Press What’s the Difference between Attribution vs Incrementality?
As marketers, we use the word attribution in many ways. Attribution quite simply is applying appropriate, or earned credit to the marketing touch-point that led to a conversion. Typically, attribution is attempted through one or more methods such as first-touch, last-touch, and multi-touch attribution (MTA).
Incrementality measurement solves for the attribution problem, however the methodology goes about the task in a very different way from MTA. To measure incrementality, audiences are randomly segmented into test and control cohorts. The difference in conversion rates between the two cohorts effectively gives us incrementality and an accurate read on the marginal incremental contribution of that media channel.
Incrementality in marketing is especially needed for channels where ad impressions are difficult to map and measure such as walled garden social channels including Facebook, Snap and Pinterest, or even TV and direct mail. For most channels or platforms, MTA cannot measure views or impressions, so you’re essentially just measuring clicks. Incrementality measurement accounts for the impressions and clicks within each of the platforms under test and therefore gives marketers a more accurate view of the true contribution of their media across their entire portfolio.
Want to learn more about incrementality measurement? Read the Incrementality Measurement Guide for DTC Marketers.
Incrementality measurement solves for the attribution problem statement, however the methodology goes about the task in a very different way than MTA.
As marketers, we use the word attribution in many ways. Attribution quite simply is applying appropriate, or earned credit to the marketing touch-point that led to a conversion. Typically, attribution is attempted through one or more methods such as first-touch, last-touch, and multi-touch attribution (MTA).
Incrementality measurement solves for the attribution problem, however the methodology goes about the task in a very different way from MTA. To measure incrementality, audiences are randomly segmented into test and control cohorts. The difference in conversion rates between the two cohorts effectively gives us incrementality and an accurate read on the marginal incremental contribution of that media channel.
Incrementality in marketing is especially needed for channels where ad impressions are difficult to map and measure such as walled garden social channels including Facebook, Snap and Pinterest, or even TV and direct mail. For most channels or platforms, MTA cannot measure views or impressions, so you’re essentially just measuring clicks. Incrementality measurement accounts for the impressions and clicks within each of the platforms under test and therefore gives marketers a more accurate view of the true contribution of their media across their entire portfolio.
Want to learn more about incrementality measurement? Read the Incrementality Measurement Guide for DTC Marketers.
Original Publisher
Incrementality measurement solves for the attribution problem statement, however the methodology goes about the task in a very different way than MTA.
Ready to see how trusted measurement can help your brand make smarter media decisions?
Press What is Incrementality Testing and How Do You Measure Incrementality?
What Is Incrementality Testing?
Media incrementality represents the true incremental contribution of a media channel, campaign, ad set, or tactic to business results.
For example, when a marketer runs an ad on Facebook, Facebook takes credit for 100% of the conversions that ad was in the path of (last-touch attribution). These results can be misleading because they include conversions that still would have happened without being exposed to the ad on Facebook. It is the additional (or incremental) conversions, beyond those that would have converted anyway, that represent the real contribution or impact of the ad. That’s incrementality – the conversions that were truly caused by the media in question.
Why should brands measure incrementality?
Because they don’t have access to all the data outside their own environment, every digital ad platform uses the same flawed last-touch attribution method. Reports provided by ad platforms will never match up with site-side analytics reports or what’s observed in a brand’s sales data. Taking platform reporting at face value is a risky practice that can lead to bad decisions and lost revenue.
Only incrementality can reveal which media investments contribute to business metrics and by how much. Measuring for incrementality identifies where to eliminate waste and surfaces opportunities to scale, expand and reallocate media spend for maximum growth.
As access to third-party data and user-level tracking end, the accuracy of platform reporting is eroding even further. Measurement that is independent of platform bias and future-proof against the whims of a constantly changing industry is critical for today’s marketers. Incrementality measurement can deliver where methods like last-touch and multi-touch attribution fail.
How Do You Calculate Incrementality?
Incrementality is most effectively measured through proven test and control experiment methodology. By withholding the ad or treatment being tested from a statistically significant segment of the intended audience (the control group) marketers can determine the percentage of the target audience that still converts when they are not exposed to the ad. Subtracting that percentage from total conversions by the exposed audience (the test group) results in the actual incremental contribution, or incrementality percentage, of the media in question.
Incrementality measurement can vary in complexity from a simple holdout test as described above to multivariate experiments so elaborate they require the expertise of a trained data scientist. But, when carefully designed and cleanly executed, controlled experiments can utilize data from an unlimited number of sources to reveal the incremental impact of just about anything marketers want to test – on any outcome that can be measured.
In general, the control group should represent a minimum of 10 percent of the total test and control reach. The test group will receive the ad; the control group will not receive the ad. There are multiple ways to build a control audience. Some examples are:
- Present a placebo ad or basic brand “anchor” ad to an exact replica or mirror audience of the exposed audience
- Suppress a subset of the target audience from the ad exposure
- Programmatic executions have counterfactual bid loss data for the target audience that did not win the media auction
The Incrementality Calculation Formula
In order to calculate incrementality, you calculate the conversion difference between the test group and the control group.
