PHfit: Function for fitting a generalized proportional hazards model
In DTR: Estimation and Comparison of Dynamic Treatment Regimes

Description Usage Arguments Details Value References See Also Examples

The function fits a generalized proportional hazards model as proposed in Tang and Wahed (2011).

1	PHfit(data, covar=NULL)

data

a data frame (X, TR, R, Z, U, delta, ...) representing the data from a two-stage randomization design with therapies A1 and A2 available at the first stage, and B1 and B2 available at the second stage.
X: first-stage indicator, X=0 if assigned to A1, and X=1 if assigned to A2
TR: time to response
R: response status, R=1 for responders, and R=0 for non-responders
Z: second-stage indicator, Z=0 if assigned to B1, and Z=1 if assigned to B2
U: observed survival time, U is death time if delta=1, and U is censoring time if delta=0
delta: censoring indicator, delta=1 for died, and delta=0 for censored
...: other variables

covar

covariate(s) to be adjusted in the model. The default (covar=NULL) fits a model without any covariates

In sequentially randomized designs, there could be more than two therapies available at each stage. For simplicity, and to maintain similarity to the most common sequentially randomized clinical trials, a two-stage randomization design allowing two treatment options at each stage is used in the current version of the package. In detail, patients are initially randomized to either A1 or A2 at the first stage. Based on their response status, they are then randomized to either B1 or B2 at the second stage. Therefore, there are a total of four DTRs: A1B1, A1B2, A2B1, and A2B2.

The function returns an object of class coxph. See coxph.object for details.

Tang X, Wahed AS: Comparison of treatment regimes with adjustment for auxiliary variables. Journal of Applied Statistics 38(12):2925-2938, 2011

simPHdata, coxph.object

## Not run: 
data("PHdata")
f <- PHfit(data=PHdata, covar="V")
summary(f)

## End(Not run)

Call:
"coxph(Surv(U, delta) ~ X + R + XR + RZ + XRZ + V)"

  n= 573, number of events= 187 

       coef exp(coef) se(coef)      z Pr(>|z|)    
X   -0.4613    0.6305   0.1869 -2.468  0.01357 *  
R   -0.7918    0.4530   0.3266 -2.425  0.01532 *  
XR   0.6769    1.9679   0.4263  1.588  0.11229    
RZ   1.2743    3.5761   0.3557  3.583  0.00034 ***
XRZ -1.4178    0.2423   0.5105 -2.777  0.00548 ** 
V   -0.2520    0.7772   0.1539 -1.638  0.10152    
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

    exp(coef) exp(-coef) lower .95 upper .95
X      0.6305     1.5862   0.43709    0.9094
R      0.4530     2.2074   0.23886    0.8592
XR     1.9679     0.5082   0.85335    4.5379
RZ     3.5761     0.2796   1.78102    7.1803
XRZ    0.2423     4.1279   0.08907    0.6589
V      0.7772     1.2866   0.57487    1.0509

Concordance= 0.601  (se = 0.023 )
Rsquare= 0.048   (max possible= 0.968 )
Likelihood ratio test= 28.2  on 6 df,   p=8.627e-05
Wald test            = 29.91  on 6 df,   p=4.082e-05
Score (logrank) test = 31.72  on 6 df,   p=1.845e-05