Thanks a lot for your feedback and for using SAS! ... View more

Thanks! What a wonderful presentation! I think you can expand the explanations of your code, make it a research paper and submit it to SAS conferences or statistical journals. ... View more

@SteveDenham wrote: You can set the truncation value at a small non-zero value, and all of the estimates are correctly determined. The issue becomes what is the small value to use. I think a good way to choose would be to see to how many decimal places the response is measured, and then set the truncation at half that value. For example, suppose you measure the response to the nearest thousandth (=Y.YYY). Under this scheme, the truncation value of 0.0005 would guarantee that it is greater than zero, and that all observed values are included.    Or am I still missing the point here?   SteveDenham I think your solution of tentatively selecting several thresholds and see what happens is a very nice idea. Despite the scheme you proposed was built upon selecting truncation thresholds, such attempts can be easily carried over to the selection of censoring thresholds. Therefore, I tried your approach on my data. Before I disclose my findings, I would like to reiterate first that my original objective was to model the relationship between y and x1, x2, ..., xn. However, the SEVERITY procedure is versatile and can serve to perform multiple tasks. The more basic one is to estimate the parameters of the distribution(s) that y follow. A more advanced one is to build regression models for the scale parameter of the distribution(s) of y, e.g., the parameter μ if y follows a lognormal distribution. The latter can be done by adding the SCALEMODEL statement in the SEVERITY procedure. In line with the capabilities of this module, my efforts of implementing your idea was also directed in two directions: (1) estimate the parameters of y in the absence of predictors; (2) estimate both the non-scale parameters of y as well as the regression coefficients of the model for the scale parameter. To accomplish the two goals, I tried several minuscule yet positive thresholds. They were of course smaller than the smallest observed positive value of my dataset. However, it was disturbing to find out that setting different thresholds did lead to different results. For the first objective, PROC SEVERITY still exhibited some consistency, at least in the estimation of several (but not all!) distributions that were built into this module. For the second objective (i.e., in the presence of predictors), the regression coefficient estimates of the scale parameter model deviated from each other more or less, and even quite wildly on some occasions. Therefore, the conclusion is that PROC SEVERITY is not a good tool for dealing with zero-censored data as the results is dependent on the specification of the censoring threshold. A supplement to this conclusion is that PROC SEVERITY supports multiple advanced functions relating to parameter estimation, including the specification of starting values that play a role in the maximum likelihood estimation process, the underlying method that this procedure uses to accomplish all of the aforementioned tasks. I am not sure whether delicate application of these utilities could remedy the problems I pointed out in the preceding paragraph, but I have not interest in trying it out. ... View more

I have seen some behavior such as this. Recall that the optimization method is non-linear and that the log likelihood values are defined as hexadecimal during calculations. That leads to truncation and semi-chaotic behavior if the program is run on a different machine or even on the same machine with a different operating system. Also, check to see if your version of SAS has changed since the original run. There were some substantive changes made to GLIMMIX going from previous versions to SAS v9.4TS1M8 that may be contributing to this. See this problem Note: https://support.sas.com/kb/70/094.html    SteveDenham ... View more

Thank you for the post- we are responding in your TS case. Thanks, and have a great day! ... View more

Hi RichardHorgen, For this issue, you might be best served by contacting Technical Support and requesting SAS Content Assessment Tool support.  Here is a link for your convenience: https://support.sas.com/en/technical-support.html#contact  Thank you for using SAS!  ... View more

@teresacorzo wrote: I’m modelling with reject inference in SAS Visual Machine Learning, I have used the reject inference node with parcelling. Previously, I’ve created models with reject inference in SAS Miner, where it assigned a weight to every registry in the dataset, assigning 1 to accepted and a given weight between 0 and 1 to the inferred data. However, in SAS Viya, the weights are all 1, in accepted and inferred. I don’t need all the data in my modelling augmented data, but I don’t want to lose information by creating a random sample that mimics the weight assigned previously in Miner. The weight is given by the following equation:     I’ve tried assing this weight manually, assigning it as a Weight variable, but the node doesn’t read it, it includes all the observations for the rejected data with no calculated weight.         Train set Accepted:   Inferred:   I haven’t found enough information in internet to solve this problem. Thanks! In SAS Visual Machine Learning, the Reject Inference Node does not automatically assign weights. Manually compute weights as in SAS Miner, then assign them using a custom "Weight" variable in the dataset. Ensure this variable is explicitly defined in the model settings to apply it during training. ... View more