#19316
Most 'usability' practitioners quite rightly put great emphasis on the ease with which sample users can complete pre-selected tasks. After all, it makes sense to ensure that common tasks, identified after research into user needs, should be completed as efficiently as possible. It is when this 'efficiency' is measured that problems can begin.
Farrell, Tom. Frontend Infocentre (2001). Articles>Usability>Statistics
#23877
Results of the Usability SIG Member Survey
The first Usability SIG survey was conducted in 1996. I thought that 2003 was an ideal opportunity to survey our members again. Due to cost constraints, the survey was only available for 30 days. Of the 1600 members, 85 responded to the survey. That might be considered a low response, but statistics show that a response rate of over 5% is considered good. Yes, we read every reply. The Usability SIG team reviewed the results and have a strategy to make improvements. The following are samples of the responses received.
Dick, David J. Usability Interface (2003). Articles>Usability>Statistics>STC
#21118
Statistically Analyzing Success Rates in Web Usability Testing: The Cochran's Q Test
The Cochran's Q Test can be used to statistically analyze success rate data. It can be used even when only a small number of users are tested. This provides some indication that a vast amount of usability data can, and should be statistically analyzed
Griffith, Jamie. WebWord (2001). Articles>Web Design>Statistics>Usability
#22381
Thirty user performance metrics for informal usability evaluations.
Bohmann, Kristoffer. Bohmann Usability (2000). Articles>Usability>Statistics
#27791
Why a Completion Rate is Better with a Confidence Interval
Confidence intervals have been lauded by the APA (American Psychological Association) as the preferred technique when presenting data for any size sample, and this has been echoed in the usability literature as well.
Sauro, Jeff. Usability Professionals Association (2006). Articles>Usability>Statistics>Methods
