Skip main navigation

New offer! Get 30% off your first 2 months of Unlimited Monthly. Start your subscription for just £35.99 £24.99. New subscribers only T&Cs apply

Find out more

Determining Cause and Effect through Experiments

Distinguishing between correlation and causation is critical to interpreting experiment results. Watch Raj Venkatesan explain more.
To understand experiments, we need to understand the distinction between correlation and causation. To do that, let’s consider this headline from a news article posted on WebMD. This headline says, does skipping breakfast cause obesity?
Think about it. Do you think that’s true? Well, you can say that people who are skipping breakfast are also obese, that there’s a positive correlation, but does that mean that the act of skipping breakfast for some reason causes obesity? We say, wait a minute, there may be other reasons here. It could be that people who are less active physically are making a plate past breakfast time and therefore, they are skipping breakfast. But the lack of physical activity is what is driving their obesity.
It could be people who are partying all night, going to bed late, waking up late, skipping breakfast, are also a piece, but it could be all the calories in the drinks that is causing obesity, not skipping breakfast. So the key here is to understand that it’s quite possible to see that some things are correlated with each other and think that one is causing the other. But you need to dig deeper to understand whether there is a causal relationship between two things. But why is that important for marketing?
Because let’s go back to this old saying that we know from the father of modern advertising. Half the money I spend on advertising is wasted; the trouble is I don’t know which half. And remember, we are trying to understand which half is wasted. And you want to know what is the effect of marketing on sales. Are marketing and sales correlated or does one cause the other? Can marketing cause sales and which part of marketing causes sales? And that’s what we are trying to find out and that’s what is why experiments are important in marketing.
It is also related to the concept of return on investment.
But why is the return on marketing spending difficult to measure? There’s marketing spending on TV, promotion, better customer targeting, but why is it difficult to know their effect on sales? It’s because marketing happens in the midst of a lot of other things. It’s not done in isolation in a lab. So the main question that is difficult to address is, would you have achieved the same sales increase without the increased advertising spend? This a conversation between chief marketing officers and chief financial officers all the time. When the chief marketing officer goes and says, look, I’ve been spending a million dollars, give me $2 million, I’m going to double your sales.
The chief financial officer says, well, wait a minute, what if the sales increases and by itself, well, how can you show me that your increase in marketing is what cause the increase in sales? If you don’t increase marketing, would the sales increase without the increase in marketing? To make that answer, to clarify that to the CFO, the CMO needs to understand what is the casual effect of marketing on sales. And experiments are a way to determine that causal effect.

Learn about how to distinguish between correlation and causation in order to ensure your marketing experiments are actually increasing sales.

This article is from the free online

Marketing Analytics

Created by
FutureLearn - Learning For Life

Reach your personal and professional goals

Unlock access to hundreds of expert online courses and degrees from top universities and educators to gain accredited qualifications and professional CV-building certificates.

Join over 18 million learners to launch, switch or build upon your career, all at your own pace, across a wide range of topic areas.

Start Learning now