# Predict vs. Impute: Filling missing data using Random Forest

I am using R package randomForest to build a Random Forest model for classification. Ultimately, I need to choose one of five programs for a group of individuals based on historical data. The final variable that is being predicted is a categorical "1, 2, 3, 4, or 5" variable.

I need to incorporate 30-40 variables--their importance will also be analyzed-- to reach a decision for each individual.

Will I be imputing or predicting data? Does it matter? For imputation, I will use randomForest::rfImpute(). For prediction, I will use randomForest:::predict.randomForest().

Please keep in mind, this data is current, in that a sample has already been collected that contains program type (1, 2, 3, 4, or 5) for each individual and will be used to impute/predict program type for the rest of the population.

Will I need to change between impute and predict at any point? If so, can you provide a scenario?