station.test: Test the Stationarity Assumption
In CoxPhLb: Analyzing Right-Censored Length-Biased Data

Description Usage Arguments Details Value References See Also Examples

Tests the null hypothesis that the incidence process is stationary.

1	station.test(a, v, delta, digits = 3L)

`a`	A vector of backward recurrence time (i.e., left-truncation time).
`v`	A vector of forward recurrence time (i.e., failure time minus left-truncation time).
`delta`	A vector of censoring indicator, 0=censored, 1=uncensored.
`digits`	An integer controlling the number of digits to print.

The stationarity assumption is checked by computing the test statistic and the corresponding p-value. A large p-value suggests strong evidence of stationarity. When the p-value is small (e.g., <0.05), it is likely that the stationarity assumption is violated.

A list containing the following components:

`test.statistic`	A test statistic.
`p.value`	A p-value based on two-sided test.
	The list is returned as an object of the `station.test` class. Objects of this class have methods for the function `print`. The object also contains the following: `result`, the table output.

Addona, V. and Wolfson, D. B. (2006). A formal test for the stationarity of the incidence rate using data from a prevalent cohort study with follow-up. Lifetime data analysis, 12(3), 267-284.

coxphlb, coxphlb.ftest, coxphlb.phtest, station.test.plot

# Check the Stationarity Assumption
stest1 <- station.test(ExampleData1$a, ExampleData1$y-ExampleData1$a,
                       ExampleData1$delta)
print(stest1) 			# display the results

stest2 <- station.test(ExampleData2$a, ExampleData2$y-ExampleData2$a,
                       ExampleData2$delta)
print(stest2)   		# display the results