Purpose

Sponsorship identification accuracy is typically assessed as the percentage of consumers answering “yes” when asked if a brand is a sponsor (hits). However, this fails to consider misattribution (answering “yes” for a non-sponsor brand; false alarms). Misattribution reflects consumer confusion and dilutes the benefits of an official sponsorship, offers an advantage to a non-sponsoring rival and reduces a brand’s return on sponsorship investment. Informed by signal-detection theory (SDT), we show how hits may be disentangled from false alarms using a measure of sensitivity called d-prime (d’). A related measure of response bias (c) is also discussed.

Design/methodology/approach

In Study 1, we report the results of an experiment. In Study 2, we rely on a field study involving actual sponsors and fans.

Findings

The use of d’ and c is superior to tallying “yes” responses because they account for accurate sponsor attribution and misattribution to non-sponsor competitors.

Originality/value

In the context of sponsorship, we demonstrate how d’ and c can be easily calculated using Excel. Our research also includes an experimental study that establishes the hypothesized effects and then replicate results in a field setting.

中文翻译：

---

超越简单的是或否：使用信号检测理论来衡量赞助识别的准确性

 目的

赞助识别准确性通常评估为当被问及品牌是否是赞助商（点击量）时回答 “是 ”的消费者的百分比。但是，这没有考虑错误归因（对于非赞助商品牌回答 “yes”;误报）。错误归因反映了消费者的困惑，稀释了官方赞助的好处，为非赞助的竞争对手提供了优势，并降低了品牌的赞助投资回报。在信号检测理论 （SDT） 的基础上，我们展示了如何使用一种称为 d-prime （d'） 的灵敏度测量来区分命中与误报。还讨论了响应偏差 （c） 的相关测量。

设计/方法/方法

在研究 1 中，我们报告了一项实验的结果。在研究 2 中，我们依赖于涉及实际赞助商和粉丝的实地研究。

 发现

使用 d' 和 c 优于计算 “yes” 响应，因为它们考虑了准确的赞助商归因和对非赞助商竞争对手的错误归因。

 原创性/价值

在赞助的背景下，我们演示了如何使用 Excel 轻松计算 d' 和 c。我们的研究还包括一项实验研究，该研究建立了假设的效果，然后在现场环境中复制结果。