Measures of Dispersion/Variability | Range, Variance, Standard Deviation | Statistics for Beginners
Introduction
In this video, the speaker talks about measures of dispersion or variability and why they are important in describing a set of data.
Measures of Dispersion or Variability
- Dispersion refers to how similar or different data points are in a set.
- Three common measures of dispersion are range, variance, and standard deviation.
- Measures of central tendency (such as mean) do not provide information on the spread of data points.
- Two sets of data can have the same mean but different levels of variability.
Range
- The range is the difference between the highest and lowest values in a dataset.
- The range is not commonly used because it only provides a rough estimate of variability.
Variance
- Variance is a more commonly used measure of dispersion that provides a more accurate estimate than range.
- Population variance is used when computing from an entire population.
Measures of Dispersion
In this section, the speaker discusses the three measures of dispersion or variability: range, variance, and standard deviation. The speaker explains how to compute each measure and provides examples.
Population Variance vs Sample Variance
- The formula for computing population variance is almost the same as that for computing sample variance.
- The major difference between the two is the denominator. For population variance, it's "n" (number of observations), while for sample variance, it's "n-1".
- When computing summation notations, "summation of x" means summing all data points in a population. "Summation of x squared" means squaring each data point before taking the sum.
Example Computation
- To illustrate how to compute sample variance, an example is given using scores from 12 students.
- First, compute the sum of all data points in the sample.
- Answer: 470
- Next, compute the sum of squared observations.
- Answer: 19668
- Substitute these values into the formula for sample variance.
- Denominator: 12 - 1 = 11
- Answer: 114.52 (approx.)
Standard Deviation
- Standard deviation is another measure of dispersion/variability.
- It's related to variance by taking its square root.
- To compute standard deviation from a given set of data points:
- Compute its variance first using either population or sample formula.
- Take its square root to get standard deviation.
Example Computation Continued
- Using the previous example computation where we got a sample variance value of 114.52:
- Answer: 10.70