Hotdeck imputation is especially useful for discrete variables (e.g 0/1 dummy variable) where the imputed values shouldn't take any other values. Regression imputation with {cmd:impute} would result into intermediate values (e.g. 0.56 for 0/1 dummy variables).
Often stratified hotdeck is of interest. The ado file "missingstrata" divides observations into 10 strata. Each stratum represents observations with a similar probability that the first variable of varlist is missing. The strata variable generated can be used for subsequent hotdeck imputation within each stratum.