The normal distribution
The normal distribution is a continuous probability distribution used to model many real-world
measurements (heights, weights, times, scores) that cluster around a central value with random variation.
A normal random variable is fully determined by two parameters: the mean μ and the
standard deviation σ.
Probability density function
The normal curve is described by a probability density function (pdf) f(x). Probabilities are areas
under this curve.
\[
\begin{aligned}
f(x) &= \frac{1}{\sigma\sqrt{2\pi}}\;e^{-\frac{1}{2}\left(\frac{x-\mu}{\sigma}\right)^2}
\end{aligned}
\]
Key properties of the normal curve
\[
\begin{aligned}
\text{Total area under the curve} &= 1 \\
\text{Symmetry about } \mu &\Rightarrow P(X \le \mu)=0.5 \\
\text{Tails extend indefinitely} &\text{ and approach the horizontal axis} \\
P(X=c) &= 0 \\
P(a \le X \le b) &= P(a < X < b)
\end{aligned}
\]
Standardization (z-scores)
Many probability calculations use the standardized variable Z, obtained by converting X into a
z-score. This expresses how many standard deviations x is from the mean.
\[
\begin{aligned}
z &= \frac{x-\mu}{\sigma}
\end{aligned}
\]
A family of curves
Changing μ shifts the curve left or right without changing its shape. Changing σ changes the
spread: smaller σ produces a taller, narrower curve; larger σ produces a wider, flatter curve.
Grouped data and density histograms
When observations are grouped into class intervals, a class probability can be approximated by the class
relative frequency. If class widths are not 1 unit, it is common to plot density so that the
total bar area equals 1.
\[
\begin{aligned}
\text{density}_i &= \frac{r_i}{w_i}
\end{aligned}
\]
Here ri is the relative frequency for class i and wi is its class width.
The calculator can estimate μ and σ from grouped data using class midpoints, then overlay the fitted
normal curve on the density histogram.