ABSTRACT

The objective of this chapter is to present the rationale for data preparation and practical guidance for conducting the procedures in applied research. It is argued that the scope of data preparation is far greater than the application of now classic diagnostic procedures such as those outlined for the regression family. Data preparation presents an opportunity to assess the integrity of the dataset and to make any necessary consequent adjustments to either the data or the analytic plan. A series of questions are outlined that provoke scrutiny of the data, followed by a set of pre-analysis procedures that help to identify any early issues. Next, the classic regression diagnostics are presented as an example of the assessment of model adequacy in the analysis stage. Finally, a brief guide is presented to the logic and creation of dummy variables, which are important tools to deal with potentially problematic situations, both expected and novel.