Measures of Central Tendency
Definition Measures of Central Tendency (Mean, Median, Mode)
Central Tendency Refers to a characteristic where the frequency of a variable tends to cluster around the ‘center’
Measures of Central Tendency Arithmetic Mean Median Mode
Arithmetic Mean Data (units produced by workers) 10, 20, 30 Mean = Ungrouped data (1) =20
Arithmetic Mean Data (units produced by workers) 10, 20, 20, 25, 25, 25, 25, 30, 30, 50, 50, 50 Ungrouped data (2) Units (x)Worker(f) Total fx
Arithmetic Mean Data (units produced by workers) 12, 24, 24, 25, 25, 25, 25, 32, 32, 45, 45, 45 Grouped data UnitsWorker(f) 10 – – – – 503 Total Midpoint(m) fm
Arithmetic Mean Ungrouped data Grouped data
Features of Arithmetic Mean Commonly used Easily understood Greatly affected by extreme values
Median 1. Array 2. Median position 3. median
Median Data (units produced by workers) 20, 10, 30 (odd) Ungrouped data (1) ① Array 10, 20, 30 ② Median position ③ Median 20
Median Data (units produced by workers) 20, 10, 40, 30 (even) Ungrouped data (1) ① Array 10, 20, 30, 40 ② Median position ② Median
Median Data (units produced by workers) 10, 20, 20, 25, 25, 25, 25, 30, 30, 50, 50, 50 Median position= Ungrouped data (2) Units (x)Worker(f) Total12 25 unitsMedian= c.f
Median Data (units produced by workers) 12, 24, 24, 25, 25, 25, 25, 32, 32, 45, 45, 45 Median = Grouped data (2) UnitsWorker(f) 10 – – – – 503 Total12 Median position = Median Class = c.f
Median Ungrouped data Grouped data
Features of Median Not affected by extreme values When data is skewed, the median is often a better indicator of “average” than the mean. Time consuming Unfamiliar to most people
Mode Data (units produced by workers) 10, 20, 20, 30 Mode = Ungrouped data (1) 20
Mode Data (units produced by workers) 10, 20, 20, 25, 25, 25, 25, 30, 30, 50, 50, 50 Ungrouped data (2) Units (x)Worker(f) Total12 Mode = 25
Mode Data (units produced by workers) 12, 24, 24, 25, 25, 25, 25, 32, 32, 45, 45, 45 Mode = Grouped data (2) UnitsWorker(f) 10 – – – – 503 Total12 The highest frequency: Modal group= units
Mode Ungrouped data Grouped data Data with the highest frequency
Features of Mode Not affected by extreme values May be more than one mode, or no mode May not give a good indication of central values
Skewness of Data Distribution Normal Mode = mean =median
Skewness of Data Distribution Positively skewed Mode < median< mean
Skewness of Data Distribution Negatively skewed Mean < median< mode
Arithmetic Mean ungrouped data grouped data
Median ungrouped data grouped data
Mode ungrouped data grouped data Data with the highest frequency
Measures of Dispersion
Definition Measures of Dispersion(Range, Quartile Deviation, Mean Deviation, Standard Deviation, Variance, Coefficient of Variation)
Dispersion It describes the level of variation and also indicates the level of consistency in the distribution.
Measures of Dispersion Range Quartile Deviation Mean Deviation Standard Deviation Variance Coefficient of Variation
Range It measures the difference between the highest and the lowest piece of data. Data1: Data2: 10, 20, 30 0, 20, 40 Range1 = x max – x min = = 20 Range2 = x max – x min = = 40
Feature It is easy to calculate and easy to understand. It is distorted by extreme values.
Quartile Deviation 1. Array 2. Quartile position 3. Quartile Value 4. IQR,QD
Quartile Deviation It excludes the first and last quarters of information and in doing so concentrates on the main core of data, ignoring extreme values Q1Q2Q3 Interquartile Range = Q 3 - Q1 Quartile Deviation =
Quartile Deviation (ungrouped) Q 1 position= Q 3 position= Q 1 value= Q 3 value=
Grouped data
Amount Spent ($)Number of Staff Total13 c. f
Amount Spent ($)Number of Staff Total13 c. f
Amount Spent ($)Number of Staff Total13 c. f
Amount Spent ($)Number of Staff Total13 c. f
Amount Spent ($)Number of Staff Total13 c. f.
Feature Not effected by extreme values. Not widely used or understood.
Quartile Deviation Q 1 = Q 3 = Ungrouped: I.Q.R= Q 3 value- Q 1 value Quartile Deviation =
Quartile Deviation Q 1 = Q 3 = Grouped: I.Q.R= Q 3 value- Q 1 value Quartile Deviation =
Mean Deviation The absolute distance of each score away from the mean.
Mean Deviation Ungrouped data
Mean Deviation Ungrouped data Team 1: Team 2:
Mean Deviation Ungrouped data Team 1: Team 2:
Mean Deviation Ungrouped data Team 1: Team 2:
Mean Deviation Ungrouped data Team 1: Team 2: M.D. 1 = 2 M.D. 2 =6.4
Mean Deviation Grouped data
UnitsMidpoint(m)Worker(f)fmf|m – | Total ,
Mean Deviation Grouped data Ungrouped data
Standard Deviation/Variance Ungrouped data
Standard Deviation/Variance Ungrouped data Team 1: Team 2:
Standard Deviation/Variance Ungrouped data Team 1: Team 2:
Standard Deviation/Variance Ungrouped data Team 1: Team 2:
Standard Deviation/Variance Ungrouped data Team 1: Team 2:
Standard Deviation (Variance) Grouped data
Units (x) Worker (f) Total Midpoint (m) fm , , ,200 4,450
UnitsMidpoint (m) Worker (f) fmf(m – ) , ,815 Total-502,2004,450
Standard Deviation/Variance Ungrouped data
Standard Deviation (Variance) Grouped data
Coefficient of Variation
Coefficient of Variation (100 Students) Height: Weight: Height C.V.: Weight C.V.: Weight is more variant than Height.
Population & sample