A comparison of various software tools for dealing with missing data via imputation

摘要: In real-life situations, we often encounter data sets containing missing observations. Statistical methods that address missingness have been extensively studied in recent years. One of the more popular approaches involves imputation values prior to analysis, thereby rendering complete. Imputation broadly encompasses an entire scope techniques developed make inferences about incomplete data, ranging from very simple strategies (e.g. mean imputation) advanced require estimation, for instance, posterior distributions using Markov chain Monte Carlo methods. Additional complexity arises when number patterns increases and/or both categorical and continuous random variables are involved. Implementation routines, procedures, or packages capable generating imputations now widely available. We review some these context a motivating example, as well simulation study,...