Displaying 2 results from an estimated 2 matches for "qb1".
Did you mean:
b1
2005 Oct 20
3
different F test in drop1 and anova
Hi,
I was wondering why anova() and drop1() give different tail
probabilities for F tests.
I guess overdispersion is calculated differently in the following
example, but why?
Thanks for any advice,
Tom
For example:
> x<-c(2,3,4,5,6)
> y<-c(0,1,0,0,1)
> b1<-glm(y~x,binomial)
> b2<-glm(y~1,binomial)
> drop1(b1,test="F")
Single term deletions
Model:
y ~
2009 Jul 23
1
[PATCH server] changes required for fedora rawhide inclusion.
...je^o()D43k2DG%
z76AX3g+bLr4sU$t8OUn}Liq?~N6Dv`Pvj+>acoXqEM2$FulKd4o!bssfHKh`%o~w&
zammc*n}!@7?m!M;(EW0g^2M9eRxMZ=|0wdCY1gy7YyIcHmS5+8yfN+K<A(T?UcLIy
z_o-<>|7r6*uZ`{FR&)xOQ}SiRr4?H`rw`d>*LaO>n(ya!Ii=vi2chHqt4HRHzB+a0
z#fuNpC%t#Q&w)7)#A^oq=go1wn}g;YSx~HeICRdm%}@G{*#6CoPlwqb1Z=*1VdggD
z<*5bl57n>kEKVmNA?pho9{pY$aj)}~xq(vTr{6ukX;S}LcNV{_)^3>D at Mlz5+UZB(
znTJ8IE=fZ9ZE5`~)rOsGvv1Da6khoCppqeJ<RajAY92AJ-+HeP>{F{A9bG=B*H+i{
zKMnJq2UZ at 8|Neu)^&9U!-xeG5!wDcY#e!?sPR*)+4mu7=5_cNvw|3E!ae;7J-4B9~
z{&x9iguvs%16$)9q9+$Tz6>gRkrH(=_w=H9y7S=y7EdDUIB54yUG9V%N...