The Tea Statistic

I’m sorry, but the pun was just too hard to resist.

Cyril Morong, author of the blog The Dangerous Economist links to a lovely write-up by Francisca Antman about drinking tea. Now, you might wonder what is so special about drinking tea. As it turns out, it can save your life.

Well, technically speaking, it probably would have saved your life if you started to drink it in the 18th century in England.

my research adds to both the historical and development literatures by exploiting a natural experiment into the effects of water quality on mortality that occurred prior to the understanding that water contamination could compromise health. This occurred through the widespread adoption of tea drinking in England which began in the 18th century. Since brewing tea required boiling water, and boiling water is a method of water purification, the rise of tea consumption in 18th century England would have resulted in an accidental improvement in the relatively poor quality of water available during the Industrial Revolution. To what extent can the rise of tea drinking account for a drop in mortality rates at this crucial juncture in economic history?

You should of course read the whole thing, but the author of the piece took data from 18th century England and showed that the period in which imports of tea into England went up from about 1 pound per person to 3 pounds per person also happened to be the period in which the death rate in England fell from 28 per 1000 to 23 per 1000.

Now, you might argue that this could be because of a variety (pun unintended) of reasons – how do we know that this is because of an increase in tea consumption?

Fair question!

What the author does is that she uses data about cause of mortality in the same period, and notes that there was a marked decrease in deaths that were caused by water borne diseases, while deaths due to air-borne diseases did not go down in the same period. In fact, there was a marginal increase in deaths due to airborne diseases.

So the simple act of having to boil water in order to make tea went a very long way towards saving lives. Or at least, that’s the hypothesis being advanced.

Now, fans of statistics among my readers will want to carefully look over the model that has been developed, and ask some probing questions – which, of course, should happen. But if you are a student starting out in the fields of development economics, health economics, statistics or econometrics, this is a great example of what is known as a natural experiment.

Natural experiments are hard to come by in economics, so any insight that can be gleaned by figuring out how to “set” one up is worth it’s weight in gold.

Making tea can save lives, who’d have thought?

And that, given the weather in Pune, is as good a reason as any to brew myself a mug. I make mine with ginger, just to make the lives of future statisticians that much more difficult.