If I’d known we had so many math geniuses reading The Slog, I’d have outsourced my reporting to you guys a long time ago.

On Wednesday, Slog reader “student” did a linear regression on Tom Carr’s ass (or on Tom Carr’s marijuana numbers, to be more precise — sorry, couldn’t resist saying that). Anyway, I had no idea what “student” was talking about. A sample:

1/(# of filings) = A + B*year + C*(0 if before I-75, 1 if after) + error; you find that it fits the data really well. The model is statistically significant at levels as low as 0.001013% (5% or 1% are usually considered convincing), and it explains around 98% of the variability of the data (adjusted R-squared = 0.9859).

But Slog readers translated for me. The best translation:

There is a 99.998987% chance that Carr is full of shit in claiming that the drop in the number of pot-busts after I-75 was due to random year-to-year changes in the number of busts.

Thanks, “golob.” Meanwhile, a new plot twist to the story that never ends. Or, more accurately, an old plot twist. A friend at The Seattle Times wants me to note that his paper got the pot numbers right back in August, two months before the P-I got the pot numbers wrong. But here’s the strange thing: The source for the numbers in both stories was Tom Carr.

So, to recap: Tom Carr was for the correct marijuana numbers before he was against them (and twice stood by being against them), which was all before he was for them again. Got that?

I now return to the question I posed in my first post about all of this: What was Tom Carr smoking?