Normal Distribution – Comprehensive Study Notes

Overview of the Lesson Goals

• Primary objective: Develop a clear understanding of the normal distribution and its defining characteristics.
• Emphasis on recognizing its bell-shaped curve, symmetry, and relevance to later statistical inference procedures.

Visual Shape & General Characteristics

• The distribution is bell-shaped, yet:
  • Bell shapes can vary in width and height; not all bell-shaped curves are truly normal.
  • A curve looking like a bell does not automatically imply normality.
• Symmetry around the central axis:
  • Because of this symmetry, the mean ((\mu)), median, and mode are all equal.
• Infinite theoretical range:
  • Values extend from $-\infty$ to $+\infty$, though extreme values occur with extremely low probability.

Fundamental Properties

• Total area under any normal curve equals 1 (i.e., total probability is 100%).
• Empirical Rule (68–95–99.7 Rule): For every normal distribution, the fraction of total area—and therefore probability—within a certain number of standard deviations ((\sigma)) of the mean is fixed:
  • Within 1(\sigma): $0.6826 \approx 68.26\%$ of observations.
  • Within 2(\sigma): $0.9544 \approx 95.44\%$ of observations.
  • Within 3(\sigma): $0.9974 \approx 99.74\%$ of observations.
• Probability as area: To find the probability that a normally distributed variable falls inside an interval, compute the area under the curve bounded by that interval.

Probability Density Function (PDF)

• A normal distribution is fully defined by its PDF:
  $f(x) = \frac{1}{\sigma\sqrt{2\pi}} e^{-\frac{(x-\mu)^2}{2\sigma^2}}$
• Parameters:
  • (\mu) (mu): the mean—determines the location/center of the curve.
  • (\sigma) (sigma): the standard deviation—controls the spread/dispersion.
• Effect of changing parameters:
  • Change in (\mu) with fixed (\sigma): Shifts the entire curve left or right without altering its shape.
  • Change in (\sigma) (holding (\mu) constant):
  • Larger (\sigma) → curve becomes flatter and more spread out.
  • Smaller (\sigma) → curve becomes taller and more concentrated around the mean.

Importance in Statistical Theory

• The normal distribution underpins many statistical inference techniques covered in subsequent lessons.
• Numerous methods—confidence intervals, hypothesis tests, and regression diagnostics—assume or rely on normality.

Practical & Theoretical Caveats

• Bell shape ≠ Normal: Some distributions resemble bells yet fail normality tests; always verify with diagnostics rather than appearance alone.
• While the curve extends to infinity, real-world datasets may truncate or approximate the tails; nonetheless, theoretical results assume the full infinite range.

End of lesson recap: Understanding symmetry, area properties, and parameter effects equips you to compute probabilities, interpret z-scores, and apply normal-based inference tools confidently in later coursework.