Sampling bias

A pizzeria once hired three teenagers to hand out discount coupons.

At the end of the month, 90% of the codes were those that were handed out by one out of the three youngsters, who received a fat bonus. The other two simply could not fathom how he did this, so they asked him. He replied that he merely distributed coupons to people who were lining up outside the pizzeria.

I recently saw a connection of mine publish a survey on LinkedIn:

Where did you hear that my company just got funded?
a. On LinkedIn
b. On Twitter
c. I haven’t heard this piece of news

Are you surprised that most respondents went with option a? If the same survey were posted on twitter, how do you think the responses would have changed?

When we use a contact thermometer, we stick in under the tongue and not in any odd crevice in the body, for we know that some samples are more accurate than others.

Your ability to choose a sample is more important than your ability to interpret its results.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s