CH4-2300

Chapter 4: Variability

Learning Outcomes

• Understand purpose of measuring variability

• Define range and interquartile range

• Compute range and interquartile range

• Understand standard deviation

• Calculate SS, variance, standard deviation of population

• Calculate SS, variance, standard deviation of sample

Review Concepts

• Summation notation (Referenced in Chapter 1)

• Central tendency (Referenced in Chapter 3)

  • Mean

  • Median

Overview of Variability

• Variability Definition:

  • Quantitative measure of differences between scores.

  • Indicates how scores are spread out or clustered together.

• Purposes of Measuring Variability:

  • Describe the distribution.

  • Measure how well an individual score represents the distribution.

Measures of Variability

• The Range:

  • Distance between smallest and largest values in a dataset.

  • Crude and unreliable measure of variability.

• The Standard Deviation:

  • Most common and important measure of variability.

  • Indicates average distance from the mean.

• The Variance:

  • Average of the squared deviations from the mean.

Details on the Range

• Calculation of the Range:

  • For continuous data, use real limits.

  • Formula: range = URL for Xmax - LRL for Xmin.

Standard Deviation and Variance for a Population

• Standard Deviation:

  • Measure of the average distance of scores from the mean.

  • Calculation varies between population and sample.

• Steps to Calculate Standard Deviation:

  1. Deviation from Mean: Calculate the distance each score is from the mean (X - μ).

  2. Mean of Deviations: Deviations sum to 0, so a different measure is needed.

  3. Square Deviations: Square each deviation to eliminate negative signs.

  4. Compute Variance: Find the average of squared deviations (variance).

  5. Standard Deviation: Take the square root of variance to find the standard deviation.

Population Variance and Standard Deviation Formulas

• SS (Sum of Squares):

  • Sum of the squared deviations from the mean.

  • Two formulas for calculating:

    • Definitional Formula:

      • Find each deviation score (X - μ), square each, and sum.

    • Computational Formula:

      • Square each score and sum, then adjust using the sum of scores squared divided by N.

• Population Variance Notation:

  • Denoted by σ (lowercase Greek letter sigma).

  • Variance formula: σ² = average of squared deviations.

Sample Variance and Standard Deviation

• Sample Calculation Differences:

  • Sample variance uses n-1 instead of N in the denominator (n = sample size).

  • Notation for sample standard deviation uses s instead of σ.

Degrees of Freedom

• Definition: Number of independent scores in the sample that can vary.

• Population Variance: Known mean, deviations from this mean.

• Sample Variance: Estimate produces a need to account for reduced variability; df = n - 1.

Biased vs. Unbiased Estimates

• Unbiased Estimate: Average of statistic equals population parameter.

• Biased Estimate: Systematic over or underestimation of the population parameter.

Transformations of Scale

• Adding a Constant: Changes mean, leaves standard deviation unchanged.

• Multiplying by a Constant: Changes both mean and standard deviation by that constant.

Variability and Inferential Statistics

• Goal of Inferential Statistics: Detect meaningful patterns in data.

• Effect of Variability: High variability can obscure patterns; termed error variance.

Learning Checks (With Answers)

• True/False Statements and explanations provided for deeper understanding of variability concepts.

Figures

• Include visual aids illustrating concepts such as population distributions, frequency distributions, variances, and examples of data spread.

Additional Learning Checks

• Students can assess understanding through True/False statements regarding variability, its impact, and calculations.