The plural of “anecdotes” isn’t “data” … or is it?

Sometimes, anecdotes are sufficient to inform decisions.  Hydroxychloroquine may be one of those cases.


In my business analytics course, I used to preach the conventional wisdom that “anecdotes aren’t data” … and “make decisions based on data, not anecdotes”.

Those are good principles, but they don’t always hold.

And, when I was operating in the real world, I didn’t always follow them.

More often than not, business decisions must be made despite incomplete and sometimes conflicting data.


When time is of the essence, you decide based on the data you have, not all the data that you wish you had.

The key phrase is “when time is of the essence”

So, you have really have 2 decisions to make: (1) Is time really of essence?, and if the answer is “yes”, then (2) What’s the course of action that is most likely to be net beneficial?

The 2nd question relies on the information that’s available at the time.

Sometimes, all you have are a handful of credible anecdotes or a compelling incident.

For example, a long time ago, working for B&D, a customer reported that one of our new coffeemakers had caught fire in his home. The guy was an engineer and he wasn’t asking for any compensation (“I was going to paint the kitchen any way … just thought you should know”).  Based on that one reported incident, we immediately halted production and initiated  a full -blown safety review.

Other times, you have a folder full of field reports (aka “anecdotes”).  They may not be random, but they sure are countable.  In other words, they do constitute data!

Sometimes you resort to analogies – situations that are structurally similar to the one you’re facing.  In effect, you port as much learning as you can from past experience.


OK, that brings us to the current controversy re: the use of Hydroxychloroquine to treat coronavirus patients.

The beloved Dr. Fauci says to hold off until there are closely controlled randomized tests of the drugs safety and efficacy.

Pres. Trump points out that the drug has been safely used for decades and there are reports of it working on coronavirus patients … so, let it rip.

Does that make Trump anti-science?

I think not.

In the WSJ article “These Drugs Are Helping Our Coronavirus Patients”, two doctors present the case for using Hydroxychloroquine:

  • The medication is relatively safe, with the main side effect being stomach irritation
  • In 2005, CDC study showed that chloroquine, an analogue, could block or inhibit the virus.
  • On March 9, a team of researchers in China published results showing hydroxychloroquine was effective against the 2019 coronavirus in a test tube.
  • Researchers in France treated a small number of patients with both hydroxychloroquine and a Z-Pak, and 100% of them were cured by day six of treatment.
  • Doctors in France, South Korea and the U.S. are already using  hydroxychloroquine on coronavirus with success. In fact, it’s part of some hospitals’ formal treatment protocols.

Additional  clinical information has also emerged from Covid treatment.

During the initial Chinese outbreak, Wuhan doctors observed that patients with lupus — a disease for which Hydroxychloroquine (HC) is a common treatment — did not seem to develop Covid-19.

Of 178 hospital patients who tested positive, none had lupus and none were on HC.

Though exposed to the virus, none of this Wuhan hospital’s 80 lupus patients were infected with the novel coronavirus.

The Wuhan doctors hypothesized that this may be due to long-term use of HC.  Source


All of the above can probably be categorized as anecdotal by, in my opinion, there are enough of them to constitute data … and the data is pretty compelling even if it’s not the result of a randomized controlled test.


So, back to our other decision criteria: Is time of the essence?

With the death toll now over 2,000 … you bet it is.

I’m with DJT (and the docs in the battle) on this one:

Let doctors prescribe Hydroxychloroquine  for their COVID-19 patients. 


P.S. Dr. Fauci had his chance to do randomized controlled tests back in 2005, but the CDC didn’t follow up on its own report.


Follow on Twitter @KenHoma

>> Latest Posts


3 Responses to “The plural of “anecdotes” isn’t “data” … or is it?”

  1. WSJ Shocker: 1 in 3 infected patients gets a ’false negative’ test result. | The Homa Files Says:

    […] See The plural of “anecdotes” isn’t “data” … or is it? […]

  2. Dr. Fauci gets grilled on Hydroxychloroquine… | The Homa Files Says:

    […] The plural of “anecdotes” isn’t “data” … or is it? […]

  3. Would I take HCQ like Trump is doing? | The Homa Files Says:

    […] The plural of “anecdotes” isn’t “data” … or is it? […]

Leave a Reply

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

You are commenting using your 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