Pattern Sequence Test

This 4-option, binomial-scored format echoes the Zener card experiments run by J. B. Rhine at Duke University in the 1930s — subjects guessed a sequence of 5 symbols and were scored against the same chance baseline used here. Rhine reported hit rates above chance and called it evidence of ESP, but follow-up analysis found the results collapsed under proper controls: sensory leakage, selective reporting of good sessions, and recording errors accounted for the 'psychic' scores. The lesson generalizes beyond parapsychology — a p-value below 0.05 is evidence of a signal only if the experiment ruled out every mundane explanation first, human pattern recognition included.

With four options, blind guessing scores 25% on average — about 2.5 hits over 10 rounds. But luck is noisy: a pure guesser still lands 5 out of 10 roughly 8% of the time, so a score that feels impressive can be nothing but variance. That is why the tool models your result as X ~ Binomial(n, p = 0.25): on the 10-round setting you actually need 6 correct, not 5, before your score clears the p < 0.05 bar and counts as real skill.

This same 25% guessing rate once shaped how big exams were graded. To cancel any gain from blind guessing, 'formula scoring' subtracted a fraction of a point for every wrong answer, tuned so a random guess was worth zero on average — for a four-option question that fraction is exactly 1/3. The SAT applied this negative marking for decades, until 2016, when it dropped the penalty and told students to guess freely.