(Test Conversion Rate – Control Conversion Rate) / (Test Conversion Rate) = Incrementality
Incrementality Test Calculation Example
Your test group saw 1.5% conversion whereas your control group saw a 0.5% conversion. The control data suggests that, without any media exposure, you would have seen a 0.5% conversion. Keep in mind that conversion could mean leads, sales, profit or whatever metric that is important to your business.
So (1.5% – 0.5%) / 1.5% = 66.7% incrementality in conversions
What Channels Make Sense for Incrementality Testing?
Advertising that generates a lot of impressions but not immediate action like a click still has brand value that ultimately leads to conversions or sales. Channels such as online display, video/YouTube, Facebook, TV, and direct mail all provide impressions, but are not always measured at the click or direct response level. That’s where incrementality testing comes in.
You can read more about the following channels here:
- Measuring Incrementality on Display Advertising
- Measuring Incrementality on Facebook
- Measuring Incrementality on Direct Mail
- Measuring Incrementality on Catalog
Incrementality Testing with Measured
Using experiments to test the incremental contribution of media to your business is the best way to make informed marketing decisions that fuel growth.
Only Measured delivers ongoing, reliable insights based on scientifically sound experiment designs that incorporate your source of truth transaction data. Everything is automated – ingestion and management of data from hundreds of sources, experiment design and implementation, and continuous reporting for confident, agile decision-making.
Could your advertising deliver more business value?
Try the free incrementality calculator to reveal how much you could improve your CPO or ROAS by replacing last-click with incrementality measurement.
Incrementality testing, when executed properly, can account for the pixel related blindness that occurs when trying to use MTA to measure the effectiveness of Walled Garden media.
What Is Incrementality Testing?
Media incrementality represents the true incremental contribution of a media channel, campaign, ad set, or tactic to business results.
For example, when a marketer runs an ad on Facebook, Facebook takes credit for 100% of the conversions that ad was in the path of (last-touch attribution). These results can be misleading because they include conversions that still would have happened without being exposed to the ad on Facebook. It is the additional (or incremental) conversions, beyond those that would have converted anyway, that represent the real contribution or impact of the ad. That’s incrementality – the conversions that were truly caused by the media in question.
Why should brands measure incrementality?
Because they don’t have access to all the data outside their own environment, every digital ad platform uses the same flawed last-touch attribution method. Reports provided by ad platforms will never match up with site-side analytics reports or what’s observed in a brand’s sales data. Taking platform reporting at face value is a risky practice that can lead to bad decisions and lost revenue.
Only incrementality can reveal which media investments contribute to business metrics and by how much. Measuring for incrementality identifies where to eliminate waste and surfaces opportunities to scale, expand and reallocate media spend for maximum growth.
As access to third-party data and user-level tracking end, the accuracy of platform reporting is eroding even further. Measurement that is independent of platform bias and future-proof against the whims of a constantly changing industry is critical for today’s marketers. Incrementality measurement can deliver where methods like last-touch and multi-touch attribution fail.
How Do You Calculate Incrementality?
Incrementality is most effectively measured through proven test and control experiment methodology. By withholding the ad or treatment being tested from a statistically significant segment of the intended audience (the control group) marketers can determine the percentage of the target audience that still converts when they are not exposed to the ad. Subtracting that percentage from total conversions by the exposed audience (the test group) results in the actual incremental contribution, or incrementality percentage, of the media in question.
Incrementality measurement can vary in complexity from a simple holdout test as described above to multivariate experiments so elaborate they require the expertise of a trained data scientist. But, when carefully designed and cleanly executed, controlled experiments can utilize data from an unlimited number of sources to reveal the incremental impact of just about anything marketers want to test – on any outcome that can be measured.
In general, the control group should represent a minimum of 10 percent of the total test and control reach. The test group will receive the ad; the control group will not receive the ad. There are multiple ways to build a control audience. Some examples are:
- Present a placebo ad or basic brand “anchor” ad to an exact replica or mirror audience of the exposed audience
- Suppress a subset of the target audience from the ad exposure
- Programmatic executions have counterfactual bid loss data for the target audience that did not win the media auction
The Incrementality Calculation Formula
In order to calculate incrementality, you calculate the conversion difference between the test group and the control group.
(Test Conversion Rate – Control Conversion Rate) / (Test Conversion Rate) = Incrementality
Incrementality Test Calculation Example
Your test group saw 1.5% conversion whereas your control group saw a 0.5% conversion. The control data suggests that, without any media exposure, you would have seen a 0.5% conversion. Keep in mind that conversion could mean leads, sales, profit or whatever metric that is important to your business.
So (1.5% – 0.5%) / 1.5% = 66.7% incrementality in conversions
What Channels Make Sense for Incrementality Testing?
Advertising that generates a lot of impressions but not immediate action like a click still has brand value that ultimately leads to conversions or sales. Channels such as online display, video/YouTube, Facebook, TV, and direct mail all provide impressions, but are not always measured at the click or direct response level. That’s where incrementality testing comes in.
