since ‎12-05-2017
‎10-12-2019
csanderson99
Level 1
Why does Target/analytics give 3 different values for test results and which one is correct?
Avatar

csanderson99

csanderson99
- Adobe Target
This is a problem I'm noticing more and more within Target and I see no literature on dealing with it. When I am looking at test results in Target, in table form I get the following results.Note that the winning lift is very nearly (but not quite) 4% and the confidence is at 97%.When I look at the exact same data in the form of average lift over time (where the final day should match exactly with the data above) I get this.Note that now the winning test is at 3.17% lift, almost a 20% decrease in...

Views

1.3K

Likes

0

Replies

1
Re: User gets a different experience every time they go to a new page
Avatar

csanderson99

csanderson99
- Adobe Target
Waiting for approval on this, will get back to you.

Views

6.9K

Likes

0

Replies

0
Re: User gets a different experience every time they go to a new page
Avatar

csanderson99

csanderson99
- Adobe Target
A quick follow up, I've been doing some QA on this and it turns out that any test created in the WYSIWYG editor is reproduced fine, but for this particular test in the form based creator it's randomly showing up when we refresh the page. Would it help if someone could take a look at the code and potentially identify the issue?

Views

6.9K

Likes

0

Replies

2
Re: User gets a different experience every time they go to a new page
Avatar

csanderson99

csanderson99
- Adobe Target
Hi, Thanks for the answer but this doesn't really help me much. As I explained, we are not changing devices, clearing cookies, or logging in from a new browse. We are entering the site on one browser, and being fed a different experience every time we click onto a different page that contains the experience (which is all pages because we are running a global navigation campaign). Is there any other reason the PCID could be changing in this situation?

Views

6.9K

Likes

0

Replies

0
User gets a different experience every time they go to a new page
Avatar

csanderson99

csanderson99
- Adobe Target
Hello, I have a problem. We're running some tests in the staging environment of our website, and every time I clear cookies to make sure the variants are appearing, I get a totally random experience every page I visit. The location of the experiment is any page containing a certain piece of a URL. To illustrate the problem better: We are running a navigation test across the whole site with 2 variants.When I visit the homepage I get variant 1. When I visit an about us page I get variant 2. When I...

Views

7.3K

Likes

0

Replies

5
Re: How to export user level data post test?
Avatar

csanderson99

csanderson99
- Adobe Target
Hi Parit, Sure. The use case is that I want to have a better calculation of RPV than what I can get from a t-test. To do that I need to run a export on all user level data with each corresponding revenue amount. Once I get the user level data I can run a Mann Whitney U Test. But to do that I'd need literally every user revenue value, individually for each variant.

Views

1.0K

Likes

0

Replies

0
How to export user level data post test?
Avatar

csanderson99

csanderson99
- Adobe Target
Tried doing a search for this and couldn't find anything, though I'm sure it's possible. Can someone help me out please? I'm not super familiar with target or adobe analytics so if it requires linking a4t and exporting from analytics I'd like to have some resource for that as well.

Views

3.8K

Likes

0

Replies

5
Re: Does Target account for multiple family errors (Stats) ?
Avatar

csanderson99

csanderson99
- Adobe Target
Thanks Jason, so it isn't automatically calculated. That's not an issue, just didn't want to create more work for myself. Do you know what type of Bonferroni correction the calculator uses?

Views

889

Likes

0

Replies

0
Re: Introduce Yourself!
Avatar

csanderson99

csanderson99
- Adobe Target
Hello everyone, My name is Chad Sanderson. A formula Testing consultant and now Head of the Experience Optimization program for Subway Restaurants based in Connecticut. I am very interested in getting to know the statistics behind Target (specifically automated personalization and MVT) Would it be best to post on this board or is there a contact I could reach out to with questions?Thanks

Views

9.7K

Like

1

Replies

1
Does Target account for multiple family errors (Stats) ?
Avatar

csanderson99

csanderson99
- Adobe Target
Basically what the title says- a statistics question. For everyone else interested. Multiple family errors (alpha inflation) happens when testing more than one variant to 95% confidence (p = .05). While each test individually has a 5% chance of Type I error, as a family grouping the error rate increased with more variants. (Formula is: 1-(1-alpha)^n where alpha is .05 and n is the number of tests). So if we are testing 8 variations (+ 1 default), the formula would be: 1-(1-.05)^8 = .34 or a 34% ...

Views

1.5K

Likes

0

Replies

2
Creating a Holdback set within Target, is it possible?
Avatar

csanderson99

csanderson99
- Adobe Target
One of the best ways to compare long term effects of tests over time is to create a holdback set, a percentage of users that always sees the original default content no matter what has been hardcoded on the website. Is there a way to implement a long-term "control" variant like this, that can be excluded by all future tests moving forward?

Views

1.2K

Likes

0

Replies

1
Analytics for Target Reporting Suite Error?
Avatar

csanderson99

csanderson99
- Adobe Target
Hi all, I'm an administrator within both Target and Analytics and Analytics has been successfully linked to Target. When I try to link a campaign to Analytics I get the error below. This issue is unique to me on our team. Two other team members can see and select all reporting suites. I've been given the exact same rights (if not more) than these users, yet I still have no access. Can someone help me figure out why this is happening?

Views

1.3K

Likes

0

Replies

1
Likes from