"The most likely cause for getting age of 53 is that you messed up the order of the arguments and which one had DATE values versus DATETIME values so that you ended up calculating the number of years since 1960." YES. That is exactly what I did. Case closed. Thank you for your help and persistence and to all who replied, thank you. Gene Maguin ... View more

Hi, I see what you did and I can repeat it. So this means I have a deeper problem. When I look at the viewtable for my file, I see these exact characters: 06/08/2011 for dob and these exact characters: 18DEC23:18:48:18 for interviewdate. When I look at the viewtable after running the syntax you posted I see these exact characters: 18786 for dob and 2018544498. In my data file dob has a format of MMDDYY10 and interviewdate has a format of datetime16. In your file both are Number. Ok. Is there a way to convert MMDDYY10 to number? Is there a way to convert datetime16 to number? Maybe relevant. The dataset is exported from Redcap as a csv file and then read into excel and saved as an excel data file (xlsx) and that xlsx file is imported into sas through proc import (dbms=xlsx). Thanks. ... View more

Tom and all who replied. Thank you. I apologize to you for describing the problem in a way that mislead you. So. Starting over. I've read in a data file and in the data file are the two named variables, interviewdatetime that is a date time variable and an actual value is 18DEC2023:18:48:18, and dob that is a date variable and an actual value is 08JUN2011. I understand the point about date-time variables being in second since the time origin, spss does the same thing. And that date variables are days since the date origin, excel does that. It seemed to me that teen_age=yrdif(datepart(p_abday_t1),p_abday_t1); should work but the result is 51.43. From the two data values you can see the value is about 12.5 years. It may be that the variable order is reversed but if so the difference would be negative-easily fixed. I understand computation that has to be done. I don't know how to write the syntax to do the required computations. Thanks, Gene Maguin ... View more

Thanks for pointing out that sas has a corr dataset and many more types as well based on the search you suggested. I understand your point but the format and structure of a sas type=corr data set is that for a matrix dataset in spss and I know to make them, I've made them and am making them. Example A.2+Figure A.3 in that search shows how to do that and the result. In her reply, Paige says that proc corr won't take matix input and that is what I thought was true when I looked at the proc corr documentation but I wanted to ask because my sas knowledge would only fill a thimble but one with a hole in it. I know that sas has IML and it can be used to do amazing things, including, I'm sure, computing a reliability coefficient but I don't know how use IML. I can do this in spss with two commands: matrix data and reliability (which accepts a matrix data file as well as regular data file as input). Thank you for replying. ... View more

I thought was true when I looked at the proc corr documentation but I wanted to ask because my sas knowledge would only fill a thimble albeit one with a hole in it. I know that sas has IML and it can be used to do amazing things, including, I'm sure, computing a reliability coefficient but I don't know how use IML. I can do this in spss with two commands: matrix data and reliability (which accepts a matrix data file as well as regular data file as input). Thank you for replying. ... View more

In her reply, Paige says that proc corr won't take matix input and that is what I thought was true when I looked at the proc corr documentation but I wanted to ask because my sas knowledge would only fill a thimble but one with a hole in it. I know that sas has IML and it can be used to do amazing things, including, I'm sure, computing a reliability coefficient but I don't know how use IML. I can do this in spss with two commands: matrix data and reliability (which accepts a matrix data file as well as regular data file as input). Thank you for replying. ... View more

Steve, Thank you. I would never have found that. I'll try it out but it certainly looks like it is what I need. One thing I noticed that that clicking on the complete code link is a dead end. Searching on "sas glimmix" and clicking on first result (https://support.sas.com/rnd/app/stat/procedures/glimmix.html) gets to a page with "SAS/STAT Software" as the heading. Under the examples is the example you pointed me to but there it is listed as Example 49.4 (and the link to the complete code works). So, who knows why; it like going into your familiar grocery store and nearly everything has been rearranged. Again, thank you. ... View more

I can a copy from the library. Thanks for the recommendation. I'll try RSPL. I understand your alternative; I read about it in an ecology statistics book. Help me learn something. How would this be implemented? Our data is the computed proportion (because the dataset was originally analyzed assuming a normal distribution). I assume that that data won't work for the alternative method. Would I have to go back to the original data where each record represents an instance where a call was made? I know that the spss procedure genlinmixed allows the data to be expressed as the number of successes of the number of attempts, where the number of attempts can be a variable in the dataset. I just assume sas can do that, why not, but does glimmix have that capability? If so, where/how would it be documented? Lastly, the other problem is proportions of 0.0 or 1.0. In these current analyses, those values are recoded to 0.005 and 0.995, respectively. What happens in a logit formulation? Discarded as undefined? Given an arbitrarily large or small value, which is what mplus apparently does? I agree that your proposed model is a better representation of the data. The question is implementation. ... View more

I don't believe i have technical skill to create a plausible beta distribution test data model. I want to ask about the meaning of the three error messages that I'm seeing. These are ERROR: QUANEW Optimization cannot be completed. ERROR: The function value of the objective function cannot be computed at the starting point. ERROR: Infeasible parameter values for evaluation of objective function with 1 quadrature point. What do these mean in terms of where the estimation process is failing. To me they are pretty opaque and I'd like to understand what is happening. ... View more