cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Search instead for 
Did you mean: 
Marc-Flo
‎08-14-2020
  • 3 Posts
  • 0 Likes Given
  • 0 Solutions
  • 0 Likes Received

Re: standard variance components structure for GLMM

by Calcite | Level 5 in Statistical Procedures
‎08-04-2020 07:54 AM
‎08-04-2020 07:54 AM
Hello Steve and thank you for your answer. Here's the code I use: PROC GLIMMIX DATA=suivi_file METHOD=laplace IC=q NOCLPRINT; CLASS id_pat profil sexe prescr ass_so tble_psy; EFFECT spl_tps=SPLINE(temps / DEGREE=1 KNOTMETHOD=LIST(70) DETAILS); MODEL bilan(EVENT='1') = spl_tps|profil age sexe tble_psy ass_so prescr / DIST = BINARY LINK=LOGIT S INTERCEPT; RANDOM INTERCEPT temps / SUB=id_pat TYPE=VC; RUN; I should precise that the number of repeated time points is variable between subject and varies from 1 to 18. Also, time points are not evenly spaced in time. So far, my best two candidates as covariance structure are VC (AICC = 39401.8) and ANTE(1) (AICC=39402.5). Considering the low difference between these two results I might be tempted to choose the ante-dependence structure which makes more sense in a repeated measures situation. Thank you for your future response.   ... View more

standard variance components structure for GLMM

by Calcite | Level 5 in Statistical Procedures
‎08-03-2020 09:41 AM
‎08-03-2020 09:41 AM
Hello everyone. I'm currently working on a GLMM for a repeated measures design whith a binary outcome. I use PROC GLIMMIX to do so and I've compared different covariance structures using information criteria. The standard variance components structure (TYPE=VC) gives me the lowest BIC so far. Since I'm working on repeated measures, I'm a bit doubtful about how I should interpret this. Does this mean that the different measures for a same individual are absolutely not correlated ? Therefore would a simple logistic regression gives me the same results ? Thank you by advance. Marc ... View more

Getting Odds Ratio in PROC GLIMMIX with spline function

by Calcite | Level 5 in Statistical Procedures
‎07-03-2020 08:34 AM
‎07-03-2020 08:34 AM
Hello. I'm currently trying to fit a GLMM for a longitudinal analysis. In this analysis the dependent variable is binary and is measured several times per subject. We've noticed that the evolution of the response of this dependent variable is clearly not linear over time. In order to take this phenomenon into account, we've insert a spline function over the time covariate.  At present the initial model look like this: PROC GLIMMIX DATA = data METHOD = LAPLACE; CLASS ind profil; EFFECT spline_time=SPLINE(time / KNOTMETHOD=PERCENTILES(9) DEGREE = 1); MODEL var_dep(EVENT='1') = spline_time|profil / DIST=BIN LINK = LOGIT; RANDOM INT time / SUBJECT = ind; RUN; The problem with the spline function is that I can't get any odds ratio, even for covariates without spline function. Is there any way (maybe a macro) to display the odds ratio ? Thank you. ... View more
Contact Me
Online Status
Offline
Date Last Visited
‎08-14-2020 12:43 PM
Quick links