In program evaluation, measurement methods are best categorized into two broad groups: direct measures and indirect measures. Using both direct and indirect measures can provide a more holistic view of the impacts of a program.
1. Direct measures - Direct measures in education research and evaluation are actual products such as papers, projects, and exams. Direct measures are often used to deteremine the degree to which students learned the content.
2. Indirect measures - Indirect measures in education research and evaluation are not actual products but can be used to examine perceptions, attitudes, and opinions about a program.
There are four common types of data that are analyzed in educational research and evaluation. Depending on how the data is collected will determine whether each type should be considered to be a direct or indirect measure.
1. Observations - Observation data is a type of qualitative data collection methodology. Observation allows the researcher to systematically collect data as it occurs within a specific event or time frame. Observers need to be well trained to ensure that the results are reliable.
2. Artifacts - Artifact data is a product or document that is generated as a part of a course or program. For example, an artifact of a course could be the syllabus that is used, or samples of student work completed inside or outside of the classroom.
3. Historical or Institutional Records – Historical or institutional records include demographic and enrollment data that is often recorded when a course or program is being conducted. This information is not necessarily generated by anyone associated with the course, but offer opportunities to examine trends over time and can serve as a foundation for other research questions.
4. Self-report - Self-report data requires participants to provide their thoughts or opinions in response to a specific prompt. Self-report data can be collected via interview, survey, and focus groups. Though commonly used, scholarly study on whether self-report is reliable has provided mixed reviews. Individuals are not always able to accurately assess their own abilities, and responses can be influenced by how the data collection instrument has been constructed.
 Ross, J.A. (2006). The reliability, validity, and utility of self-assessment, Practical Assessment, Research and Evaluation, 11(10), 1-13.