Comments on Marilyn's IQ

Marilyn is Wrong Copyright © 1998 Herb Weiner. All rights reserved.

Ask Marilyn ® by Marilyn vos Savant is a column in Parade Magazine, published by PARADE, 711 Third Avenue, New York, NY 10017, USA. According to Parade, Marilyn vos Savant is listed in the "Guinness Book of World Records Hall of Fame" for "Highest IQ."

Extremely Improbable

Jud McCranie <jud.mccranie@mindspring.com> offers the following analysis:
An IQ of 228 possible, but highly unlikely. IQ scores are normally distributed with a standard deviation of about 15. I've done some calculations.

Population (billions)   Likely highest IQ

6                            197
10                           199
20                           201
50                           203
100                          204
1,000                        210

There are 5 to 6 billion people on the Earth. I think that the record before Marilyn was 196 -- in good agreement with expectation. An IQ of 228 is way beyond expectations.

With 6,000,000,000 people -- the likely difference between highest IQ and the second highest is 0.11 standard deviations, or a mere 1.7 IQ points. Marilyn's claim: 32 points above the second highest.

The chances that any particular person on Earth (chosen at random) has an IQ of 228 is about 1 in 9,800,000,000,000,000. That is less likely than buying one ticket in the 6 number state lottery and winning the grand prize, and buying one more ticket the next week and it winning that grand prize too.

The chances that anyone on Earth has an IQ of 228 is about 1 in 1,600,000,000 -- that's over 100 times less likely than a single lottery ticket matching all 6 numbers. So it is extremely unlikely that anyone on Earth has an IQ of 228.

Marilyn's IQ Results

Darryl Miyaguchi <miyaguch@usa.net> responds:

Jud McCranie's IQ table may be slightly misleading in a couple of ways. For one, the Stanford-Binet IQ test which Marilyn took assigns 16 IQ points per standard deviation (not 15). Second, it is not a given that IQ scores are perfectly normally distributed, although that may be approximately true. So it is quite possible that there are more extremely high scores than would be expected from a perfect bell curve.

Marilyn's official score on her Stanford-Binet form L (as written on her school record) was actually "167+" (ceiling score). See the article, "In The Kingdom of the Brain -- How Love Changed the Smartest Couple in New York," by Julie Baumgold, in the magazine, New York, February 6, 1989.

Estimated IQs for Some of the Greatest Geniuses

Ulf Norlinger <ulf.norlinger@swipnet.se> writes:
I agree with you that it is highly improbable that Marilyn scored such high, if it was for an adult. But for a ten year old it is not completely uncommon. So far as I have heard her IQ score in adult age have been reported to be 218 Stanford-Binet. That is improbable though. Even with an empirically adjusted Bell-curve, according to Encyclopedia Britannica, nobody in history should have scored above 210 - 215 Stanford-Binet at adult age!

For more information, refer to Estimated IQs for Some of the Greatest Geniuses.


http://www.wiskit.com/marilyn/iq.html last updated October 3, 1998 by herbw@wiskit.com