Chapter 2.75 Methods Statistics
Chapter 2: Research Methods: Statistics
Measures of Variability
Measures of variability describe the difference and spread within a dataset.
They are part of descriptive statistics and include:
Range
Variance
Standard Deviation
Range
The range is calculated as the difference between the highest and lowest scores in a distribution.
Example 1: If the highest score is 75 and the lowest score is 25, the range is 75 - 25 = 50.
Example 2: For scores 10 and 1, the range is 10 - 1 = 9.
Variance
Variance measures how much scores differ from the mean (average).
Understand variance as the dispersion of data points from the mean due to various chance factors.
Calculating Variance
Formula for sample variance:[ s^2 = \frac{\Sigma (x - \bar{x})^2}{n - 1} ]
Where:
( s^2 ) = variance
( \Sigma ) = sum of squared deviations
( x ) = individual score
( \bar{x} ) = mean
( n ) = number of scores
Example of Variance Calculation
Scores: {2, 3, 4, 5, 6}
Mean: (2 + 3 + 4 + 5 + 6) / 5 = 4
Calculating Differences from the Mean:
(2 - 4) = -2 → (-2)² = 4
(3 - 4) = -1 → (-1)² = 1
(4 - 4) = 0 → (0)² = 0
(5 - 4) = 1 → (1)² = 1
(6 - 4) = 2 → (2)² = 4
Sum of Squared Deviations: 4 + 1 + 0 + 1 + 4 = 10
Variance Calculation:( s^2 = \frac{10}{4} = 2.5 )
Standard Deviation
Reflects how tightly data values cluster around the mean.
A small standard deviation indicates that values are close to the mean, while a large standard deviation indicates they are spread out.
Calculating Standard Deviation
Formula:[ S = \sqrt{s^2} = \sqrt{\frac{\Sigma(x - \bar{x})^2}{n - 1}} ]
Standard deviation is the square root of the variance.
Standard Deviation Example
ABC School: Mean GPA = 70%, SD = 4.
DEF School: Mean GPA = 70%, SD = 28.
Decision on funding: ABC School should get more funding due to lower variability (SD of 4).
Properties of Normal Distribution
The normal distribution is bell-shaped with specific characteristics:
About 68% of scores lie within ±1 SD.
Approximately 95% lie within ±2 SD.
Roughly 99% lie within ±3 SD.
Z Scores
Z-scores quantify how many standard deviations a score is from the mean.
Percentile Ranking: Indicates score distribution relative to others (e.g., someone at the 90th percentile performed better than 90% of test takers).
Statistical Significance
Pertains to hypothesis testing; used to validate hypotheses against observed data.
Denoted by ( \alpha ) (alpha), usually set at 0.05 (5%).
Determine support for hypotheses using the p-value:
If p-value ≤ α, hypothesis is supported.
If p-value > α, null hypothesis is supported.
Inferential Statistics
These methods compare sample data to population data, allowing findings from samples to be generalized.
Example: A study on clothing's impact on popularity uses inferential statistics for broader conclusions.
Visual Representation of Normal Distribution
Demonstrates standard deviations and cumulative percentages across normal distribution range.
Shows data distribution where the mean divides data into symmetrical halves.