Content
Summary
The normal distribution is a symmetrical probability density function where the mean, median, and mode coincide, allowing probabilities to be calculated as areas under the curve. By standardizing values into z-scores, any normal distribution can be converted to the standard normal distribution (mean 0, standard deviation 1) to utilize Z-tables or technology for probability determination.
Intuition
Think of the normal distribution as a perfectly balanced bell curve where the center represents the average value. Because it is symmetrical, half of all data lies to the left of the mean and half to the right. The Empirical Rule gives us a quick mental map: roughly 68% of data sits within one standard deviation of the mean, 95% within two, and 99.7% within three. Since calculating probabilities directly via calculus is complex, we use z-scores to translate any specific value into a standardized position relative to the mean. This allows us to use universal tables or calculator functions to find the area (probability) associated with that position.
Key equations
The z-score formula, where Z is the standardized value, X is the raw value, is the mean, and s is the standard deviation.
The probability of a value being greater than x is equal to 1 minus the cumulative probability of it being less than x.
Derivation
- The normal distribution is defined as a symmetrical probability density function where the mean, median, and mode are identical.
- The Empirical Rule establishes that approximately 68%, 95%, and 99.7% of values lie within one, two, and three standard deviations of the mean, respectively.
- Direct integration of the normal distribution formula is complex, necessitating a conversion to the Standard Normal Distribution (mean 0, standard deviation 1).
- Standardization is achieved by calculating the z-score using the formula Z = (X - mean) / standard deviation.
- Once standardized, probabilities correspond to the area under the curve, which can be found using Z-tables (cumulative area to the left) or technology.
- For continuous distributions, the probability of a single point is zero, so P(X < x) is equivalent to P(X <= x).
Worked example
A researcher wants to find the probability that a value is greater than the mean in a normal distribution. Using the properties of symmetry and standardization, determine this probability.
- Identify that the normal distribution is symmetrical around the mean.
- Recognize that the total area under the curve is 1.
- Due to symmetry, the area to the left of the mean equals the area to the right.
- Calculate the area to the right: 1 / 2 = 0.5.
- Alternatively, using z-scores: The mean corresponds to Z = 0. P(Z > 0) = 1 - P(Z < 0). Since P(Z < 0) = 0.5, P(Z > 0) = 0.5.
Answer 0.5
Common mistakes
- Confusing the area to the left with the area to the right; remember that P(X > x) = 1 - P(X < x).
- Forgetting that for continuous distributions, P(X < x) is the same as P(X <= x).
- Attempting to integrate the normal distribution formula directly instead of using standardization or technology.
- Using the wrong bounds in calculator functions; for example, using 1E99 for infinity rather than a small number.