Raman getting 40% of the 6/6 ballot drop is statistically IMPOSSIBLE. Not just improbable

Loading Twitter/X Embed...
If tweet fails to load, click here.

quote:

---

The odds of Nithya Raman receiving 40% of the vote yesterday are “LESS LIKELY than picking ONE GRAIN OF SAND on Earth dozens of times in a row.” I believe elections tend to be fair. Someone help me make sense of math that seems impossible…

I ASKED CHATGPT -
“What is the statistical likelihood that 40% of votes from a “new batch” of ballots go to a candidate who received 24% of votes from all other batches that represented 95% of counted electorate. Give me a % odds.”

The Answer (Part 1) -
“Assuming the candidate’s “true” share is 24%, the odds that a random new batch lands at 40% or higher depends on batch size:
50 ballots
0.88%
100 ballots
0.028%
200 ballots
0.00004%
500 ballots
~0.00000000000018%
1,000 ballots
~0.0000000000000000000000000035%”

My follow up -
“Assume 40,000 ballots. Are the odds one in a billion? One in a trillion? Worse? This seems to be happening in Los Angeles Mayor’s race between Mayor Bass, Spencer Pratt and Nithya Raman.”

The Answer (Part 2) -
“If the 40,000-ballot batch were drawn from the same population that produced 24% support in the other 95% of votes, then seeing 40% support in that batch would be far beyond “one in a billion” or “one in a trillion.”

75 standard deviations is in an entirely different universe.

The probability is approximately:

~10?¹²²°

or about

1 chance in 10¹²²°

That’s a number with roughly 1,220 zeros after the 1.

Statistically, if the batch were truly a random sample of the same electorate, the odds are so small that statisticians would effectively treat the event as impossible. The usual conclusion would not be “wow, what a lucky fluctuation,” but rather that the batch is not representative of the earlier ballots—for example, it came from a different geographic area, voting method, demographic group, or subset of voters.

So yes: much worse than one in a billion, much worse than one in a trillion, and vastly smaller than any probability encountered in ordinary statistical analysis.”

My follow up -
“More grains of sand on earth than the likelihood of this?”

The Answer (Part 3) -
“Yes. Much, much more.

Estimated grains of sand on Earth are often put around 10¹8 to 10²°.

Your odds example was roughly:

1 in 10¹²²°

So this is not just “less likely than picking one grain of sand on Earth.”

It’s more like picking the right grain of sand on Earth correctly over and over again dozens of times in a row.”

Sincerely,
Jeremy Padawer
LINK

---