The Recast Blog
Start Measuring What Matters
We see a lot of media mix modeling RFPs here at Recast. Unfortunately, a lot of them don’t emphasize what we, as practitioners, think is most important – not to us, but to them as a brand. …
Featured Posts
All Recast Articles
Attribution is opinion, canonical conversions are fact
Ad platforms use their attribution models to tell you which campaigns contributed to conversions (leads, sales, subscriptions or whatever is most important to your business). The way they measure attributed conversions is an opinion based on the data available to the platforms. It’s subject to limitations (for example, conversions need …
Attribution is opinion, canonical conversions are fact Read More
The difficulty measuring ‘dark social’ traffic and word of mouth
There’s a commonly cited Neilsen study that revealed that 92% of consumers trust referrals from family or friends more than any other type of advertising or referral. If you read that report and think “I wonder how much of my traffic comes from word of mouth”, well it’s actually not …
The difficulty measuring ‘dark social’ traffic and word of mouth Read More
Are you wasting money on Branded Paid Search?
The Search Advertising Market has been valued at 178 Billion in 2021 and is expected to grow at an 8.5% Compounded Annual Growth Rate from 2021 to 2018. Search is an important part of the Marketing Mix for most companies. One of the drivers of Search Advertising’s rise is its …
Geo-testing Won’t Save You
Disclaimer: This blog post was written by an external contributor about geo-testing for measuring advertising effectiveness. The approach laid out in this document is not reflective of how Recast approaches geo-testing and geo-level analysis. The actual model specification can be found in the technical model specification. Ever since Apple gave …
Is there a good way to do a test of statistical significance for ROAS?
Someone posed the following query in a marketing measurement slack I’m in: At first, this question seemed really easy. Hubristically, I replied “just use a t-test for difference in means.” However, it turns out that the analysis isn’t quite so straightforward (which I realized after a few minutes of thought …
Is there a good way to do a test of statistical significance for ROAS? Read More
Cleaning URLs for Accurate Channel Attribution
Anyone who’s ever run an online marketing campaign has encountered URL parameters. These are an additional section you add at the end of the URL, usually to track the marketing source of people who click on your ads, emails, or other marketing campaigns. Because over 60% of the internet uses …
Google Analytics Channel Attribution Made Us Switch Off Our Growth Engine
Nobody sits down to make a channel investment decision they hope will immediately lose millions of dollars and get them axed, but that’s what’s at risk if you’re using purely cookie-based attribution. Attribution expert Michael Taylor compares cookie based attribution to “looking under a street light for a wallet you …
Google Analytics Channel Attribution Made Us Switch Off Our Growth Engine Read More
How much data do you need for your Marketing Mix Model?
One commonly asked question from clients just getting started with Marketing Mix Modeling (MMM), is how much data they need to build a model. It’s a particularly important question in B2B, where there isn’t always the volume that large scale consumer brands enjoy. In theory there’s no ‘right’ answer to …
How much data do you need for your Marketing Mix Model? Read More
What does ‘Incrementality’ mean?
You may have heard the term incrementality in the context of marketing attribution, and wondered what exactly it meant. Incrementality is about measuring what actions would not have happened without a specific intervention. For example if I spend money advertising my product, I need to know how many people bought …
Why R-squared is worse than useless
At Recast I have the privilege and challenge of introducing advanced statistical concepts to people who have a strong desire to be more data driven, but who do not have much of a background in formal statistics. While word has gotten out that “statistical significance” isn’t all it’s cracked up …