8.3 Measures of Central Tendency & Data Spread

8.3 Measures of Central Tendency & Data Spread

Quick Summary: Summarizing quantitative distributions requires understanding measures of center and variation. This section defines the arithmetic mean, median, mode, and range, evaluates the impact of outliers on mean versus median across skewed distributions, introduces algebraic techniques to solve missing value problems from a given mean, and explains weighted average calculations used in Ontario grading systems.

---

Measures of Central Tendency

Measures of central tendency identify a single central numerical value that summarizes an entire dataset.

1. Arithmetic Mean ($\bar{x}$)

The mean is the numerical average obtained by summing all data values and dividing by the total count $n$.

$$\bar{x} = \frac{\sum_{i=1}^{n} x_i}{n} = \frac{x_1 + x_2 + \dots + x_n}{n}$$

• Key Characteristic: Uses every single data point in its calculation; however, it is highly sensitive to extreme outliers.

2. Median ($M$)

The median is the physical middle value of a dataset when the data points are arranged in ascending or descending numerical order.

• Algorithm to Find Median:
  1. Order all $n$ data values from smallest to largest.
  2. If $n$ is odd: The median is the single middle value located at position $\frac{n + 1}{2}$.
  3. If $n$ is even: The median is the arithmetic average of the two middle values located at positions $\frac{n}{2}$ and $\frac{n}{2} + 1$.
• Key Characteristic: Resistant / Robust to extreme outliers because its value depends solely on order position rather than numerical magnitude.

3. Mode

The mode is the data value (or values) that occurs with the highest frequency in a dataset.

• A dataset can be unimodal (one mode), bimodal (two modes), multimodal (three or more modes), or have no mode (if all values occur equally).
• Key Characteristic: The only measure of central tendency that can be used for nominal categorical data (e.g., most popular elective subject).

---

Measures of Data Spread: Range

The range measures the total numerical boundary spread of a dataset.

$$\text{Range} = x_{\text{maximum}} - x_{\text{minimum}}$$

• Limitation: Like the mean, the range is calculated using only the two extreme values ($x_{\max}$ and $x_{\min}$), making it extremely vulnerable to distortion by outliers.

---

Impact of Outliers & Distribution Skewness

An outlier is an extreme observation that lies an abnormal distance from other values in a dataset.

Loading diagram...

1. Symmetric Distributions

When data is symmetrically distributed around a central peak (e.g., standard bell curve):

$$\text{Mean} \approx \text{Median} \approx \text{Mode}$$

Both the mean and median serve as accurate measures of central tendency.

2. Positively Skewed (Right-Skewed) Distributions

Data contains a cluster of lower values on the left with a long tail extending toward high values on the right (or a high positive outlier).

• Outlier Effect: High extreme values pull the mean upward to the right, while the median remains stable near the physical middle.

$$\text{Mean} > \text{Median}$$

• Best Measure of Center: Median (since the mean is falsely inflated).

3. Negatively Skewed (Left-Skewed) Distributions

Data contains a cluster of higher values on the right with a long tail extending toward low values on the left (or a low negative outlier, such as a zero on a test).

• Outlier Effect: Low extreme values pull the mean downward to the left.

$$\text{Mean} < \text{Median}$$

• Best Measure of Center: Median.

---

Algebraic Reasoning Backwards from a Given Mean

Many Ontario MPT problems require candidates to reason backwards from a known arithmetic mean to determine a missing individual value or score.

Core Algebraic Principle

From the definition of mean $\bar{x} = \frac{\text{Total Sum}}{n}$, the Total Sum of all values is equal to the product of the number of items $n$ and the mean $\bar{x}$:

$$\text{Total Sum} = n \times \bar{x}$$

Step-by-Step Method for Missing Values:

1. Multiply the total count of items ($n_{\text{total}}$) by the target mean ($\bar{x}_{\text{target}}$) to find the Required Total Sum.
2. Sum all known existing data values to find the Existing Sum.
3. Subtract the Existing Sum from the Required Total Sum: $$\text{Missing Value} = (n_{\text{total}} \times \bar{x}_{\text{target}}) - \sum x_{\text{known}}$$

---

Weighted Mean Calculations

When data values carry different relative importances, weights, or percentages (as in Ontario school assessment categories), a weighted mean must be used.

