[R-sig-Geo] Test de Hosmer et Lemeshow

Komine momadou at yahoo.fr
Wed Apr 13 17:26:31 CEST 2011

Thanks very much Raphael Saldanha, 

I used this method also to verify the first. I find the same result for the
first P.Value in my first message. So I think I can interpret the first
p.value only! 

> cut.score<-cut(score,breaks=quantile(score,probs=seq(0,1,0.1)),include.lowest=T) 
> obs<-xtabs(cbind(1-Fire$Ignition,Fire$Ignition)~cut.score) 
> expect<-xtabs(cbind(1-score,score)~cut.score) 
> chisq<-sum((obs-expect)^2/expect) 
> P<-1-pchisq(chisq,10-2) 
> print(c("X^2"=chisq,DF=10-2,"p(<Chi)"=P)) 
     X^2       DF  p(<Chi) 
2.702574 8.000000 0.951615 

View this message in context: http://r-sig-geo.2731867.n2.nabble.com/Re-Test-de-Hosmer-et-Lemeshow-tp6265333p6269454.html
Sent from the R-sig-geo mailing list archive at Nabble.com.

More information about the R-sig-Geo mailing list