Samples & SAS Notes > Analytics
>
Categorical Data Analysis
| Date | Title | Type | ||
|---|---|---|---|---|
| 11/20/09 |
22592 - Are there any recommended references or additional documentation about the CATMOD and LOGISTIC procedures? See the "References" section at the end of the CATMOD and LOGISTIC chapters in the SAS/STAT User's Guide and below. References from SAS Allison, P.D. (1999), Logistic Regression Using the SAS System: Theory ... http://support.sas.com/kb/22/592.html, 20KB |
Usage Note | ||
| 10/26/09 |
24822 - Changing the Numeric Format of PROC FREQ Output This sample describes how to change these defaults for the three main types of PROC FREQ output: one-way tables, multiway tables in list format, and multiway tables presented as crosstabulations. http://support.sas.com/kb/24/822.html, 21KB |
Sample | ||
| 9/25/09 |
37108 - How can I set the reference levels for the CLASS predictor variables in my model? Some procedures such as GENMOD, GLMSELECT, PHREG, and others provide options in their CLASS statements (or in other statements) which allow for reference cell coding of CLASS variables and specifying reference levels ... http://support.sas.com/kb/37/108.html, 59KB |
Usage Note | ||
| 9/23/09 |
37228 - How can I estimate probability differences using my logistic model and get a confidence interval? Since the log odds is the response function in a logistic model, such models allow you to estimate the log odds for a setting of the predictors. By exponentiating, you can estimate the odds. Similarly, the difference ... http://support.sas.com/kb/37/228.html, 47KB |
Usage Note | ||
| 9/16/09 |
37105 - Why does the program editor window banner say "PROC .. running" after the procedure has finished? The ANOVA, ARIMA, CATMOD, FACTEX, GLM, MODEL, OPTEX, PLAN, and REG procedures are interactive procedures. They remain active after processing a RUN statement. The "running" message in the banner of the ... http://support.sas.com/kb/37/105.html, 30KB |
Usage Note | ||
| 9/16/09 |
37181 - Warning: Output was not created -and- The current ODS SELECT/EXCLUDE/OUTPUT statement was cleared See this usage note on why the following messages occur and how to avoid them. WARNING: Output 'parameterestimates' was not created. Make sure that the output object name, label, or path is spelled correctly. ... http://support.sas.com/kb/37/181.html, 27KB |
Usage Note | ||
| 9/16/09 |
37171 - Why do I get a message that I cannot open an output data set because it is in use by me? When using an interactive procedure to create a data set, the following message may occur when trying to display the data set, such as with the Table Editor (viewtable, or vt, command). This usage note describes why ... http://support.sas.com/kb/37/171.html, 26KB |
Usage Note | ||
| 9/3/09 |
6955 - Predicted values produced by PROC GAM are not predicted means (probabilities or counts) Prior to SAS 9.2, the predicted values produced by the PRED option in the OUTPUT statement of PROC GAM do not have the inverse link function applied and are instead linear predictor values. Consequently, when the DIST= ... http://support.sas.com/kb/6/955.html, 19KB |
Usage Note | ||
| 8/31/09 |
37037 - Area under curve (c)=0.5 and all pairs tied with BINWIDTH=0 and OUTROC= option used If you specify the BINWIDTH=0 and OUTROC= options in the MODEL statement of PROC LOGISTIC, the c statistic (area under the ROC curve) may incorrectly be reported as 0.5 and the "Percent Tied" may equal 100%. To avoid ... http://support.sas.com/kb/37/037.html, 18KB |
Problem Note | ||
| 8/21/09 |
36453 - How to import and assess outside modeling techniques using SASŪ Enterprise Miner(tm) This video shows an example of how to import a non-supplied model into SAS Enterprise Miner and be able to assess it with other models. http://support.sas.com/kb/36/453.html, 21KB |
Usage Note | ||
