krylow.pls {timereg} | R Documentation |
Fits the PLS estimator for the additive risk model based on the least squares fitting criterion
L(β,D,d) = β^T D β - 2 β^T d
where D=int Z H Z dt and d=int Z H dN.
krylow.pls(D,d,dim)
D |
defined above |
d |
defined above |
dim |
number of pls dimensions |
returns a list with the following arguments:
beta |
PLS regression coefficients |
Thomas Scheike
Martinussen and Scheike, The Aalen additive hazards model with high-dimensional regressors, submitted.
Martinussen and Scheike, Dynamic Regression Models for Survival Data, Springer (2006).
## makes data for pbc complete case data(pbc) pbc$time<-pbc$time+runif(418); pbc$time<-pbc$time/365 pbc[pbc==-9]<-NA; rsum<-apply(pbc,1,sum); pbc<-pbc[!is.na(rsum),] covs<-as.matrix(pbc[,-c(10,17)]) lcovs<-covs; lcovs[,c(3,5,6,10,11,13,17,18)]<- log(lcovs[,c(3,5,6,10,11,13,17,18)]) ## computes the matrices needed for the least squares ## criterion out<-aalen.test(Surv(time,status)~const(lcovs),pbc,robust=0,n.sim=0) S=out$intZHZ; s=out$intZHdN; out<-krylow.pls(S,s,2)