Information Technology Reference
In-Depth Information
331
Pages
Figure 13.5 The number of visits per page, example 1
this is the traditional long tail, telling us that a few pages generated a lot of
traffic but the same amount of traffic is generated by a large pool of lesser-visited
pages. without going into greater detail, it is fair to assume (just by looking at it) that
a standard long tail distribution like this is inversely proportional and thus follows the
power law.
then, we should be able to plot the same information on a double-logarithmic
chart. if a straight line appears, it confirms that we are talking about the traditional
long tail.
so we need to add two more steps to our list:
3.
mark your y-axis, click Format axis, choose logarithmic as the scale, and then
click apply to Chart.
4.
mark your x-axis, click Format axis, choose logarithmic as the scale, and then
click apply to Chart.
Using the same dataset as Figure 13.5, we get a changed chart, as shown in
Figure 13.6.
i applied a straight line through the graph. we can thus conclude that we have a
perfect long tail distribution.
now let's try to look at a less optimal dataset that does not necessarily create
a straight line. i did a similar export and linear graph and ended up with the chart
shown in Figure 13.7.
Search WWH ::




Custom Search