Bernstein Polynomial Based Proportional Odds Model

Fits the BPPO model to time-to-event data.

bppo(formula, degree, data, approach = c("mle", "bayes"), ...)

Arguments

formula	a Surv object with time-to-event observations, right censoring status and explanatory terms.
degree	Bernstein polynomial degree.
data	a data.frame object.
approach	Bayesian or maximum likelihood estimation methods, default is approach = "mle".
...	further arguments passed to or from other methods

Value

An object of class `spbp`.

See also

spbp, bpph and bpaft for other BP based models.

Examples

library("spsurv")
data("veteran")

fit <- bppo(Surv(time, status) ~ karno + celltype,
data = veteran)
#> Priors are ignored due to mle approach.

summary(fit)
#> Bernstein Polynomial based Proportional Odds model
#> Call:
#> spbp.default(formula = Surv(time, status) ~ karno + celltype, 
#>     degree = degree, data = veteran, approach = "mle", model = "po")
#> 
#>   n= 137, number of events= 128 
#> 
#>                       coef exp(coef) se(coef)     z Pr(>|z|)    
#> karno             -0.06127   0.94057  0.00877 -6.98  2.9e-12 ***
#> celltypesmallcell  1.28876   3.62828  0.43726  2.95   0.0032 ** 
#> celltypeadeno      1.43812   4.21275  0.47370  3.04   0.0024 ** 
#> celltypelarge      0.10805   1.11411  0.46658  0.23   0.8169    
#> ---
#> Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#> 
#> Likelihood ratio test= 73.3  on 4 df,   p=5e-15
#> Wald test            = 65.4  on 4 df,   p=2e-13