Impute missing binary responses and analyze each imputed data set

Performs independent Bernoulli imputations for missing binary responses in the control and treatment groups, then calculates a CMH risk difference and p-value for each imputed data set. Only observations in ctrlab and trtlab are included in the analysis.

Usage

h_impute_analyze_resp(
  dat,
  p_ctrl,
  p_trt,
  trtvar,
  ctrlab,
  trtlab,
  respvar,
  stratvar,
  n_imputations
)

Arguments

dat

(data.frame) Analysis data containing treatment, response, and stratification variables.

p_ctrl

(numeric(1)) Probability of response used to impute missing control-group responses.

p_trt

(numeric(1)) Probability of response used to impute missing treatment-group responses.

trtvar

(string) Name of the treatment variable in dat.

ctrlab

(string) Value of trtvar identifying the control group.

trtlab

(string) Value of trtvar identifying the treatment group.

respvar

(string) Name of a logical binary response variable in dat. Missing values are imputed; observed values are retained.

stratvar

(character) Names of one or more stratification variables in dat. Stratification variables must not be missing in the analysis groups.

n_imputations

(count) Number of independently imputed data sets to analyze.

Value

A tibble with one row per imputation and the following columns:

• rd_est: CMH risk-difference estimate.

• rd_se: standard error of the risk-difference estimate.

• rd_var: variance of the risk-difference estimate.

• p_cmh: CMH p-value using the Wilson-Hilferty transformation.

• z_stat: Wilson-Hilferty z statistic used to calculate p_cmh.