Study Notes on Measures of Spread
Course Information
Chapter: 3.2 (part B)
Topic: Measures of Spread
Instructor: Melony Parkhurst
Textbook: Essential Statistics, Navidi & Monk
Course Code: STAT 1401
Bell-Shaped Histogram
Description: To describe a histogram that has a single peak near the center of the data.
Shape: Bell-shaped
Histogram: This type of histogram is characterized by its symmetry and a peak at the center.
The Empirical Rule
Definition: The Empirical Rule is used for data that has a bell-shaped distribution. It provides an approximate description of the data regarding the spread and distribution of data points relative to the mean.
Characteristics:
The data follows a bell-shaped histogram.
Standard Deviations: When population data has a bell-shaped histogram:
Approximately 68% of the data falls within 1 standard deviation of the mean.
Approximately 95% of the data falls within 2 standard deviations of the mean.
Approximately 99.7% of the data falls within 3 standard deviations of the mean.
Symbols in Distribution
X-axis Representation: The symbols on the x-axis of the histogram represent the mathematical concepts and data characteristics rather than specific values. The symbol 'μ' is commonly used to denote the mean.
Data Distribution Percentages
Distribution: The percentages of data are distributed among the standard deviations in relation to the mean, as described in the context of a bell-shaped histogram. Refer to specific diagrams for highlighted areas and percentage values.
Chebyshev’s Inequality
Definition: Chebyshev’s Inequality offers a method to approximate the proportion of data within a certain number (K) of standard deviations from the mean.
Application: This inequality is more general as it can be applied to any shape of data distribution.
Comparison of Empirical Rule and Chebyshev’s Inequality
Empirical Rule:
Applicability: Only applicable to data that follows a bell-shaped distribution.
Chebyshev’s Inequality:
Applicability: Can apply to any shape of data distribution, hence is more versatile.
Disadvantages: Often provides a rough approximation, and the actual proportions of data within K standard deviations are typically larger than the estimates given by Chebyshev’s Inequality.
Exercises
Exercise 1:
Context: A data set has a population mean of 20 and a standard deviation of 3.
Question 1: Is it appropriate to use the Empirical Rule to approximate the proportion of data between 14 and 26? Why or why not?
Exercise 2:
Context: A data set has a mean of 50 and a standard deviation of 8.
Question 2: Is it appropriate to use the Empirical Rule to approximate the proportion of data between 42 and 58? Why or why not?
Exercise 3:
Context: Assume a sample comes from population data with a bell-shaped histogram; sample mean is 120 and sample standard deviation is 8.
Questions:
Label the distribution according to the Empirical Rule.
What are the cut-off values for the middle 95%?
What percent of the values are between 112 and 128?