The Danger Of A Small Sample Size

At risk of triggering your high school algebra PTSD...

I'm going to dust off the Central Limit Theorem. Because it is a good thing for all of us product marketers to keep in mind.

The CLT is pretty simple. In short, the idea is that a "random" sample of 30-50 will usually be representative of a much, much larger sample (like 5,000).

So, practically, when we're testing a pitch...

Or developing a new product...

A good rule of thumb is to try to have 50 (yes, 50!!) conversations with customers before coming to any firm conclusions.

Pretend, for example, that you're launching a new product.

And you go to 10 customers (who you already know) asking for their feedback...

And let's say 80% of them give positive encouragement of your direction...

The CLT would suggest not to trust the results for two reasons:

1. Your 10 are not necessarily "random" enough - you already know them!
2. You need a larger sample size to REALLY draw firm conclusions.

At Patent355, we recently noticed that many (most) startups' biggest problem has nothing to do with their product...

Or their willingness to listen to customers...

It's their inability (in this noisy world) to schedule those first 30-50 true feedback conversations!

So, we created an offering to help with this.

DM me if you'd like to hear the specifics of our cold email feedback program...

It's already been a game-changer for multiple clients these past few months!

(And, like all of our services, is fueled by behavioral science ??)