Expand my Community achievements bar.

Join us for the next Community Q&A Coffee Break on Tuesday April 23, 2024 with Eric Matisoff, Principal Evangelist, Analytics & Data Science, who will join us to discuss all the big news and announcements from Summit 2024!
SOLVED

Sum Rev Squared

Avatar

Level 3

After we create this calculated metric, how should we use this to analyse the numbers by variant in Adobe Target report?

1 Accepted Solution

Avatar

Correct answer by
Community Advisor

Thanks for the clarification. This is my first time hearing of "Sum Rev Squared". And I've never used this before with calculating lifts and confidences with Target experiments.

The method described at https://experienceleaguecommunities.adobe.com/t5/adobe-analytics-questions/sum-of-revenue-squared/td... uses the Column Sum function. This sums up the values in a column. https://experienceleague.adobe.com/docs/analytics/components/calculated-metrics/calcmetrics-referenc...

With that in mind, I suppose you could break down your Target Experience dimension by another dimension, e.g. Day, and apply the calculated metric against that to get a sum per Target Experience value. Note: I don't know if that is really the correct way to perform a proper lift/confidence calculation. I'm just suggesting it based on my understanding of the Column Sum function.

View solution in original post

3 Replies

Avatar

Community Advisor

Did you mean the Coefficient of Determination "R squared"? https://en.wikipedia.org/wiki/Coefficient_of_determination Instead of "Sum Rev Squared".

Avatar

Level 3

Nope, that is completely different from what I have asked. 

I am trying to use Adobe Sheet for analyzing standard deviations of target activities, since that is not available out of the box in Adobe Target. I used this https://experienceleaguecommunities.adobe.com/t5/adobe-analytics-questions/sum-of-revenue-squared/td... to create this metric. Now when I use it in A4T reports, there is no way I can break this metric down by control and treatments groups. What is the workaround to see the numbers of this metric for both control and treatment groups? Once I have these numbers, I can use Adobe sheet to calculate standard deviations by using this metric.

Avatar

Correct answer by
Community Advisor

Thanks for the clarification. This is my first time hearing of "Sum Rev Squared". And I've never used this before with calculating lifts and confidences with Target experiments.

The method described at https://experienceleaguecommunities.adobe.com/t5/adobe-analytics-questions/sum-of-revenue-squared/td... uses the Column Sum function. This sums up the values in a column. https://experienceleague.adobe.com/docs/analytics/components/calculated-metrics/calcmetrics-referenc...

With that in mind, I suppose you could break down your Target Experience dimension by another dimension, e.g. Day, and apply the calculated metric against that to get a sum per Target Experience value. Note: I don't know if that is really the correct way to perform a proper lift/confidence calculation. I'm just suggesting it based on my understanding of the Column Sum function.