The Usability Log Analyzer generates diagnostic reports by
analysis of logs of user activity. The analysis is based on a three layer model
-
The lowest layer - Stochastic Processes
The mathematical foundation of the usability analyzer is a model of stochastic
processes, in which the states are the page identifiers (in records of server
log files these are the client URL). State attributes include page properties
derived from the log files, such as average time delay before or after the
transitions, rates of exit and backward navigation, etc.
- The middle layer - Human Factors
The middle layer of the usability analyzer is a model of human browsing, assigning navigational
attributes to page visits and transitions. The navigational attributes include
characteristics of the page properties in task-driven navigation compared to
exploratory navigation. The model assumes that certain navigational attributes
are typical to problematic pages and transitions, and are unlikely for
design that enables seamless
navigation.
- The top layer - Statistical Decision
The top layer of the usability analyzer is a statistical decision model, used for concluding that
particular navigational attributes are statistically significant. Statistical
significance is determined by computing the probability of error in
rejecting the null hypothesis, which is that page properties of task-driven
navigation are the same as those of exploratory navigation.
|
The Model Underlying the Usability Log Analyzer
Statistical Decision
|
Human
Factors
|
Stochastic Processes
|
|
To
get a free usage statistics report -
To order a full usage report -
Did you not find the information you need?
Do you want to comment on the website content? Please, send your question or comment to
Did you experience any problems with this
website? obsolete or broken links? inconvenient design? design mistakes? We would appreciate your comments. Please, send
them to