Unit 2: Graphical and Diagrammatic Presentation of Data

Organisation and Classification of Data

Raw data collected from investigations is often unstructured, bulky, and difficult to interpret. To make this data meaningful, it must undergo systematic organisation and classification.

Definition: Data Classification is the process of arranging raw data into homogeneous groups or classes according to their common characteristics, features, or behaviors.

Proper organisation of data serves as the foundation for tabulating, graphing, and analyzing statistical information. The main objectives of classification are to simplify complexity, facilitate comparison, and highlight significant features of the dataset.

Types of Data Classification

Data can be classified into four primary categories depending on the nature of the inquiry:

Uses of Graphs in Analysing Data

Graphs are powerful visual tools that translate abstract numbers into intuitive visual forms. They are highly valued in statistical analysis for several key reasons:

• Identifying Trends and Patterns: Graphs make it easy to spot upward or downward trends, seasonal variations, and long-term cycles over time.
• Facilitating Quick Comparisons: Visual differences in heights, lengths, or slopes allow instantaneous comparisons between datasets without examining individual values.
• Determining Positional Averages: Certain graphs can be used to locate statistical measures directly. For example, the median can be found using cumulative frequency curves (ogives), and the mode can be estimated using a histogram.
• Detecting Correlation: Scatter graphs and line charts help researchers identify whether a relationship exists between two variables (e.g., temperature and sales).
• Simplifying Complex Datasets: Large volumes of multidimensional data can be summarized compactly on a single coordinate plane.

Advantages of Diagrams in Presenting Data

Diagrams differ from graphs in that they are primarily used for presentation, publicity, and comparison, whereas graphs are more suited for mathematical study and analysis. The main advantages of using diagrams include:

1. Universal Appeal: Diagrams can be understood easily by individuals without mathematical training. They convey meaning faster than complex statistical tables.
2. High Visual Memory Retention: Humans tend to remember visual shapes, colors, and structures much longer than raw numbers.
3. Saves Time and Effort: Interpreting a structured diagram requires significantly less cognitive effort than analyzing rows of numbers in a table.
4. Facilitates Direct Comparison: Placing bars or pie sectors side-by-side provides an immediate relative sense of proportion and size.
5. Highly Informative: A single well-constructed diagram can represent multiple variables and dimensions of a dataset simultaneously without causing information overload.

Types of Diagrammatic Presentation

Diagrams are geometric representations of data. The three most common forms include simple bar diagrams, joint bar diagrams, and pie diagrams.

1. Bar Diagram

A bar diagram (or simple bar chart) consists of a series of equidistant rectangular bars where the length of each bar is proportional to the value of the variable it represents.

• Characteristics: The width of the bars is arbitrary but must remain uniform. The spacing between any two consecutive bars must also be equal.
• Orientation: Bars can be drawn vertically (often for time-series data) or horizontally (often for qualitative data).
• Application: Used to compare distinct categories, such as the population of different cities or sales across different product lines.

2. Joint Bar Diagram

Also known as a multiple bar diagram, a joint bar diagram presents two or more sets of interrelated data side-by-side for comparison over time or across categories.

• Construction: Multiple bars representing different variables are grouped together for each category. Distinct colors, shades, or patterns must be used to differentiate the variables, along with a clear legend.
• Application: Useful for representing imports and exports of a country over consecutive years, or birth rates and death rates of different regions.
• Common Mistake: Avoid adding too many variables in a single joint bar diagram, as it makes the chart cluttered and hard to read.

3. Pie Diagram

A pie diagram (or circle chart) is a circular diagram divided into sectors or slices. The entire circle represents the total value, and the central angle of each sector is proportional to the component value it represents.

Formula for Central Angle:
Central Angle of Sector = (Component Value / Total Value) × 360°

The table below shows an example of calculating central angles for a household budget:

• Application: Ideal for showing percentage breakdowns or relative market shares where the total equals 100% (or 360°).

Types of Graphical Presentation

Unlike diagrams, graphs are drawn on coordinate axes (X-axis and Y-axis) and are highly suited for mathematical analysis and continuous variables.

1. Cumulative Frequency Distribution (Ogives)

A cumulative frequency distribution is a representation of continuous data where frequencies are progressively accumulated. There are two main types of cumulative curves, known as Ogives:

• Less Than Ogive: Created by adding frequencies from top to bottom. Upper limits of class intervals are plotted on the X-axis, and their corresponding cumulative frequencies are plotted on the Y-axis. The curve rises from left to right.
• More Than Ogive: Created by accumulating frequencies from bottom to top. Lower limits of class intervals are plotted on the X-axis, and cumulative frequencies are plotted on the Y-axis. The curve falls from left to right.

Exam Note: The point of intersection between the "Less Than" and "More Than" ogive curves gives the exact value of the Median of the dataset on the X-axis.

2. Histogram

A histogram is a graphical representation of a grouped frequency distribution consisting of contiguous vertical rectangles.

• Structure: The class intervals are marked on the horizontal X-axis, and the frequencies are marked on the vertical Y-axis. The area of each rectangle is proportional to the frequency of its corresponding class interval.
• Key Rule: Unlike bar charts, there are no gaps between the rectangles of a histogram because the underlying variable is continuous.
• Application: It is widely used to visualize the shape of data distributions and to estimate the Mode graphically by identifying the tallest rectangle.

3. Frequency Polygon

A frequency polygon is a line graph designed to represent the shape of a frequency distribution.

• Method of Construction: It can be constructed either by plotting the midpoints of the classes against their respective frequencies and connecting them with straight lines, or by connecting the midpoints of the top of the bars in a histogram.
• Closing the Polygon: To complete the polygon, the line must be extended at both ends to touch the X-axis. This is done by joining them to the midpoints of two imaginary classes (one preceding the first class and one succeeding the last class) with zero frequency. This ensures that the total area under the polygon remains equal to the total area of the corresponding histogram.