Hi all, I am trying to calculate the variance-covariance matrix for parameter Beta under the null (Ho) using the "prop.odds" function in the timereg package. In other words, I am looking for Var(Beta under the null). For the Cox PH model, I used the "vcov" function and did the following: cox <- coxph(Surv(time, censor) ~ x, iter = 0, init = 0, data = dat) sig2 <- vcov(cox) Is there something similar to use for a prop.odds model? Note: Here is a simple example of how I fit a prop.odds model po <- prop.odds(Event(time, censor) ~ x, data = dat) Thanks for the help! -- View this message in context: http://r.789695.n4.nabble.com/Variance-of-parameter-Beta-under-the-null-for-Prop-Odds-tp4713037.html Sent from the R help mailing list archive at Nabble.com.