tian_ve: Estimate VE using method from Tian et al. 2005

In fluvee/wave: Waning Vaccine Effectiveness

Estimate VE using method from Tian et al. 2005

Description

In this method, kernel-weighted partial likelihood approach is used to estimate the time-dependent coefficient in the generalized Cox model [REF] . At each time point, the estimate is obtained by maximizing a smooth concave function of a p x 1 vector of parameters, where p is the dimension of the vector of covariates. To test the hypothesis of no VE waning (i.e., the proportional hazards assumption is met), confidence bands from the distribution of the estimated cumulative function of beta(t) can be obtained. If the line (0,0) is not contained within the confidence band s over the entire time interval, then the proportional hazards assumption is not met and the null hypothesis of no VE waning is rejected.

Usage

tian_ve(dat, n_days, n_periods, n_days_period, alpha = 0.05)

Arguments

dat	data set
n_days	number of days in the study
n_periods	number of periods in the study
n_days_period	number of days per period
alpha	hypothesis critical value

Value

number of times the null hypothesis is rejected

fluvee/wave documentation built on Nov. 9, 2023, 12:31 p.m.