Condition-based maintenance (CBM) is a maintenance approach wherein equipment repair or replacement decisions are based on the current and projected health of the equipment measured by periodic collection and analysis of data. In this context, the accuracy of data is vital. Unfortunately, missing and inaccurate data are recurring problems in many CBM database. These problems can cause bias or lead to inaccurate analysis. A comparison between five methods of processing missing and inaccurate data is presented. The comparison is based on calculating the accuracy of diagnosis of machine's health when the algorithm called Logical Analysis of Data (LAD) is used. An application is presented when data is processed by these methods. The results are shown and discussed.