rld (version 1.0)

lrtest: Likelihood Ratio Test

Description

This function performs likelihood ratio test (LRT) to test regression paramters in the mean model and frailty variance paramter nu.

Usage

lrtest(model1, model2, TestNu=TRUE, Siglevel=0.05)

Arguments

model1

a result of the nested model which is returned by rld.

model2

a result of the full model which is returned by rld.

TestNu

logic value: If TRUE, the frailty variance paramter will be tested. Otherwise, the regression parameters will be tested. The default is TRUE.

Siglevel

a value: significance level. The default is 0.05.

Value

Details

Under the null hypothesis of frailty variance parameter nu=0, the test statistic converges to a mixture of chi-squared distribution. For regression parameters, under the null hypothesis beta=0, the test statistic converges to chi-squared distribution. Please refer to Kang et al.(2015) for more details.

References

Kang, C., Huang, Y., and Miller, C. (2015). A discrete-time survival model with random effects for designing and analyzing repeated low-dose challenge experiments. Biostatistics, 16(2): 295-310.

See Also

rld

Examples

#test frailty variance parameter
data(SampleData)
newdata <- transdata(data = SampleData, ndlevel = 3, nexposure = c(10, 10, 2))
fitout1 <- rld(formula = survival::Surv(time, delta)~factor(trt)+factor(dose), data = newdata,
               frailty = FALSE)
fitout2 <- rld(formula = survival::Surv(time, delta)~factor(trt)+factor(dose), data = newdata,
               frailty = TRUE)
testnu <- lrtest(model1 = fitout1, model2 = fitout2, TestNu=TRUE)

## Not run: 
# #test regression parameters
# fitout3 <- rld(formula = survival::Surv(time, delta)~factor(dose), data = newdata,
#                frailty = TRUE)
# fitout4 <- rld(formula = survival::Surv(time, delta)~factor(trt)+factor(dose), data = newdata,
#                frailty = TRUE)
# testbeta <- lrtest(model1 = fitout3, model2 = fitout4, TestNu=FALSE)
# ## End(Not run)