Re: ecommerce Conversion Rate Analysis
- From: "Steve" <tilston@xxxxxxxxxxx>
- Date: 24 Aug 2005 09:53:08 -0700
Thanks for you reply Robert, I'll definitely check out that book.
Unfortunately, looking at my data, i'm not sure I have enough buyers to
be sure of statisitcal significance (although I have thousands of
visitors). Basically my data for a couple of months before the change
was an average daily conversion rate of 2.5% with a standard deviation
of 0.6%. On a chart it looks really random but very rarely above 3.5%
or below 2%. Since the change the conversion has averaged 2.7% for a
couple of weeks with a similar variance, but it's difficult to know if
it's a real effect, as I can find short periods prior to the change
with an average conversion that high.
One way I found to test significance was the chi squard test, where I'd
divide my visitors into a 2x2 matrix of buyers vs. non-buyers and
before and after the change. Does anyone know if this is a valid use of
this test? And thanks again for your help Robert
.
- References:
- ecommerce Conversion Rate Analysis
- From: Steve
- Re: ecommerce Conversion Rate Analysis
- From: Robert Dodier
- ecommerce Conversion Rate Analysis
- Prev by Date: Re: Linear Model with Missing Data Values
- Next by Date: Re: Software suggestions
- Previous by thread: Re: ecommerce Conversion Rate Analysis
- Next by thread: Confidence Band question
- Index(es):
Relevant Pages
|
