5.4. Removing and Modifying Data for Individual Tasks

It's much more common for a participant to disengage from just a few tasks than the entire study. Disengagement usually happens in longer online usability studies, perhaps more than 15 or 20 minutes long. Participants might get bored or be in a hurry to finish. Whatever the reason, we recommend that you take a close look at task-level data. Bottom line—don't throw out the baby with the bath water.

5.4.1. Outliers

Outliers are extreme points in data and are the result of atypical behavior. Outliers need to be examined before any conclusions about data can be made. The most common type of outlier in an online usability study is task time data. We typically remove task time data when a participant ...

Get Beyond the Usability Lab now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.