LAUSR

As an academic researcher, I found the relative lack of references a bit frustrating but this is perhaps a minor quibble. That said, many interesting and important data analysis issues are discussed, such as descriptive analysis as the necessary start of the process, effect sizes over p-values, and the importance of theory, and of theory-building in quantitative research. There are so many things that could be covered in such a book, that it is unsurprising that some things are left untouched – for example, it would have been interesting to see a consideration of the sample versus population arguments that some argue render statistical hypothesis testing irrelevant when using administrative datasets where the whole population has been “sampled” (Gibbs, Shafer, and Miles 2017). Another issue that could have been considered would be the potential contribution of mixed methods to a quantitative secondary data analysis, and the issues that might then arise. This would certainly be a useful book to support an introductory undergraduate quantitative analysis course for any social science discipline, including in education, even though the examples are not generally focussed on education-specific datasets. The book dips into a number of important issues that could be used to open up meaningful discussion of key issues in quantitative data analysis and to help teach the strengths and pitfalls of using secondary data sets in research. Its unique approach, focussing on secondary data and related issues, certainly complements other well-known, perhaps more methods-focussed, SPSS-based books such as those of Andy Field (2013) and Julie Pallant (2010).