42 sshzd Examples ## 1-D estimate: Buffalo snowfall data(buffalo) buff.fit
sshzd 43 Description Estimate hazard function using smoothing spline ANOVA models. <strong>The</strong> symbolic model specification via formula follows the same rules as in lm, but with the response of a special form. Usage sshzd(formula, type=NULL, data=list(), alpha=1.4, weights=NULL, subset, na.action=na.omit, id.basis=NULL, nbasis=NULL, seed=NULL, prec=1e-7, maxiter=30) Arguments formula type data alpha weights subset na.action id.basis nbasis seed prec maxiter Symbolic description of the model to be fit, where the response is of the form Surv(futime,status,start=0). List specifying the type of spline for each variable. See mkterm for details. Optional data frame containing the variables in the model. Parameter defining cross-validation score for smoothing parameter selection. Optional vector of counts for duplicated data. Optional vector specifying a subset of observations to be used in the fitting process. Function which indicates what should happen when the data contain NAs. Index of observations to be used as "knots." Number of "knots" to be used. Ignored when id.basis is specified. Seed to be used for the random generation of "knots." Ignored when id.basis is specified. Precision requirement for internal iterations. Maximum number of iterations allowed for internal iterations. Details <strong>The</strong> model specification via formula is for the log hazard. For example, Suve(t,d)~t*u prescribes a model of the form logf(t, u) = C + g t (t) + g u (u) + g t,u (t, u) with the terms denoted by "1", "t", "u", and "t:u". Replacing t*u by t+u in the formula, one gets a proportional hazard model with g t,u = 0. sshzd takes standard right-censored lifetime data, with possible left-truncation and covariates; in Surv(futime,status,start=0)~..., futime is the follow-up time, status is the censoring indicator, and start is the optional left-truncation time. <strong>The</strong> main effect of futime must appear in the model terms specified via .... Parallel to those in a ssanova object, the model terms are sums of unpenalized and penalized terms. Attached to every penalized term there is a smoothing parameter, and the model complexity is largely determined by the number of smoothing parameters.
- Page 1 and 2: The gss Package February 16, 2008 V
- Page 3 and 4: aids 3 Source Douglas, A. and Delam
- Page 5 and 6: cdssden 5 Format Source A vector of
- Page 7 and 8: dssden 7 References Gu, C. (2002),
- Page 9 and 10: family 9 cfit.nbinomial(y, wt, offs
- Page 11 and 12: gauss.quad 11 Source Moreau, T., O
- Page 13 and 14: gssanova 13 Value gssanova returns
- Page 15 and 16: gssanova0 15 data weights subset Op
- Page 17 and 18: hzdrate.sshzd 17 ## Not run: rm(tes
- Page 19 and 20: mkfun.tp 19 See Also mkterm, mkfun.
- Page 21 and 22: mkran 21 The Z matrix is determined
- Page 23 and 24: mkterm 23 mkterm Assembling Model T
- Page 25 and 26: nlm0 25 fit1
- Page 27 and 28: ozone 27 Format A data frame contai
- Page 29 and 30: predict.ssanova 29 Value For se.fit
- Page 31 and 32: project 31 project Projecting Smoot
- Page 33 and 34: kpk0 33 nu varht random dc sr y0 Op
- Page 35 and 36: ssanova 35 Arguments d k Dimension
- Page 37 and 38: ssanova0 37 References Gu, C. (2002
- Page 39 and 40: ssanova0 39 Note For complex models
- Page 41: ssden 41 The selective term elimina
- Page 45 and 46: summary.gssanova 45 ## Not run: dat
- Page 47 and 48: summary.gssanova0 47 References Gu,
- Page 49 and 50: wesdr 49 Value summary.ssanova retu
- Page 51 and 52: Index ∗Topic datasets aids, 2 bac
- Page 53: INDEX 53 mkrk.sphere, 22 mkrk.spher