Hi,
 
I am using flexmix to model some data which is modelled  with linear 
regressions.  I have results obtained along the lines of that shown below, and 
can retreive component parameters, but I cannot find a way or retrieving the 
variance of the sigma (variance of the normal model) can anyone advise how to 
do this?:
 
>fm=compiledstepFlexmix(lkopsum ~ 
>lfasttax+ypr+ypr2,data=land,k=k,nrep=2000,control=Fcontrol)
>fmexample=fm@models$'3'
fmexample
Call:
compiledstepFlexmix(lkopsum ~ lfasttax + ypr + ypr2, data = land,
    control = Fcontrol, k = 3, nrep = 500)
Cluster sizes:
  1   2   3
325 425 216
convergence after 57 iterations
> refitexample=refit(fmexample)
> summary(refitexample)
$Comp.1
             Estimate Std. Error z value  Pr(>|z|)
(Intercept) 8.3713863  0.1165509 71.8260 < 2.2e-16 ***
lfasttax    0.7921171  0.0190065 41.6762 < 2.2e-16 ***
ypr         0.0641430  0.0048686 13.1747 < 2.2e-16 ***
ypr2        0.0044674  0.0012131  3.6827 0.0002308 ***
---
Signif. codes:  0 â***â 0.001 â**â 0.01 â*â 0.05 â.â 0.1 â â 1
$Comp.2
              Estimate Std. Error z value Pr(>|z|)
(Intercept)  6.2262676  0.1340461  46.449   <2e-16 ***
lfasttax     1.0864937  0.0196605  55.263   <2e-16 ***
ypr          0.1129625  0.0057275  19.723   <2e-16 ***
ypr2        -0.0029301  0.0010706  -2.737   0.0062 **
---
Signif. codes:  0 â***â 0.001 â**â 0.01 â*â 0.05 â.â 0.1 â â 1
$Comp.3
             Estimate Std. Error z value  Pr(>|z|)
(Intercept) 8.4120331  0.3045145 27.6244 < 2.2e-16 ***
lfasttax    0.6394828  0.0504086 12.6860 < 2.2e-16 ***
ypr         0.0701468  0.0155021  4.5250  6.04e-06 ***
ypr2        0.0110253  0.0034031  3.2397  0.001196 **
---
Signif. codes:  0 â***â 0.001 â**â 0.01 â*â 0.05 â.â 0.1 â â 1

                                          
        [[alternative HTML version deleted]]

______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Reply via email to