Creating a new font altogether looks like an interesting approach. Could you please tell us or provide some hints on how to do this in SAS? ... View more

@whymath wrote: I think Simsun is 宋体, I have learned it long ago. Just checked it on my computer, in "C:\Windows\Fonts", a font displayed as "宋体 常规". When I review its attributes, I see the path is: ‪C:\Windows\Fonts\simsun.ttc   是的，您说的没错。我在搜索引擎上以“Simsun”为关键词搜索，这是我搜到的内容，提示Simsun就是宋体。 Yes, you are right. I searched on a search engine with the keyword "Simsun". Here is what I found, which indicated that Simsun is 宋体. ... View more

谢谢您的详细阐述！我也涨了知识了！我觉得您可以把这些对@chiwei的问题的答复整理成一篇论文，发表在SAS使用者小组（SAS User Groups, SUGs）上。我认为这个问题很重要，但目前为止我还不知道有其他人给出了答案。  ... View more

哇噢！这真的很酷！您可以讲解一下您的操作流程（尤其是您在记事本中修改的代码的含义）吗？另外，@chiwei 提出的要求是将所有中文字体改为Simsun。经过您的修改，RTF文件中的中文字体变为宋体，而不是Simsun。 Woh! That is really cool! Could you please elaborate the opertaional procedure (especially the meaning of codes you altered in Notepad)? By the way, @chiwei  proposed the request of setting the font of all Chinese characters to Simsun. After your modification, the font of Chinese characters in the RTF file was changed into 宋体 instead of Simsun. ... View more

Yes, the foundation of operation is the key issue I wish to know about CAS. Thank you for informing me that it is solely based on SAS Viya. But unfortunately, that virtually obliterates my need for learning it right now for, as I had stated, my institution has not purchased its license. Anyway, thank you for your kind help! I hope our discussion, especially the links you summarized could benefit other SAS users who may have the need and passion to learn CAS like I did. If that is the case, then my time spent on this discussion worths it. ... View more

Thank you for your reply! I saw that the materials you provided are generally oriented to SAS Viya users. I am not working with SAS Viya, as my institution does not have a license for it. I am currently using SAS 9.4, with multiple procedures (e.g., the GAMMOD procedure) only available in CAS. I am hoping to learn issues pertaining to that. ... View more

Take a look at this discussion: Solved: Code to get the pooled c-statistic and 95% CI after multiple imputatio... - SAS Support Communities. ... View more

Weighted least squares, to be exact. Because of the fact that weighted least squares is a special kind of generalized least squares, it is not wrong to say that the regression coefficients are estimated by generalized least squares in the SURVEYREG procedure. ... View more

@Season wrote: I am not sure if @chiwei has multi-language support installed but I think the curx of the problem Erratum to a spelling error: the word should be spelled as "crux". ... View more

I am afraid that you had misunderstood me. What I said was incorrect was that my teachers told us to examine the normality of the dependent variable instead of the residual of the model. I know this is a trivial issue, but I was concerned that our conversation could serve as references for other web users who may not be necessarily that familiar with the theory of linear and mixed models and might get confused. ... View more

Judging from the plot you provided, I think there is heteroscedasticity. You could post the result of the Breusch-Pagan test here anyway as it a formal statistical test tailored for testing heteroscedasticity. ... View more

Thank you for your reply! Actually, it was @chiwei instead of me who was stuck on the problem mentioned in this topic. I am not sure if @chiwei has multi-language support installed but I think the curx of the problem raised by @chiwei was that he or she was trying to build a bilingual report and automatically designate the fonts of English and Chinese characters respectively. Moreover, the exact wordings are not pre-defined, a condition required for inline formatting. ... View more

In one word, it is usually the model predictive mean that is used for prediction. For instance, suppose we are building a model on the amount of money an insurance company pays for reimbursement. When we say we want to predict this quantity, we mean that we wish to know the amount of money the insurance company reimburses given the values the predictors (i.e., independent variables) take. This usually amounts to calculating the predicted mean by the model given the value of the predictors. Now that the predictive mean of Tweedie model is always larger than zero, we, in the fictitious scenario mentioned above, will claim that the amount of reimbursement is always larger than zero, since this is what the Tweedie model tells us in terms of its predictive mean. But that is definitely not true. A lot of zeros are actually observed. That is why the data is termed as zero-inflated data. However, if the researcher is interested on the factors associated with the dependent variable rather than hoping to find out the expected mean given values of predictors, then Tweedie models can be selected. Following the scenario above, suppose we are interested in the correlation of the amount of money reimbursed and age instead of trying to figure out the amount of money the company is expected to pay given that the person's age is, say, 69. In this case, the absolute amount of the regression coefficient estimate as well as its sign (+ or -) can provide us information regarding the relationship of the amount of money reimbursed and age. ... View more

When I was mentioning the utility of Tweedie models in prediction, my emphasis was on its predicted mean. The fact that the predicted mean cannot be zero is in conflict with the fact that the dependent variable is in fact a zero-inflated variable. The number you mentioned was the value of the probability density function of the Tweedie distribution at a given point. ... View more