proprate2.gs {surv2sample} | R Documentation |
Checks the assumption of proportional rates (proportional hazards, proportional odds) in two samples of right-censored data using the Gill–Schumacher test based on the comparison of two estimates of the rate ratio.
proprate2.gs(x, group, model = 0, weight1 = "logrank", weight2 = "prentice")
x |
a "Surv" object, as returned by the Surv
function. |
group |
a vector indicating to which group each observation belongs. May contain values 1 and 2 only. |
model |
the type of model. Possible values are 0 for proportional hazards, 1 for proportional odds. |
weight1, weight2 |
weight functions for the ratio estimates.
Possible values are "logrank" , "prentice" ,
"gehan" . |
This function performs the Gill–Schumacher test of the hypothesis that transformation rates (currently hazard rates or odds functions) are proportional (their ratio is constant in time) in two samples of censored survival data.
The test was proposed by Gill and Schumacher (1987) for proportional hazards, see Kraus (2007) for its extension to proportional transformation rates. The test statistic compares two weighted estimates of the ratio of rates. Possible weights are of the logrank, Prentice–Wilcoxon or Gehan type.
A "proprate2.gs"
object with components:
stat |
the test statistic. |
pval |
the p-value. |
eta1, eta2 |
weighted estimates of the rate ratio. |
Some of input parameters are included too.
David Kraus (http://www.davidkraus.net/)
Gill, R. and Schumacher, M. (1987) A simple test of the proportional hazards assumption. Biometrika 74, 289–300.
Kraus, D. (2007) Checking proportional rates in the two-sample transformation model. Research Report 2203, Institute of Information Theory and Automation, Prague. Available at http://www.davidkraus.net/surv2sample/.
proprate2.neyman
, proprate2.ks
for other
tests of the proportional rate assumption
proprate2
for the simplified partial likelihood estimation
## chronic active hepatitis data data(hepatitis) ## perform the Gill--Schumacher test of proportional odds proprate2.gs(Surv(hepatitis$time, hepatitis$status), hepatitis$treatment, model = 1)