Summary

This chapter has gone through techniques for data handling. Prior to data analysis, it is important to get the data into a consistently structured format, which string processing and pattern matching are helpful in doing. We have also gone through some basic memory management considerations. Finally, we discussed how to handle missing data using deletion, and two imputation approaches. The techniques of this chapter yield no new scientific insights or information about relationships in the data, yet they are often crucial preliminary steps prior to descriptive or inferential analyses. For large-scale projects, additional technologies designed just for data management, such as database platforms, will be important adjuncts to R by itself.