I agree what theespionage is saying,but at the same time when ioi saids someone's opinion is stupid,then that kind of doesn't help matters any. I love and respect what ioi does on this site,but he's not the best when it comes to the PR stuff. He does kind of seem 2 get annoyed easily,when someone challenges this site. I believe you can challenge this site and still be respectful about it. So,I can see were both sides are coming from. I've never been good at math and numbers in general,so I think getting these numbers is a massive and complicated process,which I could and never would do. That's the main reason I respect and love this site.

Tell me what survey group you use for the polls. Id like to know. I know Ive done multiple surveys for NPD. Also, what survey group did you use to gather information when you were still in school before you had the idea to run a website because websites didnt exist yet... you know... the numbers you have published next to everything else.

But you have them and next to the data of games you publish. People arent smart enough to realize things like that. And you dont see how its misleading that you have historical data that you didnt estimate yourself next to the other games you do?

If the error was just about 5%, between VG Chartz numbers and reality, each game of the top 10 couldn't move more than 2 places. That's already a ranking I can look at without thinking "this could be totally different" (as the one we have now that the 1st could very well be 9th and the 9th could very well be 1st). When I say "could very well be", I'm estimating such scenario and similar ones to account for 30% of the cases. Moreover, if the error was just about 5%, I could look at a recent number without thinking "this could be half...or 3 times more than that" (and in this case I'm never out of the 95% confidence range, so I'm not considering extreme cases, as you tried to make it seem). Instead, it would be "this could be a little less (95%) or a little more (105%)". See the difference? It's a hell of a difference.

With this I don't want to criticize the numbers or the methodology used. I think VG Chartz does a good and unique job and I understand that it comes to a point where shortening the confidence ranges can only be achieved by using bigger samples and ultimately this is a Accuracy-vs-Investment trade-off that needs to be balanced. The problem is not there and I can praise VG Chartz's methods and positioning as many times as needed for you to understand that in most of the cases I'm on VG Chartz's side when the rest of the videogaming industry despises it. The problem is in communication, since VG Chartz misleads newcomers (including relevant videogaming stakeholders). Some will dig in until they find how VG Chartz really works and what can they expect from the numbers they see, others won't. VG Chartz still has to learn how to pass a complex message in a simple and accessible way, and there are various alternatives for doing so. Most of them could even be subliminar messages (including the way the numbers are presented) while others could be a simple tutorial eventually with a FAQ linked to a big area at the head of every page saying "Where the numbers come from" (rather than a tiny link at the footer saying "About Us" and that presents VG Chartz's history...somewhere in the middle should be a little and incomplete explanation about the numbers).

What does bother me? This:

1 - People's stubbornness to acknowledge VG Chartz's limitations. What it really does, what it doesn't. What can be actually expect from the numbers, what we should be careful at.

2 - The way VG Chartz presents its results and the lack of willingness to make all the (or at least the major) videogaming stakeholders to understand VG Chartz's value-added contributions towards the industry.

3 - The combination of point 1 and 2 generate rivalry between the sites (like it's happening between IGN and VG Chartz) both at administration and community levels, when it should be the opposite (sites should help each other). After all, we are on the internet and, as the very name tells, it's a net, not a place full of fortifications.

4 - People willing to give insights about VG Chartz being mistreated by the owner of the site, and that reaction being further supported by other users. I don't care if there was incorrect behaviour from the other side in the first place. Flamebait shouldn't be fought with flamebait and the site admin should lead by example.

I fully understood. I know that there are several levels and ranges of confidence and that most of the values will fall within a shorter range than the 50%-150% I was talking about. I'm sorry if my example wasn't the best to illustrate what I was trying to say. I was supposing to work with 95% confidence (most of the companies from the different industries work with 95% or 99%, no one finds 85% or 70% reasonable) in order to understand what could I expect from the weekly numbers I see. My conclusion was: I can expect very little and the way the numbers are presented doesn't tell me that at all. My suggestion is: create a radio button at the top in which evey user can sellect the confidence he/she wants (95%, 85%, 70%) and display the numbers as rounded intervals. For example, a game like COD Ghosts for X360, which sold 550854, would appear like this "275k - 826k" for the 95% option, "367k - 734k" for the 85% option and "459k - 643k" for the 70% option. This way it would be clear for anyone how reliable the ranking actually is.

Thank you for the tip but the range of perspectives from you and other users here in this thread is enough for me to have a pretty decent idea of what the numbers represent. I'm ok with what I get from this site and the information I have now to really understand that. I just think you could improve the way VG Chartz communicates and the way you interact with your own userbase (don't forget they are your ultimate clients).

http://www.barb.co.uk/resources/reference-documents/how-we-do-what-we-do

This is a better page to include - an actual, detailed explanation for how the data is gathered.

And again, you didn't respond to me directly, so I'll say it again - You cannot take such a tiny portion of a market (if you're even getting any data for a particular title during that week, which I highly doubt you can receive for every game out there) and balloon it out to a precise and exact number to the nearest unit and rank them.  I don't care what page is added, it's impossible and the final figures appear misleading because of it.  It's a matter of integrity and professionalism.  It's one thing if you're covering the majority of a particular market and you can say with reasonable confidence one game sold X amount over the other, but that's not the case here. 

Out of curiosity, do you perhaps include Standard Deviation in your VGChartzPro sales data?

If you were going to provide a range, one standard deviation would be the natural choice of range to provide, in my opinion, but since most regular VGChartz users probably wouldn't have studied statistics to any great extent, I'd imagine it would only cause confusion for many... yet I could see it being useful information to those that are paying for the numbers.

I'm guessing you haven't studied statistics.

Sampling works exactly as ioi has described, and the resulting numbers are typically scaled up directly (plus adjustments for known biases), rather than rounding roughly. Why? Because every time you round, you lose further information. And then when you sum over a lot of numbers, the error gets worse. Sampling error is bad enough as it is, you don't want to make it worse with rounding.

Sampling error itself follows a fairly simple rule. To work out the margin of error for a 95% confidence interval, for a large population, you can approximate it using 0.98/sqrt(n), where n is the number of samples. So, for that BARB thing, a sample of 11,000 will provide a margin of error of 0.93%. But they'll still note that Strictly Come Dancing got 11.07 million, despite the 0.07 being within the margin of error. And they'll still list The One Show on Tuesday having higher ratings than The One Show on Monday despite the difference being 0.01 million, well below the margin of error.

The reason is that people like things ranked. It's not the purpose of the site to rank them, but to provide the numbers. The ranking is for regular users, and makes for a bit more enjoyment from debating the numbers.

post removed by user.