You can read more about the following channels here:
- Measuring Incrementality on Display Advertising
- Measuring Incrementality on Facebook
- Measuring Incrementality on Direct Mail
- Measuring Incrementality on Catalog
Incrementality Testing with Measured
Using experiments to test the incremental contribution of media to your business is the best way to make informed marketing decisions that fuel growth.
Only Measured delivers ongoing, reliable insights based on scientifically sound experiment designs that incorporate your source of truth transaction data. Everything is automated – ingestion and management of data from hundreds of sources, experiment design and implementation, and continuous reporting for confident, agile decision-making.
Could your advertising deliver more business value?
Try the free incrementality calculator to reveal how much you could improve your CPO or ROAS by replacing last-click with incrementality measurement.
Original Publisher
Incrementality testing, when executed properly, can account for the pixel related blindness that occurs when trying to use MTA to measure the effectiveness of Walled Garden media.
Ready to see how trusted measurement can help your brand make smarter media decisions?
Press Focus on the High Value Decisions
“Start with the questions you want to answer and work back from there.”
That has been the conventional wisdom when it comes to media measurement. To some extent that makes sense. But is that all there is to it? We can think of several examples where just asking the question without being mindful of the decision falls short. We suggest taking this further and focusing on the decision you will make when this question is answered. How will this decision change based on the range of possible outcomes?
With regard to cross-channel media measurement, we first need to understand what media investment decisions are being informed, the range of possible outcomes, and how decisions will change based on this range. With this information, you can then prioritize measurement resources and the requirement for precision.
Following are two examples of commonly asked questions that, while interesting, do not inform a practical media investment decision that will change based on the possible outcomes.
How can I understand the exact path my customers take to a conversion?
This sounds great but is essentially impossible. Set aside whether this is doable in the walled-garden privacy-sensitive environment in which we live today. If it were possible to have a clear understanding of the exact path sequence, what media-investment decisions would you make? Unless you spend 100 percent of your media investment with a single programmatic partner, you can’t force a human to consume media in the exact sequence and path you desire.
How can I understand the incrementality of my branded search?
Again, this sounds like a compelling question, but often the decision to own your brand keyword is strategic. Whether the incrementality is 5 or 95 percent, be mindful of the resources required to chase this down with precision as the investment decision is not likely to change.
Instead of those two, here are three better cross-channel measurement questions that align perfectly to the investment decision-making process and will change significantly based on the range of potential measurement outcomes.
- Which of my prospecting tactics and media vendors can I continue to spend into related to my guiding metric, and how much should I adjust my budget for each in a test-learn-grow framework?
- How much can I spend into a specific prospecting tactic and vendor before the amount reaches my guiding metric limitation?
- Which prospecting tactics are not performing and should be cut or have their budgets reduced (and by how much) in a test-learn-grow framework?
In the world of cross-channel media measurement, asking the right questions is important but being clear on the related decisions and range of possible outcomes is just as critical for the prioritization of resources, the success of your campaign, and driving growth for the business.
In the world of cross-channel media measurement, asking the right questions is important but being clear on the related decisions and range of possible outcomes is just as critical.
“Start with the questions you want to answer and work back from there.”
That has been the conventional wisdom when it comes to media measurement. To some extent that makes sense. But is that all there is to it? We can think of several examples where just asking the question without being mindful of the decision falls short. We suggest taking this further and focusing on the decision you will make when this question is answered. How will this decision change based on the range of possible outcomes?
With regard to cross-channel media measurement, we first need to understand what media investment decisions are being informed, the range of possible outcomes, and how decisions will change based on this range. With this information, you can then prioritize measurement resources and the requirement for precision.
Following are two examples of commonly asked questions that, while interesting, do not inform a practical media investment decision that will change based on the possible outcomes.
How can I understand the exact path my customers take to a conversion?
This sounds great but is essentially impossible. Set aside whether this is doable in the walled-garden privacy-sensitive environment in which we live today. If it were possible to have a clear understanding of the exact path sequence, what media-investment decisions would you make? Unless you spend 100 percent of your media investment with a single programmatic partner, you can’t force a human to consume media in the exact sequence and path you desire.
How can I understand the incrementality of my branded search?
Again, this sounds like a compelling question, but often the decision to own your brand keyword is strategic. Whether the incrementality is 5 or 95 percent, be mindful of the resources required to chase this down with precision as the investment decision is not likely to change.
Instead of those two, here are three better cross-channel measurement questions that align perfectly to the investment decision-making process and will change significantly based on the range of potential measurement outcomes.
- Which of my prospecting tactics and media vendors can I continue to spend into related to my guiding metric, and how much should I adjust my budget for each in a test-learn-grow framework?
- How much can I spend into a specific prospecting tactic and vendor before the amount reaches my guiding metric limitation?
- Which prospecting tactics are not performing and should be cut or have their budgets reduced (and by how much) in a test-learn-grow framework?
In the world of cross-channel media measurement, asking the right questions is important but being clear on the related decisions and range of possible outcomes is just as critical for the prioritization of resources, the success of your campaign, and driving growth for the business.
Original Publisher
In the world of cross-channel media measurement, asking the right questions is important but being clear on the related decisions and range of possible outcomes is just as critical.
Ready to see how trusted measurement can help your brand make smarter media decisions?