[R] Variance estimates for survreg vs. lm

2015-07-03 Thread Richard Perry
I would like help understanding why a survival regression with no censored data-points does not give the same variance estimates as a linear model (see code below). I think it must be something to do with the fact that the variance is an actual parameter in the survival version via the log(scale),

Re: [R] Possible bug in rlm

2015-04-24 Thread Richard Perry
Have just checked with R 3.2.0 and MASS 7.3-40 and there still appears to be a problem/strangeness at around k=2.5 On 23 April 2015 at 14:09, Francis Bursa wrote: > Dear all, > > I believe I have found a bug in rlm in the MASS package. Specifically, the > scale estimate can be wrong when there