ABSTRACT
Data science requires metrics. But how does a researcher measure constructs such as delight, immersion, or intention to use? It's best to develop a suitable measure, rather than to just throw something together or use an inappropriate scale. This course presents seven simplified steps for developing a valid and reliable measure. The new scale can then be used to quantify and explain user behavior, make decisions and predictions, and build models. This half-day class is intended for anyone who desires a rapid but thorough overview of how to develop a measure, and it requires a modest understanding of statistics.
- Instructor information is available at norenekelly.com and WEARscale.com. This process is largely based on Scale Development: Theory and Applications by Robert F. DeVellis (2017).Google Scholar
Index Terms
- How Do We Measure That?!: Quick Scale Development
Recommendations
Measuring commitment to self-tracking: development of the C2ST scale
AbstractSelf-tracking technologies bring a new set of experiences into our lives. Through sensors and ubiquitous measurements of bodily performance, a new form of automation experience shapes our understanding of our body and our behavior. While for many ...
Cloud Computing Adoption: Scale Development, Measurement and Validation
The purpose of this article is to develop a cloud computing adoption scale for Indian manufacturing, service, and process Industries. The scale development procedure has been followed from the previous studies and is refined further for clear ...
Learning similarity measures from data
AbstractDefining similarity measures is a requirement for some machine learning methods. One such method is case-based reasoning (CBR) where the similarity measure is used to retrieve the stored case or a set of cases most similar to the query case. ...
Comments