Lying with WordPress statistics

I must admit that I repeatedly feel flattered by the number of page-views on my blog as shown by the WordPress statistics plugin. However, despite the nice graphical representation, they are a little too flattering for the humble number of page-views my blog attracts. A traditional line-graph consists of two axes. Traditionally, these are referred to as the x-axis, and the y-axis. To say it bluntly: the wordpress statistics plug-in messes up on account of both axes.
 

Problems with the Y-axis

Regarding the y-axis, representing the number of page-views on a specific day, the problem lies with the numeric limits of the axis. In other words: in every representation the minimum and maximum value on the y-axis differs, which is especially problematic regarding the minimum value of the axis. When I try to discern a trend in the humble number of page-views on my blog, I’m often mislead due to this problem.

Let’s take a look. Today, I saw the graph represented below on my WordPress Dashboard. This graph clearly shows an increase in the number of page-views since June 5th. At least, so it appears. When we take a closer look at the y-axis, we see that it starts at 10, instead of 0. Is that a big deal? Yes it is. This means that the graph only shows 80% of the total reach of the graph.

About ten minutes later a new day started which resulted in a totally different graph, as shown below. Still, we see an increase in the absolute number of page-views, but now the slope of the line seems to be less steep. Instead of a clear increase, we now see more clearly a relatively stable number of page-views of about 30, with an initial dip and a peak at the end of the selected time-period. Reason for this is the completely different values used to represent the y-axis. This results in a graph which is a lot less optimistic for my blog.

Problems with the X–axis

Regarding the x-axis, representing the dates on which the page-views were registered, the problem lies with the absence of dates on which no page-views were registered at all. This seems to be an even more serious problem. Again, I’ve added the graph created by WordPress statistics on one of my blog-posts. It shows a recognizable pattern: the most page-views on the day it was published and after that a steady decline. However, a superficial review of this graph would lead to the conclusion that readers have found this blog-post once or twice a day after that.

 

But, is that a valid conclusion? No it is not. A more detailed view of the graph shows that there have been many days that no-one at all viewed this post. Below, I’ve printed a bar-chart that also shows the days with 0 page-views. Again, it shows an image a lot less optimistic regarding my blog.

 

How bad is it and can it be solved?

Is this all that bad? Well, it gives the users of WordPress a positive feeling about themselves. But, for those who want a realistic overview of the success of their blog, the image given by these stats is not all that helpful. The more page-views a blog has, the worse this problem becomes: the plugin adjust the y-axis to show the absolute variation in number of page-views as large as possible, thereby overestimating the relative differences. The problem with the x-axis is highly problematic for the posts that are rarely visited.

Should this be adjusted in a next version of the plugin? Well, that’s a point for discussion. I can image a few people disappointed when their optimistic images turn more realistic. Nevertheless, I would suggest that the folks at WordPress at least would add the possibility for users to manually define the limits of the axes. Or, at the least, allow users to select the visualization of days that no page-views were registered on the x-axis and to have the y-axis start at zero.

Latest Comments

  1. Jonathan Davis says:

    I completely agree. Sometimes the bottom value of my y-axis is at 0 (after the day has just started) and the graph gives a good representation of what my traffic looks like. Later, it will be at some other high number and will give a graph that’s hard to interpret. I was searching for a way to manually define the limits, and I haven’t found one. Let me know if you’ve figured out a way… good post.

Leave a Reply