14.1 Reading and Interpreting Histograms, Circle Graphs, Scatterplots, and Two-Way Tables

14.1 Reading and Interpreting Histograms, Circle Graphs, Scatterplots, and Two-Way Tables

Probability, Statistics, and Data Interpretation constitutes Competency 4 of the Florida Teacher Certification Examinations (FTCE) General Knowledge Test (082) Subtest 4: Mathematics (828), accounting for approximately 20% of the overall mathematics items. Within this domain, Competency 4.1 assesses an educator's capacity to read, analyze, and extract actionable conclusions from diverse graphical representations of data. On the examination, items evaluate whether candidates can translate raw visual displays into precise numerical quantities, compute relative and conditional frequencies, and recognize underlying structural patterns.

---

Frequency Distributions and Continuous Histograms

A frequency distribution summarizes how often individual numerical values or interval categories occur within a dataset. When data are grouped into numeric intervals, the frequency ($f$) represents the count of observations falling within each interval bin, while the relative frequency expresses each count as a proportion or percentage of the total sample size ($n$):

$$\text{Relative Frequency} = \frac{f}{n}$$

Distinguishing Histograms from Categorical Bar Graphs

A fundamental conceptual distinction tested on the FTCE is the difference between a histogram and a bar graph:

          BAR GRAPH (Categorical)                 HISTOGRAM (Continuous Numerical)
     Frequency                               Frequency
        ▲                                       ▲
     20 │   ┌───┐       ┌───┐                20 │       ┌───┐
     15 │   │   │ ┌───┐ │   │                15 │   ┌───┤   ├───┐
     10 │   │   │ │   │ │   │                10 │   │   │   │   │ ┌───┐
      5 │   │   │ │   │ │   │                 5 │ ┌─┤   │   │   │ │   │
        └───┴───┴─┴───┴─┴───┴──►                └───┴─┴───┴───┴───┴─┴───┴──►
             Art  Music Drama                       0  10  20  30  40  50
              (Spaces Between)                         (Touching Bins)

Reading Bins and Boundary Conventions

In a histogram, each bar spans an interval bin $[a, b)$. By mathematical convention, a value falling exactly on a boundary belongs to the upper bin (or lower bin, depending on the explicitly defined interval rule). To find the total number of observations, sum the heights of all bars across the histogram:

$$n = \sum_{i=1}^{k} f_i$$

Worked Example: Score Range Analysis

A high school department administers a 100-point reading benchmark. The score distribution for 80 students is grouped into bins of width 10:

• $[50, 60)$: 8 students
• $[60, 70)$: 16 students
• $[70, 80)$: 28 students
• $[80, 90)$: 20 students
• $[90, 100]$: 8 students

To determine what percentage of students scored at least 70:

• Step 1: Sum frequencies for intervals meeting the condition $(\ge 70)$: $28 + 20 + 8 = 56$ students.
• Step 2: Divide by total sample size: $\frac{56}{80} = 0.70$.
• Step 3: Convert to percentage: $0.70 \times 100\% = 70\%$. Exactly $70\%$ of the cohort scored at or above 70.

---

Circle Graphs (Pie Charts) and Sector Angles

A circle graph (or pie chart) visualizes how a whole entity ($100\%$) is divided into proportional categories. The total angular measure of a circle is strictly $360^\circ$. Consequently, every individual sector angle is proportional to its percentage share of the whole:

$$\text{Central Sector Angle } (\theta) = \frac{\text{Category Quantity}}{\text{Total Quantity}} \times 360^\circ = \text{Percentage} \times 3.6^\circ$$

Because $100\% = 360^\circ$, each $1\%$ of the distribution corresponds precisely to $3.6^\circ$:

• A $25\%$ quadrant subtends $0.25 \times 360^\circ = 90^\circ$.
• A $10\%$ slice subtends $0.10 \times 360^\circ = 36^\circ$.
• A $5\%$ slice subtends $0.05 \times 360^\circ = 18^\circ$.

                                CIRCLE GRAPH SECTOR ANGLES
                                      100% = 360°
                                       1% = 3.6°
                                         ┌───┐
                                    25%  │ 90°│  (0.25 × 360°)
                                    50%  │180°│  (0.50 × 360°)
                                    10%  │ 36°│  (0.10 × 360°)
                                     5%  │ 18°│  (0.05 × 360°)
                                         └───┘

Worked Example: Budget Sector Determination

A district school board allocates a total capital outlay budget of $\$18,000,000$. On an informational circular graphic, the sector representing Technology Infrastructure measures an angle of $54^\circ$. What dollar amount is allocated to Technology Infrastructure?

