Main Properties of the Normal Probability Curve

 

15

Main Properties of the Normal Probability Curve 

The normal probability curve, also known as the Gaussian distribution, is a cornerstone of statistical theory and a fundamental tool in the behavioural and natural sciences. Its mathematical properties and practical applications allow researchers to make inferences about populations from sample data. This document outlines 15 main properties of the normal probability curve and expands upon its key characteristics and applications, supported by academic references.

1. The normal curve is symmetrical: The curve is perfectly symmetrical about the ordinate at the central point. This means the left half is a mirror image of the right half. Consequently, for any value a certain distance from the mean, there is a corresponding value on the opposite side with the same frequency .

2. The normal curve is unimodal: The curve has a single peak, indicating that the maximum frequency of scores occurs at one point along the horizontal axis. This single peak corresponds to the mode of the distribution .

3. Mean, median and mode coincide: Due to its perfect symmetry, the mean (µ), median (Mdn), and mode (Mo) of a normal distribution are all equal and located precisely at the centre of the distribution .

4. The maximum ordinate occurs at the centre: The highest point (the peak) on the curve, known as the maximum ordinate ($Y_0$), occurs at the mean. This represents the most frequent score in the distribution .

5. The normal curve is asymptotic to the X-axis: The tails of the curve approach, but never touch, the horizontal axis. They extend infinitely in both directions ($-\mathrm{\infty }$ to $+\mathrm{\infty }$), implying that while extremely unlikely, values can theoretically be very far from the mean .

6. The height of the curve declines symmetrically: As one moves away from the mean in either direction, the height of the curve (the ordinate) decreases at a rate proportional to the distance. The ordinates for values equidistant from the mean (e.g., $\mu +1\sigma$ and $\mu -1\sigma$) are identical .

7. The points of inflection occur at $\pm 1$ standard deviation ($\pm 1\sigma$): The points where the curve changes from being concave down (curving inward) to concave up (curving outward) are called points of inflection. In a normal distribution, these points are located exactly one standard deviation above and below the mean .

8. The total percentage of area under the curve within points of inflection is fixed: According to the Empirical Rule, approximately 68.26% of the total area under the curve—and thus approximately 68.26% of the observations—falls within $\pm 1\sigma$ of the mean .

9. Normal curve is a smooth curve: The normal distribution is a continuous probability distribution, represented by a smooth, bell-shaped curve rather than a histogram with discrete bars. It has a specific kurtosis value of 0.263 (often simplified to 0.265 or referred to as mesokurtic), which defines its moderate peakness .

10. The normal curve is bilateral: Exactly 50% of the total area under the curve lies to the left of the mean, and 50% lies to the right. This property is a direct consequence of its symmetry .

11. The normal curve is a mathematical model in behavioural sciences: It serves as a theoretical model for many naturally occurring variables, such as IQ scores, heights, and measurement errors, and provides a basis for statistical inference .

12. Greater percentage of cases at the middle of the distribution: A majority of observations cluster around the mean. The distribution of cases is as follows:

    • $\pm 1\sigma$: 68.26% of cases.

    • $\pm 2\sigma$: 95.44% of cases.

    • $\pm 3\sigma$: 99.73% of cases.
      This leaves only a very small percentage (0.27%) of cases outside $\pm 3\sigma$ .

13. The scale of X-axis in normal curve is generalised by Z deviates: Any normal distribution can be transformed into the standard normal distribution with a mean of 0 and a standard deviation of 1. This is done by converting raw scores (X) into Z-scores using the formula $Z=\frac{X-\mu }{\sigma }$. This standardization allows for the use of single probability tables (Z-tables) for all normal distributions .

14. The equation of the normal probability curve:
    The mathematical formula for the normal probability density function (PDF) is:

    $$y=\frac{N}{\sigma \sqrt{2\pi }}{e}^{-\frac{(X-\mu {)}^2}{2{\sigma }^2}}$$

    or more commonly for a single observation:

    $$f(x)=\frac{1}{\sigma \sqrt{2\pi }}{e}^{-\frac{1}{2}{\left(\frac{x-\mu }{\sigma }\right)}^2}$$

    where $y$ or $f(x)$ is the height of the curve, $x$ is the score, $\mu$ is the population mean, $\sigma$ is the population standard deviation, $\pi \approx 3.14159$, and $e\approx 2.71828$ .

15. The normal curve is based on elementary principles of probability: The other name of the curve is the normal probability curve because the total area under the curve is 1 (or 100%), and the probability of a score falling within a specific interval is represented by the area under the curve for that interval .

References and Further Reading

The properties and applications listed above are standard across statistical literature. For deeper exploration, the following sources are recommended:

• For a comprehensive overview of properties: Academic textbooks such as those by Lovric (2011) and Mann (2012) detail the mathematical underpinnings of the normal distribution and its characteristics . A foundational text on continuous distributions, including the normal curve, is provided by Johnson, Kotz, and Balakrishnan .

  • Reference: Johnson, N. L., Kotz, S., & Balakrishnan, N. (1994). Continuous Univariate Distributions, Volume 1 (2nd ed.). Wiley. ISBN: 978-0471584957

• For the history and derivation: The normal distribution is also known as the Gaussian distribution, named after Carl Friedrich Gauss, who used it to model astronomical data . Its derivation from the theory of errors and the method of least squares is a key part of its history.

  • Reference: Gauss, C. F. (1809). Theoria motus corporum coelestium in sectionibus conicis solem ambientium. (Theory of the Motion of the Heavenly Bodies Moving about the Sun in Conic Sections).

• For the Empirical Rule (68-95-99.7 Rule): This rule is a direct application of the properties of the normal curve and is cited in numerous introductory statistics texts and resources . It provides a quick way to understand the spread of data in a normal distribution.

  • Reference: The exact percentages (68.27%, 95.45%, 99.73%) are derived from integrating the standard normal density function. Tables providing these areas under the curve have been published for over a century. An authoritative source for statistical tables is:

    • Reference: Fisher, R. A., & Yates, F. (1963). Statistical Tables for Biological, Agricultural and Medical Research (6th ed.). Oliver & Boyd.

• For the equation and its components: The probability density function (PDF) of the normal distribution is defined by its parameters, $\mu$ and $\sigma$, and the mathematical constants $\pi$ and $e$ .

  • Reference: The function is a solution to a specific differential equation and its role in probability theory is central to the Central Limit Theorem, which states that the sum of a large number of independent random variables will be approximately normally distributed. For a rigorous treatment, see:

    • Reference: Feller, W. (1968). An Introduction to Probability Theory and Its Applications, Volume 1 (3rd ed.). Wiley. ISBN: 978-0471257080

Conclusion

The normal probability curve is more than just a theoretical concept; it is a practical tool that underpins modern statistics. Its well-defined properties—symmetry, asymptotic nature, and fixed area percentages—make it invaluable for interpreting data, testing hypotheses, and making predictions across diverse fields from education and psychology to finance and manufacturing . Understanding these properties is essential for any researcher or student engaged in quantitative analysis.