Genetic.optim.AIWKME {otrKM}

The optimal treatment regime based on the (S)AIWKME estimator.

Description

Given a predetermined t0, estimate the optimal treatment regime by maximizing t0-year survival probability based on the (S)AIWKME estimator.

Usage

Genetic.optim.AIWKME(datalist, ps, prep, t0, smooth = TRUE)

Arguments

datalist

A list used to calculate the (S)AIWKME estimator including treatment named a, observed time named obs.t, censoring indicator (0, censored) named delta, and baseline covariates used to assign treatment named l. Notice that all the data in the datalist should be ordered by observed time.

ps

A list including the probability of receiving treatment given baseline covariates named fal. Fps.AIWKME can produce ps by positing logistic model.

prep

A list including the augmented terms in the numerator with treatment all to 1 named gamma.num.1 and all to 0 named gamma.num.0 and in the denominator with treatment all to 1 named gamma.den.1 and all to 0 named gamma.den.0; gamma.num.1 and the others are matrix with ordered observed time as rows and patients as columns. Fprep.AIWKME can produce prep by positing Cox proportional hazards model.

t0

A predetermined time.

smooth

A logic variable indicating wether a smoothed version should be used.

Details

More details can be found in references.

Value

A numeric vector in which the last number is the estimated optimal t0-year survival probability and others are the estimated parameters of the optimal treatment regime.

References

Jiang, R., Lu, W., Song, R., and Davidian, M. (2017) On estimation of optimal treatment regimes for maximizing t‐year survival probability. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 79: 1165-1185. DOI:10.1111/rssb.12201

Examples

# load data
data(simulation)
simulation=simulation[order(simulation$Survival),]

# convert the data into a datalist
datalist=list(z=simulation$Instrument,a=simulation$Treatment,
              obs.t=simulation$Survival,delta=simulation$Status,
              l=cbind(simulation$Covariate1,simulation$Covariate2))

# predetermined t0
t0=5

# calculate ps and prep
ps=Fps.AIWKME(datalist)
prep=Fprep.AIWKME(datalist, t0)

Genetic.optim.AIWKME(datalist, ps, prep, t0, smooth=TRUE)