Calculator
IQ range
Minimum: Maximum: Results
Probability: Frequency: Total in the world[1]: Total ever lived[1]:
[1] Population estimates as of 2023.
Formula
The IQ "scale" is not a direct measure, but a rank, which only has meaning relative to other scores. It is defined to have a normal distribution with mean value $\mu = 100$ and (typically) a standard deviation of $\sigma = 15$:
\begin{align}f(x = IQ) &= \frac{1}{\sigma\sqrt{2\pi}} \exp\left[\frac{-(x - \mu)^2}{2\sigma^2}\right] \\\\
&= \frac{1}{15\sqrt{2\pi}} \exp\left[\frac{-(IQ - 100)^2}{2\cdot 15^2}\right]. \end{align}
Surprisingly, it is possible to convert any continuous distribution of test scores into a normal distribution that preserves the order. The probability that an IQ is less than $IQ_{max}$ is given by:
\begin{align}
P(IQ < IQ_{max}) &= \int_{-\infty}^{IQ_{max}} \frac{1}{\sigma\sqrt{2\pi}} \exp\left[\frac{-(IQ - \mu)^2}{2\sigma^2}\right] \,\mathrm dx \\\\
&= \frac12\left[1 + \operatorname{erf}\left(\frac{IQ_{max} - \mu}{\sigma\sqrt{2}}\right)\right] \\\\
&= \frac12\left[1 + \operatorname{erf}\left(\frac{IQ_{max} - 100}{15\sqrt{2}}\right)\right]. \end{align}
So the probability that $IQ_{min} < IQ < IQ_{max}$ is:
$$\frac12\left[\operatorname{erf}\left(\frac{IQ_{max} - 100}{15\sqrt{2}}\right) - \operatorname{erf}\left(\frac{IQ_{min} - 100}{15\sqrt{2}}\right)\right].$$
No comments:
Post a Comment