02 - Descriptive Statistics (continued)

Introduction to Descriptive Statistics

Arithmetic Mean: Usually referred to as the average.
- Calculation: Sum of all data points divided by the number of points (denoted as x̄ for sample mean).
- Example: For dataset {2, 5, 5, 6}, arithmetic mean = (2 + 5 + 5 + 6) / 4 = 4.5.
Median: The middle point of a dataset.
- Finding the median:
  - Sort the data.
  - If odd number of points, the median is the middle point.
  - If even number, average the two middle points.
- Example: For dataset {5, 7, 2, 3, 1, 3, 2, 1}, sorted = {1, 1, 2, 2, 3, 3, 5, 7}, median = (2+2)/2 = 2.5.
Mode: The most frequently occurring data point.
- Can be used for categorical data (e.g., colors) where mean and median do not apply.
- Example: In {5, 5, 2, 2, 3, 7, 3}, modes are 2 and 5 (bimodal).

Outliers: Data points that lie far from other points; their identification can be subjective.
Affected Measures:
- Arithmetic mean is sensitive to outliers.
- Median usually remains unchanged.
- Mode often remains unchanged or can be ambiguous.
Example: Adding outlier (177) affects the arithmetic mean significantly but has little effect on median and mode.
- Mean changed considerably, while median changed slightly (9 to 9.5).

Geometric Mean: Used for rates of growth (e.g., finance).
- Example: For percentages like 2%, 3%, 13%, the geometric mean gives a more accurate average rate of return over time.
Harmonic Mean: Used in scenarios involving rates, such as speed.
- Example: Traveling at 40 mph to a point, returning at 80 mph results in an effective average speed of 53.33 mph rather than simple averaging.

Arithmetic mean: Balance point of the distribution.
Median: Splits dataset into two equal halves.
Mode: Highest peak in the data distribution.
In symmetric distributions, mean = median.
In skewed distributions, the mean pulls toward the tail, while the median remains more stable.

Definition: Arithmetic mean but accounts for different frequencies of data points.
Example: Survey of exercise hours needs adjustment for varying responses to achieve accurate overall average.
Weighted average takes into account how many times each response occurred.

Standard Deviation: Measures how spread out data points are around the mean.
Variance: The square of the standard deviation, helps in understanding the dispersion.
Key Notation:
- Sample standard deviation: s
- Population standard deviation: σ
Relationship between variance and standard deviation explored and understood conceptually.

Quartiles: Divide the dataset into four equal parts.
- Q1: 25% mark, Q2: median (50% mark), Q3: 75% mark.
Interquartile Range (IQR): Q3 - Q1, measures the middle 50% of the data.
Outlier identification: Points outside 1.5 times the IQR from Q1 or Q3 are considered outliers.

Standardizing: Converting data into standard deviations.
Z-score: Indicates how many standard deviations an element is from the mean.
Formula: z = (X - μ) / σ, where X is the individual data point, μ is the mean, and σ is the standard deviation.
Z-scores help in comparing different datasets statistically.
Rule of Thumb:
- 1 standard deviation: considered close.
- 2 standard deviations: considered far.
- 3+ standard deviations: very far.

Examples demonstrated throughout the video to reinforce concepts with applications in real-world statistics.
Emphasis on using tools like calculators for calculations involving standard deviation and z-scores.