• Step 1: Calculate the proportional share represented by $54^\circ$: $$\text{Proportion} = \frac{54^\circ}{360^\circ} = 0.15 = 15\%$$
• Step 2: Multiply the proportion by the total budget: $$\text{Expenditure} = 0.15 \times \$18,000,000 = \$2,700,000$$
• Conclusion: Technology Infrastructure receives $\$2,700,000$.

---

Scatterplots, Bivariate Data, and Trendlines

A scatterplot plots pairs of quantitative numerical values $(x, y)$ on a Cartesian coordinate plane to investigate the relationship or association between two continuous variables. The independent (explanatory) variable is plotted on the horizontal $x$-axis, while the dependent (response) variable is plotted on the vertical $y$-axis.

Characterizing Associations

When analyzing scatterplots on the FTCE, describe the relationship using three structural criteria:

1. Direction of Association:
   • Positive Correlation: As $x$ increases, $y$ tends to increase (data points drift upward from left to right; positive slope).
   • Negative Correlation: As $x$ increases, $y$ tends to decrease (data points drift downward from left to right; negative slope).
   • No Correlation: Points are randomly dispersed with no discernible upward or downward pattern (horizontal drift; slope near zero).
2. Form: Whether the points cluster along a straight line (linear) or follow a curve (non-linear / curvilinear).
3. Strength: How tightly clustered the points are around the trendline (strong, moderate, or weak).

   POSITIVE CORRELATION             NEGATIVE CORRELATION                 NO CORRELATION
      ▲                                ▲                                ▲
    y │         •  •                 y │  •   •                       y │   •     •    •
      │      •  •  •                   │     •  •                       │      •     •
      │   •  •  •                      │       •  •  •                  │   •     •    •
      │ •  •                           │          •  •                  │     •    •    •
      └──────────────►                 └──────────────►                 └──────────────►
             x                                x                                x

Line of Best Fit (Trendline)

A line of best fit (linear regression line) models the underlying linear trend of bivariate data: $\hat{y} = mx + b$.

• Slope ($m$): Represents the average estimated rate of change in the response variable $y$ for each 1-unit increase in explanatory variable $x$.
• Interpolation vs. Extrapolation:
  • Interpolation: Predicting a $y$-value for an $x$-value that falls inside the range of observed data points. This is generally more reliable than extrapolation.
  • Extrapolation: Predicting a $y$-value for an $x$-value outside the observed data boundaries. Extrapolation is inherently risky because the linear relationship may fail beyond the observed domain.

---

Two-Way Frequency Tables and Contingency Analysis

A two-way frequency table (contingency table) organizes bivariate categorical data by displaying the frequencies of two distinct nominal or ordinal variables simultaneously.

                           TWO-WAY TABLE STRUCTURAL ANATOMY
                                     Variable B Categories
                              ┌──────────────┬──────────────┬──────────────┐
                              │  Category 1  │  Category 2  │    Marginal  │
               ┌──────────────┼──────────────┼──────────────┼──────────────┤
  Variable A   │  Category 1  │  Joint (1,1) │  Joint (1,2) │  Row Total 1 │
  Categories   ├──────────────┼──────────────┼──────────────┼──────────────┤
               │  Category 2  │  Joint (2,1) │  Joint (2,2) │  Row Total 2 │
               ├──────────────┼──────────────┼──────────────┼──────────────┤
               │    Marginal  │ Column Tot 1 │ Column Tot 2 │  Grand Total │
               └──────────────┴──────────────┴──────────────┴──────────────┘

Joint, Marginal, and Conditional Frequencies

1. Joint Frequencies: The values in the inner body cells of the table representing observations that satisfy both row and column conditions simultaneously ($A \cap B$).
2. Marginal Frequencies: The values in the margins (row totals and column totals) representing the total counts for a single variable category across all levels of the other variable.
3. Conditional Relative Frequency: The proportion of observations in a specific subset that satisfy a second condition. The denominator is restricted to a single marginal row or column total: $$P(B \mid A) = \frac{\text{Joint Frequency of } (A \text{ and } B)}{\text{Marginal Total of } A}$$

Worked Example: Contingency Probability

A survey of 150 high school seniors records whether they participate in extracurricular athletics and whether they work part-time jobs:

• What is the marginal relative frequency of being an athlete? $$\frac{60}{150} = 0.40 = 40\%$$
• What is the joint relative frequency of being an employed athlete? $$\frac{36}{150} = 0.24 = 24\%$$
• Given that a student is an athlete, what is the conditional relative frequency that the student is employed? $$\frac{\text{Joint (Employed Athlete)}}{\text{Marginal Total (Athlete)}} = \frac{36}{60} = 0.60 = 60\%$$
• Notice that $\frac{36}{60} = 0.60$ and $\frac{54}{90} = 0.60$; because the conditional probability of employment is identical between athletes and non-athletes, athletics and employment status are statistically independent in this sample.