Data and Analytics for Instructional Designers by Megan Torrance

Author:Megan Torrance [Torrance, Megan]
Language: eng
Format: epub
ISBN: 9781953946454
Publisher: Association for Talent Development
Published: 2023-04-15T00:00:00+00:00

Figure 8-2. The Scientific Method Applied to Learning Analytics

Exploratory Analysis

While hypothesis testing is a rigorous approach to analytics, I should point out that not all analysis needs to be this hard-edged and focused. In fact, transforming the questions posed by the business and your L&D team into discrete, testable hypotheses may require some initial exploratory analysis.

In exploratory data analysis, you will collect a lot of data and dig through it looking for patterns or a lack of perceivable patterns. This is like walking into a retail clothing store and not looking for anything particular; you’re just hoping that a sweater catches your eye and you’ll pick it up, try it on, and see if it works for you. In this metaphor, the clothes are the data sets and your casual search is the analysis.

Of course, it’s entirely likely that you had a general idea of the kind of thing you were looking for when you went into the store (otherwise you probably wouldn’t have gone into the store). This metaphor continues to hold true for that type of exploratory data analysis. For example, when I go into a clothing store, I am only looking for women’s clothing that would fit me and generally for the season that I happen to be in. I know what clothes I already have and therefore don’t need to buy, so I kind of have a sense for what I’m looking for. At the same time, I’m open to new things I might stumble upon as I shop. The exploratory data analysis is an opportunity to help find additional questions and create different hypotheses.

One of our nonprofit clients was open to us pursuing an analytics endeavor for their learning offerings, but didn’t really know what to ask. They were open to whatever insights we might find and how they could help them create a strategy for future course development, fundraise more effectively with donors, or improve the overall experience for the learners. While we didn’t have any concrete questions, we did have a good sense for their data because we support their LMS and their course offerings. We had enrollment dates, user group information, some very limited user data, SCORM data from their e-learning programs, and very basic video consumption data from a series of videos they’d released last year.

Knowing what data was available to us helped our team come up with an initial list of questions that we thought would be useful.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.