Weighted Mean Formula

$$\bar{x}_w = \frac{\sum_{i=1}^{k} (w_i \cdot x_i)}{\sum_{i=1}^{k} w_i} = \frac{w_1 x_1 + w_2 x_2 + \dots + w_k x_k}{w_1 + w_2 + \dots + w_k}$$

where $x_i$ represents each grade or score, and $w_i$ represents its corresponding weight (as a percentage or decimal weight).

Ontario Course Grading Example:

In accordance with Ontario Growing Success assessment policies, secondary courses are weighted as:

• Term Coursework: $70\%$ ($w_1 = 0.70$)
• Final Culminating / Exam: $30\%$ ($w_2 = 0.30$)

$$\text{Final Grade} = (0.70 \times \text{Term Mark}) + (0.30 \times \text{Final Exam Mark})$$

---

Comprehensive Worked Central Tendency & Missing Value Problems

Problem 1: Missing Test Score Calculation A student has completed 4 out of 5 math unit tests in a semester, achieving marks of $74\%$, $82\%$, $68\%$, and $88\%$. The student aims to earn an overall mean of $80\%$ across all 5 tests.

1. Calculate the mark required on the 5th test to reach an $80\%$ mean.
2. If the maximum possible mark on test 5 is $100\%$, what is the maximum overall mean this student could possibly achieve?

Problem 2: Outlier Impact & Weighted Grade Calculation An Ontario Grade 10 student receives the following strand assessment marks:

• Knowledge & Understanding (Weight $30\%$): $85\%$
• Application (Weight $30\%$): $75\%$
• Communication (Weight $20\%$): $90\%$
• Thinking & Inquiry (Weight $20\%$): $60\%$

Calculated overall term mark = $78.0\%$. For the final evaluation (counting for $30\%$ of the final grade), the student scores $88\%$.

1. Calculate the final overall course mark using the weighted mean.
2. Analyze how a single extreme zero score ($0\%$) on a missed $10\%$ assignment affects the unweighted mean versus median of a 5-assignment set: $\{80, 82, 85, 88, 0\}$.

---

Step-by-Step Solution:

1. Step 1: Solve Missing Test Score Problem

   • Target number of tests $n = 5$. Target mean $\bar{x} = 80\%$.
   • Required total sum = $5 \times 80 = 400$ marks.
   • Sum of first 4 tests = $74 + 82 + 68 + 88 = 312$ marks.
   • Required 5th test mark = $400 - 312 = 88\%$.
   • Check: $\frac{74 + 82 + 68 + 88 + 88}{5} = \frac{400}{5} = 80\%$ (Correct).

2. Step 2: Calculate Maximum Possible Mean

   • If the student scores $100\%$ on the 5th test, total sum = $312 + 100 = 412$.
   • Maximum possible mean = $\frac{412}{5} = 82.4\%$.

3. Step 3: Calculate Weighted Final Course Mark

   • Term Mark = $78.0\%$ (Weight $70\% = 0.70$).
   • Final Exam = $88.0\%$ (Weight $30\% = 0.30$).
   • Apply Weighted Mean Formula: $$\text{Final Grade} = (0.70 \times 78.0) + (0.30 \times 88.0) = 54.6 + 26.4 = 81.0\%$$

4. Step 4: Analyze Outlier Effect on Unweighted Mean vs. Median

   • Given dataset with zero outlier: $\{0, 80, 82, 85, 88\}$ ($n = 5$).
   • Unweighted Mean: $$\bar{x} = \frac{0 + 80 + 82 + 85 + 88}{5} = \frac{335}{5} = 67.0\%$$
   • Median: Data ordered = $\{0, 80, \mathbf{82}, 85, 88\}$. Physical middle value ($3^{\text{rd}}$ position) = $82.0\%$.
   • Comparison: The single zero score pulls the mean down severely from $83.75\%$ (without zero) to $67.0\%$ (a drop of $16.75\%$). However, the median only drops from $83.5\%$ to $82.0\%$ (a minor drop of $1.5\%$), demonstrating the median's robustness against outliers.