pred.smooth.surv

Helper function; calculates the estimated probability of survival for control 
group for control group surrogate values using treatment group surrogate and 
outcome information.

robust

internal

smooth

nonparametric

survival

Provides functions to estimate the proportion of treatment effect on the primary outcome that is explained by the treatment effect on the surrogate marker.

Layla Parast

Rsurrogate

Robust Estimation of the Proportion of Treatment Effect
Explained by Surrogate Marker Information

pred.smooth.surv function

<dl> <dt>xone.f</dt>
<dd>
observed event times in the treatment group</dd> <dt>deltaone.f</dt>
<dd>
censoring indicators in the treatment group</dd> <dt>sone.f</dt>
<dd>
surrogate marker values in the treatment group</dd> <dt>szero.one</dt>
<dd>
surrogate marker values in the control group</dd> <dt>myt</dt>
<dd>
time of interest</dd> <dt>weight.pred</dt>
<dd>
weight used for perturbation resampling</dd> <dt>extrapolate</dt>
<dd>
TRUE or FALSE; indicates whether local constant extrapolation should be used, default is FALSE</dd> <dt>transform</dt>
<dd>
TRUE or FALSE; indicates whether a transformation should be used, default is FALSE</dd> <dt>ps.weight</dt>
<dd>
vector of propensity score weights to be used in the multiple marker setting, default is NULL</dd>
 <dt>warn.support</dt>
<dd>
value passed from R.s.estimate function to control warnings; user does not need to specify.</dd></dl>

Arguments

Layla Parast

Author


Calculates the conditional probability of survival for control group values — pred.smooth.surv

<dl>

 <dt>xone.f</dt>
<dd>
observed event times in the treatment group</dd>

 <dt>deltaone.f</dt>
<dd>
censoring indicators in the treatment group</dd>

 <dt>sone.f</dt>
<dd>
surrogate marker values in the treatment group</dd>

 <dt>szero.one</dt>
<dd>
surrogate marker values in the control group</dd>

 <dt>myt</dt>
<dd>
time of interest</dd>

 <dt>weight.pred</dt>
<dd>
weight used for perturbation resampling</dd>

 <dt>extrapolate</dt>
<dd>
TRUE or FALSE; indicates whether local constant extrapolation should be used, default is FALSE</dd>

 <dt>transform</dt>
<dd>
TRUE or FALSE; indicates whether a transformation should be used, default is FALSE</dd>

 <dt>ps.weight</dt>
<dd>
vector of propensity score weights to be used in the multiple marker setting, default is NULL</dd>


 <dt>warn.support</dt>
<dd>
value passed from R.s.estimate function to control warnings; user does not need to specify.</dd>



</dl>

pred.smooth.surv: Calculates the conditional probability of survival for control group values

Description

Usage

Value

Arguments

Author

Details