summary.tmle {tmleLite} | R Documentation |
These functions are all methods for class tmle
or summary.tmle
objects
summary.tmle(object,...) print.tmle(object,...) print.summary.tmle(object,...)
object |
an object of class tmle for summary.tmle and print.tmle , class summary.tmle for print.summary.tmle . |
... |
currently ignored. |
print.tmle
prints the estimate, variance, p-value, and 95% confidence interval only. print.summary.tmle
, called indirectly by entering the command summary(result) (where result
has class tmle
), outputs additional information.
psi |
additive treatment effect estimate |
var |
variance of estimate, based on the influence curve |
pvalue |
two-sided p-value |
CI |
95% confidence interval |
epsilon |
MLE for coefficient used in targeting step |
Qmodel |
working model used to obtain initial estimate of Q portion of the likelihood |
Qterms |
terms in the model for Q |
Qcoef |
coefficient of each term in model for Q |
g_Amodel |
model used to estimate treatment mechanism g_A |
g_Aterms |
terms in the treatment mechanism model |
g_Acoef |
coefficient of each term in model for treatment mechanism |
g_Mmodel |
model used to estimate missingness mechanism g_M |
g_Mterms |
terms in the missingness mechanism model |
g_Mcoef |
coefficient of each term in model for missingness mechanism |
Susan Gruber
# generate data n <- 500 W <- matrix(rnorm(n*3), ncol=3) A <- rbinom(n,1, 1/(1+exp(-(.1*W[,1] - .1*W[,2] + .5*W[,3])))) Y <- A + 2*W[,1] + W[,3] + W[,2]^2 + rnorm(n) colnames(W) <- paste("W",1:3, sep="") result <- tmle(Y,A,W, Q=Y~A+W1, g_A=rep(.5, n)) summary(result)