Frequency and Central Tendency
Frequency and Central Tendency
Organizing Data
Summarizing Data
Simplifies and organizes data for clarity.
Visual representation of data can be done using tables or graphs.
Frequency and Frequency Distribution
Frequency
Refers to the number of times a category occurs.
Example: Counting the number of siblings in a survey.
Expressed as frequency (t) for ungrouped data.
Ungrouped Data
Represents discrete range values where the frequency of scores can be clearly seen.
Provides an insight into the "raw data" of the dataset.
Grouped Data
Involves distributing a set of scores into intervals rather than showing individual scores.
Simplifies and modifies the raw data into grouped ranges where precise values may be obscured.
Steps to Create a Frequency Distribution from Grouped Data
Find the Real Range:
Using the formula:
ext{Real Range} = ext{max} - ext{min} + 1
Find the Interval Width:
Divide the real range by the number of intervals proposed.
Round the quotient to the nearest whole number for convenience.
Construct the Frequency Distribution Table:
Create a table with the calculated intervals, based on the number determined in Step 2.
Example Calculations:
Real Range:
Max Score:
Max = 99
Min Score:
Min = 66
Calculation: 99 - 66 + 1 = 34
Interval Width:
With 5 intervals:
ext{Interval Width} = rac{34}{5} = 6.857
ightarrow 7 rounded to nearest whole.
Construct a Frequency Table:
Example Intervals:
93 - 99
86 - 92
Characteristics of the Mean
Effect of Changing an Existing Score on the Mean:
Altering any score will adjust the mean towards the direction of the new score.
Example:
Initial Scores: 8, 9, 5, 5, 5, 10, 6, 8 = 56.
New Score: 9, 9, 5, 5, 5, 10, 6, 8 = 57.
Mean change calculation: ext{Mean} = rac{57}{8} = 7.125.
Adding or Removing a Score:
The mean will change unless the added/removed value equals the current mean.
Example Wait on Mean:
Original Mean = 4.56
With Values: 4, 5, 6 -> Mean = 5
Adjustment Examples:
4 + 5 + 6 + 6 = rac{21}{4} = 5.25
4 + 5 + 6 + 4 = rac{19}{4} = 4.75
Applying Operations to Each Score:
Adding, subtracting, multiplying or dividing all scores by a constant will cause the mean to be adjusted by that constant directly.
Example with Extra Credit:
Test Scores: 70, 75, 80, 80, 85, 90, 80 -> new mean reflects this adjustment.
Balance Point of the Mean:
The sum of differences of scores from the mean is zero.
ext{Sum} "(X - M)= 0
Specific Example: {4, 5, 6}
Calculation of differences:
$4 - 5 = -1$
$5 - 5 = 0$
$6 - 5 = 1$
Minimizing Squared Differences:
The sum of the squared differences of scores from their mean is minimized.
Formula: ext{Sum}ig((X - M)^2ig)
Example Calculation:
Deviation:
$(4 - 5)^2 = (-1)^2 = 1$
$(6 - 5)^2 = (1)^2 = 1$
Median
Definition:
The median is the middle value in a range of data points arranged in numerical order.
Signifies the midpoint where half the dataset lies above, and half lies below.
It is not influenced by outliers.
Calculation Based on the Position
Median Position Formula: rac{n + 1}{2}
Even vs. Odd Sets Calculation:
For Odd: Simply take the middle value.
For Even: Average of the two middle values.
Example: Set {99, 66, 44, 13, 8} sorted = {8, 13, 44, 66, 99}:
Median = 44 (position $[5 + 1]/2 = 3$)
For {66, 44}: Calculation for Median = rac{(66 + 44)}{2} = 55.
Mode
Definition:
The mode is the most frequently occurring value in a dataset.
It is essential to list the data values in numerical order and count occurrences.
Calculation of Mode
Example: From the set {2, 3, 3, 3, 3, 4, 4, 4, 4, 4, 5, 5, 5, 6, 7}:
Mode = 4 (occurs most often).
Distribution Characteristics
It is possible to have multiple modes:
Unimodal: one mode
Bimodal: two modes
Multimodal: more than two modes.
Reporting Mean, Median, and Mode in Distributions
Normal Distribution:
The mean includes all scores in calculation.
Skewed Distributions:
Use median as it is not influenced by outliers.
Ordinal Scale Data:
Mode is reported for modal distributions.