tvcFlex: Estimate the TD and/or NL effect(s) of time-varying...

In ywang297/CoxFlex: Flexible Modeling of the Time-to-Event Data

Estimate the TD and/or NL effect(s) of time-varying continuous covariate(s) in time-to-event analysis

Description

Estimate the TD and/or NL effect(s) of time-varying continuous covariate(s) in time-to-event analysis

Usage

tvcFlex(data, Type, variables, TD, NL, TEL, m, p, knots)

Arguments

data	A data frame in the long (interval) format with one line per unit of time.
Type	A vector consisting the name of variables representing the start/stop of each time interval, event indicator, and names of variable representing the TEL of each sparsely mearused time-varying covariates. e.g. c("start","stop","event","tel").
variables	A vector consisting the name of varialbes that will be adjusted in the model.
TD	A vector of binary indicators representing whether the corresponding variable has a time-dependent effect or not (1=Yes, 0=No).
NL	A vector of binary indicators representing whether the corresponding variable has a non-linear effect or not (1=Yes, 0=No).
TEL	A vector of binary indicators representing whether to adjust the TEL effect of the corresponding variable (1=Yes, 0=No).
m	The number of interior knots used in the regression B-spline
p	The degree of the regression B-spline
knots	Default value is -999, set the knots at the default place.

Value

Returns a list of the following items:

PLL	partial loglikelihood of the final model
NP	number of parameters estimated in the model
NE	number of events in the dataset
knots_covariates	knots for splines of NL effects for corresponding covariates
knots_time	knots for splines of the TD effect
knots_TEL	knots for splines of the TEL effect
variables	name of the covariates in the order they are adjusted in the model
coefficients_splines_NL	estimated splines coefficients for NL effects
coefficients_splines_TD	estimated splines coefficients for TD effects
coefficients_splines_TEL	estimated splines coefficients for TEL effects
coef	estimated coefficients for covariates not having TD and NL effects
sd	standard errors of the corresponding estimated coefficients
pval	p-values for corresponding estimated effects

Note

Note that the TD and NL arguments have different meanings than that in the BackSelection

ywang297/CoxFlex documentation built on March 18, 2024, 3:26 a.m.