Some genius says Delta method is sound for this goal. Here is an example of a single independent variable Weibull model and the variance of the survival function could derived from the variance of that independent variable.   ... View more

Hello, Season It's very kind of you for providing those external links. Let's me read them now. Much appreciated! Tom ... View more

Hi, @FreelanceReinh Thank you for your response. Hmmm, my bachelor degree is not statistics. We have: P (A = 1 & B = 0) = P(A=1)*P(B=0) P (A = 0 & B = 1) = P(A=0)*P(B=1) Actually, can we say: P (A = 1 & B = 1) = P(A=1)*P(B=1) P (A = 1 & B = 1) = P(A=1)*P(B=1) for the observations? If so, I think for each observation, they are independent for the response event. ... View more

He wants the spline, which usually is a non-linear graph with x being a continuous independent variable (e.g., weight, blood pressure, creatinine level, etc.) and the y being the hazard ratio and its 95%CI bands. Here is from Gemini: Restricted cubic splines (RCS) don't actually "split" the coefficient of a single variable into several sub-coefficients directly. Instead, they **transform a single continuous variable into a set of new, related variables (called basis functions), and it's these new variables that each get their own regression coefficient.** The original variable itself is no longer directly in the model in its raw form, or if it is, it's typically just the first basis function. The math behind this lies in the construction of these basis functions. The idea is to allow for a flexible, nonlinear relationship with the outcome while ensuring the curve behaves nicely (is "restricted" to be linear) in the tails of the data. Let's assume you have a continuous variable, $X$, and you want to model its effect nonlinearly using RCS.   ... (See the PDF file for completed answer from Gemini) ... View more

Hi, Rick   Thanks for the clarification. Now I see. Luckily, there is the DO Loop method. ... View more

Hello, Koen Thank you so much for answering my question. Actually, I have experience with the method of DO Loop and it works. The drawback of the DO Loop is that it requires a lot of code lines, including DATA, PROC SQL, and PROC SGPLOT etc. But it indeed works. Therefore, I tried to find some simpler ways to to so, like PROC PLM. Anyway, thanks again for your feedback. Tom ... View more

SAS version: SAS Viya for Learners.   Same error. WARNING: The SCORE statement cannot be used for the specified model.   Codes: proc lifereg data = albumin_iptw; class sex mv rrt hypertension diabetes copd coronary_disease albumin_used; model time*mortality(0) = sex age sofa inr bun lactate glucose albumin mv rrt hypertension diabetes copd coronary_disease albumin_used / distribution = weibull; weight wt; store out= w1; run; proc plm restore = w1; score data = cov out= scored_predictions; run;      ... View more

Hello, Dave Thank you for your feedback. Say, we have event A=1 and B=0. According to the matching condition, we have A + B = 1. The condition probability of P( A = 1 & B = 0 | A + B = 1) is calculated as P (A = 1 & B = 0) / [P(A = 1 & B = 0) + P (A = 0 & B = 1)] Please notice the last step, they have: P (A = 1 & B = 0) = P(A=1)*P(B=0) P (A = 0 & B = 1) = P(A=0)*P(B=1) I think the last two formula means A = 1 and B = 0 as well as A = 0 and B = 1 are independent, respectively. That's why I'm confused about the independence between event A and B. ... View more

Thanks, dear buddy @Ksharp ... View more

Thank you both @Ksharp and @SteveDenham I think I need to supplement my mathematical statistics basis before I can dig deeper into this issue. Regards, ... View more