There has been a recent change in the way Google Analytics calculates sessions:http://analytics.blogspot.com/2011/08/update-to-sessions-in-google-analytics.html .
Some of our clients who monitor their sites with GA have seen large changes to their metrics, and inevitably questions regarding the perceived change in the performance of our marketing campaigns, land on our desks.
The size of the effect depends on the typical user behaviour on the site, and the type of campaign strategy. We see the greatest change in sites where there is short interaction time and low page-depth interaction. The effects are also greater where the campaign is deep-linked to the site. This arises because the person searching is sent immediately to the most relevant page so his interaction in terms of navigation and time is lower.
We have observed some secondary effects of the change which affect the actual value of parameters, not just the average value per visit, etc. As an example, consider the time-on-site metric for sites where a significant number of interactions are one page deep
A typical scenario could be the following: a person comes to page A on the site after searching for the term “Dog”; he then goes back to the search engine and searches for the term “Cat” and lands on page B sixty seconds later and then leaves the site. Previously this would be considered one session (as the browser was not closed) and time-on-page A would be sixty seconds (page B would be zero seconds). With the new method of counting sessions, a new session starts as the person comes back on the search term “Cat” and you end up with two visits,both with zero time-on-site. When you add all the time-on-site metrics and divide by visit numbers, not only do you get a smaller number (because of the larger number of sessions), but the actual total will be smaller as well. To illustrate, in one site we observed a 25% increase in session count, but a 50% drop in time-per-session. A similar effect can be seen if you use goal values to monitor some events. Only one goal is recorded per session, so if you have goals which can be achieved more than once in a session you might find that the actual number of reported goal completions has increased – as you now have more sessions.