Recent content by freezingswallow

  1. F

    Help with RPSFT model implementation in SAS

    Hi! I am doing an analysis on overall survival endpoint. The patients in the placebo group will be switched to treatment group in the open-label phase on voluntary base. I plan to use Rank-preserving structural failure time method (RPSFT) model. Is anyone familiar with this method and know how...
  2. F

    How to control the number of variables to display in one page using proc report

    My goal is to make a data listing which contains 10 variables. However, the space for a single page is not sufficient to display all 10 variables. I used proc report to make the listing file. SAS will automatically cut off the 10 variables into 2 pages. I hope that I can control how many...
  3. F

    GEE model with Error " The generalized Hessian matrix is not positive definite"

    Hi experts, When I was trying to build a marginal GEE model (logit = bin) for a censoring variable in a survival study, I implemented the following SAS procedure: ------------------------------------------------------------------------------------------------ proc genmod data = midata5...
  4. F

    ERROR: Procedure GEE not found

    Hi Professionals, I've just read this webpage about building weighted GEE models with PROC GEE. The link is: http://support.sas.com/documentation/cdl/en/statug/67523/HTML/default/viewer.htm#statug_gee_syntax01.htm But after I tried the code on my local computer (both SAS 9.3 and 9.4), I...
  5. F

    methods for selection a subset of population to measure biomarkers

    Hi! In a quite large time-to-event clinical trial project, the population is very large (more than 1,000 people). I want to measure the subjects' bio-markers. But the issue is: the cost of measuring everyone's bio-marker is super high. So I probably would like to choose a subset of these...
  6. F

    Question about two-way anova with interaction effect

    Hi! I just read this from a textbook on the topic of two-way anova: "If interaction effect between factor A and factor B is significant, we cannot test the main effect for A or B ". I'm just not sure why it is unlikely to test the significance of main effect for A or B in an two-way anova with...
  7. F

    A question about whether dropping interaction terms as a whole or not

    Hello! I'm taking a regression course this semester and I have a question regarding when to drop the interaction terms. Suppose we have a regression model like this: Y = a + b1*X1 + b2*X2 + b3*X3 + b4*X1_X3 + b5*X2_X3 where Y is the response variable (say, the outcome of a disease), X1 and...