Localised average causal effects

lace computes the localised average causal effect for each quantile.

Usage

lace(
  y,
  x,
  g,
  covar = NULL,
  q,
  x0q,
  xc_sub = TRUE,
  family = "gaussian",
  xpos = "mean"
)

y: vector of outcome values
x: vector of exposure values
g: the instrumental variable
covar: data.frame of covariates
q: the number of quantiles the exposure distribution is to be split into within which a causal effect will be fitted, known as localised average causal effects (LACE) (default: 10)
x0q: quantiles of x0 (the IV-free exposure)
xc_sub: compute the association between the exposure and the insturment in each quantile of x0
family: a description of the error distribution and link function to be used in the model and is a character string naming either the gaussian (i.e. "gaussian" for continuous data) or binomial (i.e. "binomial" for binary data) family function (default: "gaussian")
xpos: the position used to relate x to the localised average causal effect, this can either be the mean of the x-values within each quantile or a percentile (e.g. 0.5 corresponds to the median value) (default: "mean")

lace returns a data.frame of the LACE for quantile:

coef: the LACE in each quantile
coef_se: the standard error of the LACE in each quantile
xmean: the mean of the exposure in each quantile
xcoef_sub: the association between the exposure and the instrument in each quantile
xcoef_sub_se: the standard error of the association between the exposure and the instrument in each quantile