sensitivityJR(z, s, y, beta0, beta1, phi, Pi, psi,
selection, groupings,
ci = 0.95, ci.method = c("analytic","bootstrap"),
na.rm = FALSE, N.boot = 100, interval = c(-100, 100),
oneSidedTest = FALSE, twoSidedTest = TRUE,
verbose=getOption("verbose"), isSlaveMode = FALSE)
NA
for
unselected records.psi
is the log-odds ratio of selection.
Pi
is the probability of being in the as
indicating selection.c(g0,g1)
, the first element g0
being the
value of z
the delineates the first group, the last element
g1
being the value of z
which delineates the second group.c("analytic","bootstrap")
NA
values should be
removed from the data set.ci.method
includes FALSE
TRUE
sensitivity3d
beta0
,
beta1
, and phi/Pi/psi
. Array dimensions are length(beta0)
,
length(beta1)
, length(psi)
.quantile
if using
ci.method
ACE
element.ACE
element.Shepherd BE, Redman MW, Ankerst DP (2008), "Does Finasteride affect the severity of prostate cancer? A causal sensitivity analysis," Journal of the American Statistical Association 2008, 484, 1392-1404. Shepherd BE, Gilbert PB, and Dupont CT, "Sensitivity analyses comparing time-to-event outcomes only existing in a subset selected postrandomization and relaxing monotonicity," Biometrics, in press.
sensitivityGBH
,
sensitivitySGD
data(vaccine.trial)
ansJR<-with(vaccine.trial,
sensitivityJR(z=treatment,s=hiv.outcome,y=logVL,
beta0=c(-1,-.75,-.5,-.25,0,.25,.5,.75,1),
beta1=c(-1,-.75,-.5,-.25,0,.25,.5,.75,1),
phi=c(0.95,0.90,0.80), selection="infected",
groupings=c("placebo","vaccine"),
N.boot=100)
)
ansJR
Run the code above in your browser using DataLab