The page you specify for the ERROR-codes is a good one : https://developer.sas.com/rest-apis/compute/docs/error-codes   BR, Koen ... View more

You need a cross tabulation table (or crosstab) and you can easily make that with PROC REPORT.   See : Paper 388-2014 Sailing Over the ACROSS Hurdle in PROC REPORT Cynthia L. Zender, SAS Institute Inc., Cary, NC https://support.sas.com/resources/papers/proceedings14/SAS388-2014.pdf   BR, Koen ... View more

See above message (also written by me).   I am coming back to this , because the information given (in August 2022) is wrong. You can indeed use the "Manage Variables"-node in a Model Studio VDMML project to make changes to the metadata (role, measurement level, order, ...) of the variables involved, but for the target variable you cannot. For the target variable, the modification screen is greyed out (locked).   In fact, you should also be aware of the fact that the target variable role in a Model Studio project cannot be modified after executing any node or pipeline in it. So, think carefully before defining the target variable in the data pane, because once you start working with it you can't go back!   BR, Koen ... View more

Use ODS OUTPUT (ODS = Output Delivery System) ... ODS Output FinalCommunWgt = work.FinalCommunWgt ; (or maybe another table ... the one containing what you want) ODS OUTPUT: Store any statistic created by any SAS procedure By Rick Wicklin on The DO Loop  January 9, 2017 https://blogs.sas.com/content/iml/2017/01/09/ods-output-any-statistic.html   Here's the list of ODS table names (tables that PROC FACTOR can produce via ODS OUTPUT statement ... depending on the setting and options) SAS/STAT User's Guide The FACTOR Procedure https://go.documentation.sas.com/doc/en/pgmsascdc/9.4_3.5/statug/statug_factor_details15.htm   What is polychoric correlation?  By Rick Wicklin on The DO Loop December 11, 2023 https://blogs.sas.com/content/iml/2023/12/11/polychoric-correlation.html   BR, Koen ... View more

PROC CAPABILITY also allows for computing tolerance intervals.   So, there is a distinction between confidence intervals, prediction intervals and tolerance intervals.   Koen ... View more

The TINV function returns the p-th quantile from the Student's t distribution with degrees of freedom df and a noncentrality parameter nc. The probability that an observation from a t distribution is less than or equal to the returned quantile is p. TINV accepts a noninteger degree of freedom parameter df. If the optional parameter nc is not specified or is 0, the quantile from the central t distribution is returned. The QUANTILE function returns the quantile from a distribution that you specify. The QUANTILE function is the inverse of the CDF function. You must also specify a degree of freedom parameter df and optional noncentrality parameter nc. I think the quantile feature is more recent and obviously more general (since you can put "all" distributions in it).   BR, Koen ... View more