The data for learning analytics can come from many different sources and can be classified in various ways. One of the primary types is the demographic data (type 1 in Figure 8.1) the institution holds about students, such as their date of birth, sex, socio-economic status or ethnicity. Some of this may be ‘sensitive’ data (type 1a), which in many countries has its own legal definition and needs to be handled especially carefully. Much of it may be irrelevant for learning analytics; however, data such as a student’s ethnic group or disability can turn out to be relevant in predicting their academic performance. Examples of types of data used for learning analytics. https://s3-euw1-ap-pe-df-pch-content-public-u.s3.eu-west-1.amazonaws.com/9781315679563/218ef8b4-3080-49d2-bec3-85689bc3b8b0/content/fig8_1.jpg" xmlns:xlink="https://www.w3.org/1999/xlink"/>