search for: bfit

...      tframe[,var.num] <- var.values         xmat <- model.matrix(cfit,data=tframe)[,-1]         tlps <- as.vector(xmat%*%cfit$coef)         names(tlps) <- var.values         obs.off <- tlps[as.character(obs.var)]          explp.off <- exp(outer(lps - obs.off ,tlps,"+")) bfit <- survfit.coxph(cfit, se.fit = F)         fits <- outer(bfit$surv,explp.off,function(x,y) x^y)         avg.fits <-             apply(sweep(fits,2,weights,"*"),c(1,3),sum)/sum(weights)         dimnames(avg.fits) <- list(NULL,var.values)         list(time=bfit$time,fits=avg.fit...

...tframe[,var.num] <- var.values xmat <- model.matrix(cfit,data=tframe)[,-1] tlps <- as.vector(xmat%*%cfit$coef) names(tlps) <- var.values obs.off <- tlps[as.character(obs.var)] explp.off <- exp(outer(lps - obs.off ,tlps,"+")) bfit <- survfit.coxph(cfit, se.fit = F) fits <- outer(bfit$surv,explp.off,function(x,y) x^y) avg.fits <- apply(sweep(fits,2,weights,"*"),c(1,3),sum)/sum(weights) dimnames(avg.fits) <- list(NULL,var.values) list(time=bfit$time,fits=avg...

...panel function) through each of multiple data series plotted on the same graph? Specifically, while one can do something like xyplot(a+b+c~x) which plots three series, a,b & c, but can one automatically fit lines through each of them? I suppose one could generate three more variables afit, bfit, and cfit with a model & predict and then plot them, but wondered if there was an easier way. Thank you for any advice. Here is an example: # use an example panel function using smooth.spline; however, the issue relates to all panel functions # a panel function to fit smoothed lines through...