How to Analyze Lagged Effect of Ad Spend | Adstock | Statistics for Marketers Series скачать в хорошем качестве

How to Analyze Lagged Effect of Ad Spend | Adstock | Statistics for Marketers Series

In performance marketing, whenever a shift happens (either in the positive or in the negative direction), the first impulsive reaction of the marketer is to increase or decrease budget immediately. But this is based on the belief that very recent spend (yesterday's) is responsible for today's performance shift. To truly understand the relationship between ad spend and revenue or sales, you would ideally need to carry out an MMM and a causal lift test, as these can help isolate the real adstock. But this is hard to achieve. That's why I instead propose a simple solution - a correlation analysis to find the lag with the highest correlation with ad spend of today. This is a great place to start and you can follow it up with causal tests (that I have discussed in other videos). Statistical tests like ANOVA have been used to establish significance levels of the outputs like percentage of variance explained. I also show how to combine this with the day of the week effect, a kind of natural seasonal demand variation. Together these two analyses can give you a powerful yet easily available weapon to tackle performance challenges. If you want the app, just comment below or get in touch with me on LinkedIn. #marketinganalytics #performancemarketing #dataanlysis #statisticalanalysis #marketingmeasurement