graemeleehickey / joineRML

R package for fitting joint models to time-to-event data and multivariate longitudinal data
GNU General Public License v3.0
30 stars 11 forks source link

given matrix is not symmetric #71

Closed zh-zhang1984 closed 3 years ago

zh-zhang1984 commented 4 years ago

How can I solve the issue raised when I run the following code?

> fit <- mjoint(
+   formLongFixed = list("PF" = PF ~ tstop  + age, 
+                        "Compiance" = Compiance ~ tstop),
+   formLongRandom = list("PF" = ~ 1 | id,
+                         "Compiance" = ~ tstop | id),
+   formSurv = Surv(dischtime,hospital_expire_flag) ~ age,
+   data = list(dtSepsis[1000:2000,], dtSepsis[1000:2000,]),
+   inits = list("gamma" = c(0.11, 1.51, 0.80)),
+   timeVar = "tstop")
Running multivariate LMM EM algorithm to establish initial parameters...
Finished multivariate LMM EM algorithm...

warning: chol(): given matrix is not symmetric

warning: chol(): given matrix is not symmetric

warning: chol(): given matrix is not symmetric

error: chol(): decomposition failed
Error in bSim(floor(nMC/2), Mi, Ai) : chol(): decomposition failed
ellessenne commented 4 years ago

Hi, do you have an example that we could use to reproduce the issue?

graemeleehickey commented 3 years ago

Closing issue as no reply to request for reprex.