search for: resdf

Dear R team, I don't get what I think I should get when using anova.glm() with family="gaussian" -- please ignore this and forgive me if this turns out to be another example of a fundamental misunderstanding on my part (a highly likely event!) For example: S <- as.factor(rep(c(rep("m",2),rep("f",2)),2)) A <-

...- 182 fit$rank)) 183 wtdmu <- if (intercept) 184 sum(weights * y)/sum(weights) 185 else linkinv(offset) 186 nulldev <- sum(dev.resids(y, wtdmu, weights)) 187 n.ok <- nobs - sum(weights == 0) 188 nulldf <- n.ok - as.integer(intercept) 189 resdf <- n.ok - fit$rank 190 aic.model <- aic(y, n, mu, weights, dev) + 2 * fit$rank 191 list(coefficients = coef, residuals = residuals, fitted.values = mu, 192 effects = fit$effects, R = Rmat, rank = fit$rank, qr = fit[c("qr", 193 "rank", &quo...

Say I have a FOR-loop for computing powers (just a trivial example) for(i in 1:5) { x<-i^2 y<-i^3 } How can I create a data.frame and a 3D plot of (i,x(i),y(i)), i.e. for each iteration Thanks, Serguei Kaniovski -- ___________________________________________________________________ ??sterreichisches Institut f??r Wirtschaftsforschung (WIFO) Name: Serguei Kaniovski

...g[1],init.ok=as.logical(idiag[2]),step.fail= as.logical(idiag[3])) # unpack results back to correct place in output (which includes fixed d.f. and free d.f. terms) @@ -1247,7 +1250,7 @@ null.deviance = nulldev, iter = iter, weights = wt, prior.weights = weights, #df.residual = resdf, df.null = nulldf, y = y, converged = conv,sig2=G$sig2,edf=G$edf, - boundary = boundary,sp = G$sp,df=G$df,nsdf=G$nsdf,Vp=G$Vp,mgcv.conv=G$conv,gcv.ubre=G$gcv.ubre) + boundary = boundary,sp = G$sp,df=G$df,nsdf=G$nsdf,Vp=G$Vp,mgcv.conv=G$conv,gcv.ubre=G$gcv.ubre, hat=G$hat) }...