Single Variable Risk Summaries for MI BKMR fits Compute summaries of the risks associated with a change in a single variable in Z from a single level (quantile) to a second level (quantile), for the other variables in Z fixed to a specific level (quantile) for MI BKMR fits

Single Variable Risk Summaries for MI BKMR fits Compute summaries of the risks associated with a change in a single variable in Z from a single level (quantile) to a second level (quantile), for the other variables in Z fixed to a specific level (quantile) for MI BKMR fits

SingVarRiskSummaries.MI(
  BKMRfits,
  which.z = 1:ncol(BKMRfits[[1]]$Z),
  qs.diff = c(0.25, 0.75),
  q.fixed = c(0.25, 0.5, 0.75),
  q.alwaysfixed = NULL,
  index.alwaysfixed = NULL,
  sel = NULL,
  z.names = colnames(BKMRfits[[1]]$Z),
  method = "approx",
  ...
)

Arguments

BKMRfits: A list of multiple BKMR fits and that each of these fits were ran for the same number of MCMC iterations.
which.z: vector indicating which variables (columns of Z) for which the summary should be computed
qs.diff: vector indicating the two quantiles q_1 and q_2 at which to compute h(z_{q2}) -h(z_{q1})
q.fixed: vector of quantiles at which to fix the remaining predictors in Z
q.alwaysfixed: the quantile values in the point which we want to keep fixed for all comparisons
index.alwaysfixed: the index values in the point which we want to keep fixed for all comparisons
sel: selects which iterations of the MCMC sampler to use for inference
z.names: column names of the selected columns of Z in which.z
method: method for obtaining posterior summaries at a vector of new points. Options are"approx" and "exact"; defaults to "approx", which is faster particularly for large datasets
...: other arguments to pass on to the prediction function

Value

a data frame containing the (posterior mean) estimate and posterior standard deviation of the predictor risk measures

Details

For guided examples, go to https://zc2326.github.io/causalbkmr/articles/MI_BKMR.html

Examples

if (FALSE) {
library(causalbkmr)
data(BKMRfits10)
singvarrisk.MI.fixed <- SingVarRiskSummaries.MI(BKMRfits = BKMRfits10, which.z=c(1,3,4),
qs.diff = c(0.25, 0.75),  q.fixed = c(0.25, 0.50, 0.75),
q.alwaysfixed = 0.25, index.alwaysfixed = 2,
sel=sel.MI, method = "approx")

## plot the single variable dataframe for the MI fits
ggplot(singvarrisk.MI, aes(variable, est, ymin = est - 1.96*sd,
                           ymax = est + 1.96*sd, col = q.fixed)) +
  geom_hline(aes(yintercept=0), linetype="dashed", color="gray") +
  geom_pointrange(position = position_dodge(width = 0.75)) +
  coord_flip() + ggtitle("")+
  scale_x_discrete(name="Variable")+ scale_y_continuous(name="estimate")
}