Working with Data
摘要
Data are the raw material of all analysis: they can be structured or unstructured, depending on how they are presented. Structured data are tables, such as normal spreadsheets, in which any row is an istance and any column is a variable (actually, there are two main systems to represent structured datastructured data in a spreadsheet: the wide format and the long format, but this is a topic we will not go into here: it is enough for us to know that many software for statistical data analysis are capable of reshaping data from one format to another), whereas unstructured data are information stored as text, images, sounds, vocal records, and other data that cannot be stored in a tabular form.