Understanding Percentiles in Normal Distribution

Jul 12, 2025

Overview

This lecture explains percentiles in the context of a normal distribution, illustrating how to find both the percentile for a given value and the value for a given percentile using the empirical rule.

Understanding Percentiles

  • Percentile represents the percentage of data that falls below a specific value in the dataset.
  • The 25th percentile means 25% of data points are below that value.
  • Percentiles are often interpreted with context, such as test scores or weights.

Using the Empirical Rule with Percentiles

  • The empirical rule describes data distribution in a normal curve: approximately 68% within one standard deviation, 95% within two, 99.7% within three.
  • For the weights example, key values on the curve are labeled: 56, 82, 108, 134, 160, 186, and 212 pounds.

Finding the Percentile for a Given Value

  • To find the percentile for 160 pounds, consider the area under the curve to the left of 160.
  • The mean is the midpoint, so 50% of data is below the mean.
  • From the mean to one standard deviation above is 34%; add to 50% for a total of 84% below 160 pounds.
  • Thus, 160 pounds is at the 84th percentile.

Finding the Value for a Given Percentile

  • To find what weight represents the 16th percentile, shade from the left up to where 16% of the area is covered.
  • The cumulative area up to one standard deviation below the mean (108 pounds) equals 16% of the data.
  • Therefore, the 16th percentile corresponds to 108 pounds.

Key Terms & Definitions

  • Percentile — The percentage of data values that fall below a specific value.
  • Empirical Rule — States that for a normal distribution: 68% is within 1 SD, 95% within 2 SD, and 99.7% within 3 SD of the mean.
  • Standard Deviation (SD) — A measure of the spread or dispersion of a set of data points.

Action Items / Next Steps

  • Practice finding percentiles for specific values using the empirical rule and normal distribution.
  • Review how to find values corresponding to specific percentiles on a normal curve.