Quote:
Originally Posted by ravo
|
Unless I miss something he is off on one point though.
Quote:
|
If you send 10,000 visitors to a sponsor and get 9 signups, then 68% of the time when you send 10,000 visitors, you expect to attain between 6 and 12 signups (6 +/- 3) and 95% of the time you expect to attain between 3 and 15 signups. The interesting point of all this is that the error depends only on the number of signups and not the number of visitors. Most people think, ok, I'll send a certain number of visitors to a sponsor and see how many signups I get. What you should be doing instead is saying ok, I'll send a certain number of signups to a sponsor to test them.
|
With the way he is using it though he is using "how many sales in 10,000 uniques" so that IS taking into account the number of visitors. It's just that he is doing it outside of his Poisson equation beforehand as part of his variable inputs. Still it is subject to it.
IOW his value for 'm' or 'x' is actually a signup rate and not just the number of signups. It's signups per 10,000 visitors in that specific case.
You still have to take into account the number of visitors for obvious reasons such as the possibility that tracking isn't working or the sponsor is shaving. There is also opportunity cost in having a given link up and sending traffic. If the one sponsor isn't selling you can use another. It would be folly to send 100 million visitors and to keep sending because "you are trying to get 3 signups for statistical comparison purposes".
