The function is called by the wrapper. We consider data to be "semicontinuous" when more than 5% of the (non categorical) observations. For example in surveys a certain portion of people, when asked for their income, report "0", which clearly violates the assumption of income to be (log-) normally distributed.
imp_semicont_single(y_imp, X_imp, spike = NULL, pvalue = 0.2,
k = Inf)A Vector with the variable to impute.
A data.frame with the fixed effects variables.
A numeric value saying to which value Y might be spiked.
A numeric between 0 and 1 denoting the threshold of p-values a variable in the imputation model should not exceed. If they do, they are excluded from the imputation model.
An integer defining the allowed maximum of levels in a factor covariate.
A n x 1 data.frame with the original and imputed values.