What a few Cybertrucks taught me about statistics, AI, and logical thinking

A striking count

During our road trip through California, my children started counting Tesla Cybertrucks. Not because there was a serious research design behind it, but simply because it is such a striking car that you can hardly miss it when one drives past. In San Francisco and the Bay Area, we saw about ten; around Santa Barbara and Los Angeles, around five; but at Lake Tahoe, we suddenly saw dozens. That difference stood out, and right there began the interesting part for me: not the count itself, but the question of what such a seemingly random observation could mean.

Initial doubt

Of course, this is not a representative sample. We didn’t drive for the same amount of time everywhere, we didn’t visit randomly selected areas, and we didn’t systematically track how many cars drove past in total. So it could very well be a coincidence. Perhaps we simply went to places around Lake Tahoe where many Cybertrucks are driven, perhaps purchasing power and second homes play a role, or perhaps a large pickup truck practically suits the environment better there than in an urban area. All these explanations are plausible, and that is precisely why it is interesting not to immediately settle on a single narrative.

Where statistics begins

For me, statistical thinking doesn’t start with a spreadsheet, a regression model, or a significance test, but with an observation that forces you to ask better questions. You notice something remarkable, formulate an initial hypothesis, and then try not to prove it, but rather to debunk it. What other variables could explain the same pattern? Is there a selection bias? Are you looking at a specific demographic? Is there a third factor behind the correlation? Or are you simply seeing noise and assigning meaning to it in hindsight?

More than a car

With the Cybertruck, this becomes especially interesting because, culturally, the model is much more than just an electric vehicle. For years, driving electric in the United States was strongly associated with progressive, urban, and predominantly Democratic consumers, whereas pickup trucks had a much stronger cultural connection with a more conservative and Republican America. The Cybertruck strikingly brings those two worlds together: electric technology from Silicon Valley, packaged in an extremely distinct American truck.

Tesla shifted too

At the same time, the meaning of Tesla has changed as well. Due to Elon Musk’s increasingly visible political positioning, the brand has come to represent something different to various groups. Republican voters have grown more positive about Musk and Tesla, while the brand has lost its appeal among a segment of the Democratic base. As a result, the Cybertruck becomes interesting as a potential proxy for a broader cultural shift: driving electric is no longer automatically tied to a single political identity.

A proxy

Of course, this does not mean that someone who drives a Cybertruck is automatically a Republican, just as a house price doesn't reveal exactly how much someone earns. But proxies work precisely because they indirectly reveal something that is harder to measure directly. Search behaviour, for instance, can indicate consumer confidence, job vacancy growth can reflect economic expectations, and house prices can signal the socioeconomic development of a neighbourhood. A good proxy is never reality itself, but it can be a signal of an underlying trend.

From signal to research

That is also why such an innocent count becomes interesting to me. Not because dozens of Cybertrucks around Lake Tahoe prove that the political market for electric cars is shifting, but because the observation raises a hypothesis that you could subsequently investigate with better data. You could look at regional sales figures, political preference by county, income, vehicle type, urbanisation, second-home ownership, and other characteristics to see which explanation holds up once you control for alternatives.

Fewer bad explanations

That is exactly where the charm of statistics lies for me. Not in producing a single definitive answer, but in systematically narrowing the space for bad explanations. A good analysis shows you not only what is likely true, but also why other explanations are less probable. That requires discipline, because the first explanation often feels the most appealing, especially if it neatly aligns with the narrative you already had in mind.

AI makes this more important

With AI, this only becomes more critical. AI can rapidly find patterns, combine datasets, and formulate plausible explanations, but precisely because these explanations can sound so convincing, the risk of confusing a good story with a good analysis also increases. Correlation is not causation, a pattern is not a mechanism, and a prediction is not an explanation. AI does not change these basic statistical rules; rather, it highlights how essential they are.

Learning to think better

Therefore, I ultimately view statistics and AI primarily as tools for better thinking. They do not automatically produce the truth, but they help us formulate sharper hypotheses, seek alternative explanations, and systematically test which interpretation is the most logical. Sometimes that starts with millions of data points in a model, and sometimes it simply starts with two children in the back seat suddenly saying, "Dad, there goes another Cybertruck."

Perhaps it is a coincidence. Perhaps not. And exactly between those two possibilities is where analysis begins.