lss.mod: Modified Least Squares Pricnciple for Solving the AFT Model

Description Usage Arguments Details Value Author(s) References See Also Examples

View source: R/imputeYn.R

Description

This provides modified results as the package lss developed by Jin et al. (2006).

Usage

1
2
lss.mod(formula, data, subset, trace = FALSE, mcsize = 500, maxiter = 10, 
tolerance = 0.001, cov = FALSE, na.action = na.exclude, residue = FALSE)

Arguments

formula

specifies a model to be fitted. The response and covariates of the model are separated by a ~ operator. The response, on the left side of ~, should be a Surv object with two columns, of which the first column is the survival time or censored time and the second column is the censoring indicator. The covariates X, on the right side of ~, should be columns with the same length as Surv object. eg: lss(Surv(time, status)~).

data

a data frame that contains the Surv objects and covariates.

subset

specifies subset of the original data frame that should be used for the model fit.

trace

takes logical values TRUE or FALSE. If TRUE, then the summary of every iteration will be kept. Default is FALSE.

mcsize

specifies the resampling number. The default is 500.

maxiter

specifies the maximum iteration number. The iterations will be stopped after maxiter iterations if the convergence criterion is not met. Default is 50.

tolerance

specifies the value of convergence criterion. Default is 0.01.

cov

takes logical values TRUE or FALSE. If cov=TRUE, the covariance matrices ofthe least-squares estimator will be printed. Default is FALSE.

na.action

takes values na.exclude or na.fail. The default is na.exclude, which deletes the observations with missing values. The other choice is na.fail, which returns an error if any missing values are found.

residue

takes two value TRUE or FALSE. Default is FALSE. If TRUE then it shows the residuals.

Details

This is a modified version of the package lss developed by Jin et al. (2006). The Least squares principle is developed for solving the AFT model with possibly right censored data. The modification is done by introducing a ridge estimator as an initial estimator that takes into account the correlation between the covariates and censoring information while optimizing using quadratic programming.

Value

The least-squares estimator, the standard error of the least-squares estimator, the Z score and the p-value for testing the hypothesis of beta=0. The covariance matrices of the least-squares estimator, if cov is set to T.

Author(s)

Hasinur Rahaman Khan and Ewart Shaw

References

Jin et al. (2006). On least-squares regression with censored data. Biometrika, 93 (1), 147-161.

Khan and Shaw. (2013a). On Dealing with Censored Largest Observations under Weighted Least Squares. CRiSM working paper, Department of Statistics, University of Warwick, UK, No. 13-07. Also available in http://arxiv.org/abs/1312.2533.

See Also

imputeYn, print.imputeYn

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
# For uncorrelated datset with four covariates and 50 percent censoring 
data1<-data(n=100, p=4, r=0, b1=c(2,2,3,3), sig=1, Cper=0)
require(package="quadprog")
## Not run: fit.lss.mod<-lss.mod(cbind(data1$y, data1$delta) ~ data1$x,mcsize=500,trace=FALSE,maxiter=50,
 tolerance=0.01)
## End(Not run)
## Not run: fit.lss.mod

# For correlated datset with 50 percent censoring 
data2<-data(n=100, p=4, r=0.5, b1=c(2,2,3,3), sig=1, Cper=0)
## Not run: fit.lss.mod2<-lss.mod(cbind(data2$y, data2$delta) ~ data2$x, mcsize=500,trace=FALSE,
 maxiter=50, tolerance=0.01)
## End(Not run)
## Not run: fit.lss.mod2

imputeYn documentation built on May 1, 2019, 10:52 p.m.