Google Analytics: Different stats for date range vs single month?

[Bio-RadAbs]

I've been scratching my head, chin, and you name it over this one.

I have an advanced segment to remove bot traffic from my data. When I look at the Audience Overview data for a single month (let's say Aug). I am shown a session count.

No problems here, however If I set the date range to (January - August). The august monthly stats is incorrect, much lower. What this means is that, if I export a CSV report from Jan-Aug, the data is wrong compared to individually recording a month.

Anyone faced this? I've asked the question over at the Google Analytics technical section as well, but no answer

P.S I even used the 'control the number of sessions used to calculate this report' tool but no luck.

[Bio-RadAbs]

Google's pre-built filters are working fine for me (i.e. all sessions) and it's my bot filter when I view via a date range vs month only that is causing the confusion.

I got an answer from the google analytics technical page. There is a setting to exclude bot traffic, therefore avoiding the need to build custom segments.

You can do this for each profile so I've turned it on to test, let's see how my results turn out. If it removes the bot traffic automatically, then the date range wouldn't change. Here's how to do it:

Admin >> View Settings >> Bot Filtering (Click the Check Box) then the Save button. Done... no need for a dedicated segment.

[RG_SEO]

I agree with Bendall that sampling is what is most likely causing your problem here. You may find this post useful: https://support.google.com/analytics/answer/1042498?hl=en-GB

I suspect that the reason that your sampled total closely matches the total of individually downloaded monthly data is because sampled data is Google's 'best guess' when the data in the date range becomes too large. This best guess is based on sound statistics, but ultimately there will be some variances. I've found these variances get bigger the larger your site and the larger your date range. Google do this to reduce load on their servers as crunching the numbers for large data sets can be very resource intense. You COULD upgrade to Google Analytics Premium which gives you un-sampled data as standard, but this is very expensive and only really suitably for large organisations.

There is no easy way round this I'm afraid. I'd suggest that you think about what level of data you are comfortably using - sampled data can still give you valuable insights / trends. Some are comfortable with using sampled data (I prefer now too). I believe there are some tools that allow you to download un-sampled data from Google Analytics via their API but I have not tried these.

[Bio-RadAbs]

I didn't know about this. I always thought the a data range would show the same data as the small range.

Strange thing is, If I note down each month's sessions individually and then add them up, they closely match the total session count my data range gives. Its just that my month data within the range that is wrong.

[Bendall]

Are you sure the data in the larger date range is not being "Sampled". Always more dependable to add up smaller date ranges from my experience in the free version of GA, as if their is too much data to crunch it will take a sample and upscale it.

Regards

Ben