Something different: Outliers, Artifacts, and Anecdotes

Some data does not fit the pattern we identify or the narrative that guides us. How people approach a datum that does not stand in line can be ... fuzzy. Grabbing a couple of  commonly shared thoughts on the matter: 

• trimming
• winsorization
• "the plural of anecdote is not data"
• "the exception proves the rule"

"You don't count because you're different," is not usually phrased that bluntly, but I have read or heard:

Data Science versus Curation and Registration: A Year in Museums

March means I've been museum focused for a year. Visiting. Volunteering. Interacting with guests, helping collections management. Classes on the skills and technology applied.

I've learned a lot. The museum approach to helping people learn, and helping people desire to learn, is amazing and deep. Museums do not have captive audiences. They have to market learning, make it desirable. And they do. And I think that data scientists should do so too.

Small Team Designs versus Learning Access

Today, as a museum gallery host, I watched a design failure - I'm confident it was unintentional - unnecessarily block access to one of the exhibits. I think it was because of a certain way the design team was all alike.

It was a mock 1920's telegraph, attempting to highlight communications from a small town that did not yet have telephone service. It has a vigorously ruggedized mock telegraph key for the guests to try using morse code to spell out messages. When pressed firmly, it sounds a buzzer so the guest can hear the dit-dah patterns of morse code. It has the same functionality as Morse code trainers had in the era of morse-using telegraphs. The one at the link has a key, a copy of the Morse code version in use at that facility, a buzzer, and a light.

A Note About How to Influence Business Leaders

Business schools write a lot of "case studies." I write a lot about data stories. A case study is a "thick" data point, an anecdote, chosen to illustrate an idea.

At the end of an analysis, I can measure how representative a case study is. I can also write a "most-probable-case study", or "archetype study" if you prefer. Or a set of them, to represent varied environments, markets, populations, et cetera.

Read case studies to understand how business leaders are taught. Write them to help business leaders learn, in the way they already know how to learn.

That is the business power of data storytelling.

Story Characters Before Analysis: a Data Story Mistake

I saw some advice on "How to Craft a Compelling Data Narrative," and it was - I'll call it misguided. It put story craft before data analysis. Specifically: "Characters: [examples including specific customer groups omitted] This doesn’t need to be part of your presentation, but you should define the key players for yourself beforehand." This will bias and weaken your analysis. It will make your story boring.

So let's talk about how to do better analysis, and tell a more powerful story.

The Temperature of the Sky

On a clear summer day a few years ago, with a newly acquired infrared thermometer prompting my inquisition, I pondered the difference between the air temperature and radiative temperatures around me outside. It was an 80 degree (Fahrenheit) day - by air temperature, and humidity was low - probably between 25% and 35%. Yes, it was dry.

Summary and Adage

Sometimes there are nice summaries for your audience. Where this picture was taken, if the sun sets on the south side of the street, it's good to have a jacket for the evenings, and chains in the car if you drive. Perhaps shorten it to "south sunset invites cold and wet."

Useful, easy to teach... except the assumptions.

The Old Fence Line

This last weekend, I found myself in the mountains, walking by the light of the pre-dawn sky. Jupiter was bright overhead, and Venus had just risen. The new moon was with the sun, still far below the East horizon.

If you've ever done a night hike, then you understand I was a little worried about what I might walk into. The area has deer, elk, coyotes, a few bear, and a few moose. While I heard some critters shuffling in the woods, and had an owl pass close over my head, none of those were my worry.

Data and Stories: New Ideas and Old Posts

Why a new blog? This year has been more transformative for me than the COVID years. I became conscious that people are made of stories. Stories, and emotions attached to stories, are what make us people. 

In data science, where data becomes information becomes knowledge, there is no action until the knowledge becomes a story, and the story drives a decision. In software engineering, "story" is the important part of user story.  In teams, stories drive the team dynamics. In leadership, stories drive buy-in and engagement. In informal education, the story drives the interest and curiosity.