Mean: Sum of all values divided by the number of values
Formula: x̄ = (Σx)/n where Σx is the sum of all values and n is the number of values
Symbol: x̄ (x-bar) for sample mean, μ (mu) for population mean
- Add all values: Sum all data points
- Count values: Determine how many data points there are
- Divide: Divide the sum by the count
- Round if necessary: Follow specified precision requirements
List all numbers in the dataset
Add all values together: 5 + 7 + 9 + 11 = 32
Count how many numbers there are: n = 4
Mean = 32 ÷ 4 = 8
• Affected by all values in the dataset
• Influenced by outliers (extreme values)
• Balancing point of the distribution
• May not be an actual data value
• Sum all values: Include every data point in the sum
• Count accurately: Ensure correct number of data points
• Division: Always divide by the count of values
• Outlier sensitivity: Extreme values significantly affect the mean
Median: Middle value in ordered dataset
Odd count: Middle value is at position (n+1)/2
Even count: Average of values at positions n/2 and (n/2)+1
Sort values from least to greatest
Determine if count is odd or even
For odd: (n+1)/2, For even: average of n/2 and (n/2)+1
For odd: value at middle position, For even: average of two middle values
• Resistant to outliers
• Always a data value (for odd count) or average of two values
• Divides data into two equal halves
• Requires ordered data
• Always order first: Never find median of unordered data
• Odd vs even: Different procedures for each case
• Outlier resistance: Less affected by extreme values
Mode: Value that occurs most frequently in the dataset
Unimodal: One mode
Bimodal: Two modes
Multi-modal: More than two modes
No mode: All values appear equally often
Identify each distinct value in the dataset
How many times does each value appear?
What is the maximum number of occurrences?
These are the modes of the dataset
• May not exist if all values appear equally
• Can have multiple modes
• Always a data value
• Unaffected by outliers
• Frequency counting: Tally occurrences of each value
• Multiple modes: List all values with maximum frequency
• No mode: When all values appear the same number of times
Mean: Best for normally distributed data without outliers
Median: Best for skewed data or data with outliers
Mode: Best for categorical data or identifying most common value
Context matters: Choose measure based on data type and purpose
- Analyze data distribution: Look for skewness or outliers
- Consider data type: Categorical vs numerical
- Determine purpose: What are you trying to measure?
- Select appropriate measure: Based on distribution and purpose
- Calculate measure: Use correct procedure
- Interpret results: Consider context and implications
Test scores: 85, 92, 78, 85, 90, 78, 85, 92, 88, 78, 90, 85
Arrange in ascending order: 78, 78, 78, 85, 85, 85, 85, 85, 88, 90, 90, 92, 92
Sum = 78 + 78 + 78 + 85 + 85 + 85 + 85 + 85 + 88 + 90 + 90 + 92 + 92 = 1044
Count = 13
Mean = 1044 ÷ 13 ≈ 80.3
With 13 values (odd), median is the 7th value (position (13+1)/2 = 7)
7th value = 85
Count frequencies: 78 appears 3 times, 85 appears 5 times, 88 appears 1 time, 90 appears 2 times, 92 appears 2 times
Mode = 85 (highest frequency)
• Mean (80.3) is lower than median (85) due to lower scores
• Median represents typical performance
• Mode shows most common score
• Skewness: Mean < Median suggests slight left skew
• Mode frequency: Appears 5 times out of 13
• Central tendency: All measures cluster around 80-85
Salary data with potential outlier: 35, 38, 42, 45, 48, 50, 150
Notice the value 150 is much higher than others (potential outlier)
Sum = 35 + 38 + 42 + 45 + 48 + 50 + 150 = 408
Mean = 408 ÷ 7 ≈ 58.3 thousand dollars
With 7 values, median is the 4th value = 45 thousand dollars
All values appear once, so no mode exists
Mean (58.3) > Median (45) due to the outlier (150)
Median better represents typical salary as it's not influenced by the CEO's salary
• Use median (45) as it's resistant to the outlier
• Mean (58.3) is inflated by the CEO's salary
• For typical employee salary, median is more representative
• Outliers present: Use median over mean
• Normal distribution: Mean is typically most appropriate
• Skewed data: Median better represents center
Mean: Arithmetic average of all values in a dataset
Median: Middle value when data is arranged in order
Mode: Value that appears most frequently in the dataset
Central tendency: Statistical measures that represent the center of a data distribution
- Mean: Add all values and divide by the count
- Median: Arrange data in order and find middle value(s)
- Mode: Identify the most frequently occurring value(s)
- Range: Difference between maximum and minimum values
- Selection: Choose appropriate measure based on data characteristics
• Mean formula: x̄ = (Σx)/n
• Median position: For n values: (n+1)/2 if odd, average of n/2 and (n/2)+1 if even
• Mode: Value(s) with highest frequency
• Outlier effect: Mean > Median in right-skewed data
• Data type: Mean and median for numerical data, mode for any data type