How Advertising is Measured

A brief overview of techniques for measuring advertising and its success or failure in the market.

There are a few basic ways that let you measure the effects of advertising.

Luckily there is a whole cottage industry of advertising research that puts out pages and pages of information on the topic. The idea of this post is to pull some of the main topics together for easy cataloging and reference.

The Problem

Figuring out if advertising works and whether one is doing the right kinds of advertising has been the question for the ages.

“Half the money I spend on advertising is wasted; the trouble is I don’t know which half”

John Wanamaker (1838 - 1922)

Enter Statistics

Since the late 19th century, statisticians have been throwing a lot of numbers at the problem. That means models. Lots and lots of models.

One of the earliest models for sales and advertising was AIDA:

  1. Attention
  2. Interest
  3. Desire
  4. Action

Developed by E. St. Elmo Lewis in 1898.

Ads are meant to act on a part of this funnel by improving metrics on a part of this funnel.

Since then, the statisticians have gone in on coming up with models that work to explain advertising’s effects.

Measuring from Models

So then to measure your ads you’ve got to come up with a model, then test out your various inputs against the data.

Here are some example model categories from How Advertising Works: What Do We Really Know?. They use this taxonomy to categorize a number of studies in a meta-analysis of advertising measurement models.

Depending on the type of model, the inputs, variables and outputs are going to be different. The key is to develop a model that accurately matches the dataset that you have. Then you can use that model to make predictions based on changes in the variables.

Further Reading

Quick overview of that literature:

Kudos to Advertising across Platforms: Conditions for Multimedia Campaigns for this list.

Studies about the effect of advertising on sales:

Numerous studies have highlighted the existence of synergy effects (e.g., Chang and Thorson, 2004) and reasons why these synergy effects exist. A recap of research about cross-platform advertising (Neijens and Voorveld, 2015) cited studies demonstrating specifically that:

  • The use of multiple media increases the reach of a given campaign (e.g., Briggs, Krishnan, and Borin, 2005; Enoch and Johnson, 2010; Fulgoni and Lipsman, 2014; Taylor et al., 2013).
  • Combinations of media take advantage of the unique strengths of the individual media (e.g., Dijkstra, Buijtels, and Van Raaij, 2005; Okazaki and Hirose, 2009; Tsao and Sibley, 2004). Additionally, wear-out is reduced when the consumer is exposed to multiple media (e.g., Navarro-Bailon, 2012; Stammerjohan, Wood, Chang, and Thorson, 2005).
  • Information is encoded in a more complex manner when consumers are exposed to it on multiple media (Laroche, Kiani, Economakis, and Richard, 2013; Stammerjohan et al., 2005; Tavassoli, 1998; Vandeberg, Murre, Voorveld, and Smit, 2015; Voorveld, Neijens, and Smit, 2011; Voorveld and Valkenburg, 2015).
  • Exposure to information on multiple sources may increase the credibility of that information (e.g., Chang and Thorson, 2004; Dijkstra, 2002; Laroche et al., 2013; Voorveld et al., 2011).
  • Advertisements that have been seen previously on different media may benefit from curiosity already having been stimulated (e.g., Dijkstra, 2002; Edell and Keller, 1989; Voorveld et al., 2011).
  • Recalling advertisements in one medium when exposed in another adds to synergy (e.g., Chang and Thorson, 2004; Dijkstra, 2002; Edell and Keller, 1989; Voorveld et al., 2011).

Measuring the Long-Term Effects Of Television Advertising

Advertising influences brand purchase through short-term effects determined by direct increases in penetration, basket size, and buy rate. Advertising also influences brand purchase through long-term effects determined by indirect increases of future purchases through trial and increases in loyalty and brand equity.

b9fc7cc

Comments