MODULE III: DIAGRAMMATIC AND GRAPHIC PRESENTATION

Curricular Scope & Foundational Overview: Module III delivers an exhaustive, textbook-grade investigation into the visual representation of quantitative and qualitative business data in Fundamentals of Business Mathematics and Statistics (COM2MN104). It rigorously analyzes the mathematical and aesthetic distinctions between Diagrams and Graphs, examines general principles and protocols for accurate diagram construction, and presents a complete taxonomy of statistical charts. The module systematically explores One-Dimensional Bar Diagrams (Simple, Multiple, Sub-divided, Percentage, and Deviation), Two-Dimensional Diagrams (Rectangular, Square, and Angular Pie Charts), Three-Dimensional Volumes, Pictograms, and Cartograms. Furthermore, it details the graphical treatment of continuous frequency distributions through Histograms (with equal and unequal class widths), Frequency Polygons, Frequency Curves, and Cumulative Frequency Ogives, concluding with the graphic determination of central partition metrics including the Mode, Median, Quartiles, Deciles, and Percentiles.

Unit 8: Fundamentals of Visual Representation in Business Statistics

8.1 Introduction to Visual Data Representation

In modern commerce, data is generated continuously across supply chains, financial markets, human resource operations, and customer touchpoints. While numerical tabulation arranges raw records into systematic rows and columns, large and intricate statistical tables often fail to convey immediate meaning to executive leadership, investors, or general stakeholders. Diagrammatic and graphic presentations transform abstract numerical datasets into geometric figures, shapes, lines, and curves, facilitating instantaneous comprehension, comparative assessment, and strategic decision-making.

Visual representation does not replace numerical tabulation; rather, it complements statistical tables. A statistical table contains exact numerical precision and serves as the archival source of truth, whereas a diagram or graph highlights underlying patterns, trends, structural proportions, and relationships that might remain obscure in dense tabular presentations.

8.2 Distinction between Tabulation, Diagrams, and Graphs

A precise academic understanding requires establishing the exact operational and structural boundaries separating statistical tables, geometric diagrams, and mathematical graphs:

Comparative Basis	Statistical Tabulation	Diagrammatic Presentation	Graphical Presentation
Primary Purpose	Systematic storage, organization, and presentation of exact numerical values.	Visual illustration of relationships, magnitudes, and proportions for non-technical audiences.	Mathematical analysis, trend identification, and determination of statistical partition values.
Construction Medium	Plain or lined tabular sheets arranged in rows and columns.	Plain paper, canvas, or digital artboards using geometric shapes (bars, circles, rectangles).	Cartesian coordinate grid paper (X and Y axes with defined scales).
Target Audience	Research analysts, accountants, auditors, and technical statisticians.	General public, executives, marketing teams, and corporate board members.	Statisticians, econometricians, operational researchers, and financial analysts.
Data Types Accommodated	Both discrete and continuous, qualitative and quantitative data of any complexity.	Primarily categorical, discrete, spatial, or chronological series.	Continuous frequency distributions, time series, and functional mathematical relationships.
Level of Precision	Absolute numerical precision (up to exact decimal places).	Approximate; visual impressions dominate over microscopic numerical detail.	High visual precision; values can be interpolated or measured using grid coordinates.
Mathematical Utility	Provides raw inputs for calculating statistical metrics.	Limited mathematical utility; cannot be used to locate mathematical averages algebraically.	High analytical utility; used to determine Mode, Median, Quartiles, and correlation.

8.3 Significance and Managerial Utility of Visual Presentation

The widespread adoption of visual presentations in corporate reporting, macroeconomic analysis, and market research is driven by distinct operational advantages:

1. High Cognitive Retention & Impact

Human cognitive architecture processes visual patterns significantly faster than strings of numbers. Eye-tracking and behavioral research confirm that diagrams and charts create durable mental models, enabling directors and managers to grasp long-term corporate performance trends within seconds.

2. Instant Comparative Evaluation

When evaluating competing business divisions, cross-border subsidiary performance, or multi-year cost structures, side-by-side bar charts or segmented percentage bars render comparative strengths and variances instantly observable without tedious manual subtraction.

3. Trend & Cycle Recognition

Time series graphs illuminate underlying secular trends, seasonal swings, and cyclical economic fluctuations that are easily masked when viewing monthly ledger accounts across several operating fiscal years.

4. Universal & Cross-Border Appeal

Diagrams transcend language barriers and educational disparities. In multinational conglomerates and public health campaigns, pictograms, cartograms, and standardized charts communicate performance indicators across culturally diverse teams without translational ambiguity.

8.4 Inherent Limitations and Visual Pitfalls

Despite their undeniable communicative power, diagrams and graphs suffer from distinct methodological limitations that business professionals must respect to prevent analytical distortion:

Loss of Exact Precision: While a financial ledger can report revenue down to the nearest rupee (e.g., ₹12,482,912.45), a corporate bar chart can only indicate that revenue approximates ₹1.25 Crores. Minute variances essential for auditing cannot be verified directly from charts.
Susceptibility to Manipulation (Scale Trickery): Visual perception is heavily influenced by the choice of axis scales. Truncating the vertical axis (omitting the true zero base line) can exaggerate modest 2% performance gains into dramatic visual spikes, intentionally misleading investors or stakeholders.
Inability to Show Infinite Variables: While multi-dimensional tables can cross-classify five or six statistical attributes simultaneously, geometric diagrams become cluttered, unreadable, and cognitively overwhelming when displaying more than two or three dimensions.
Lack of Algebraic Treatability: Unlike raw data or arithmetic means, values depicted in diagrams cannot undergo further algebraic manipulation, integration, or secondary statistical modeling without converting back to numerical tables.

8.5 General Rules and Academic Conventions for Diagram Construction

To ensure statistical integrity, aesthetic professionalism, and academic rigor, every statistical diagram must adhere strictly to established construction canons:

1. Title & Identification

Every diagram must carry a clear, self-explanatory title at the top, stating the subject matter, geographical coverage, and reference time frame (e.g., "Export Performance of Engineering Goods (2020-2024)").

2. Proportional Dimensions

The ratio between the vertical height and horizontal width of a diagram should maintain visual harmony. The classical golden ratio or a proportion of approximately 1:1.4 to 1:1.6 ensures the chart is neither awkwardly tall nor excessively flat.

3. Scientific Scale Selection

Scale units should be round numbers (multiples of 5, 10, 50, 100, etc.) clearly stated along the axes. The origin must start at zero; if data points reside far above zero, a distinct False Base Line (break line) must be inserted.

4. Legend & Key

When multiple series are displayed within the same frame, distinct colors, shading, cross-hatching, or patterns must be utilized and mapped to a well-defined legend box positioned at the top-right or bottom.

5. Source & Footnotes

The authentic primary or secondary data source must be acknowledged at the bottom left (e.g., "Source: Annual Report of Reserve Bank of India, 2023-24"), accompanied by explanatory footnotes regarding data adjustments.

6. Neatness & Simplicity

Visual clutter must be avoided. A diagram should convey one or two central themes cleanly. Excessive grid lines, ornate 3D bevels, and non-functional visual ornamentation (chartjunk) degrade statistical interpretability.

8.6 Classification Taxonomy of Statistical Diagrams

Statistical diagrams are systematically categorized into five distinct architectural classes based on the geometric dimensions utilized to depict data magnitudes:

Classification Class	Geometric Dimension Utilized	Representative Diagram Types	Typical Business Application
One-Dimensional (1-D)	Length (or Height) only; width is arbitrary and uniform.	Simple Bar, Multiple Bar, Sub-divided Bar, Percentage Bar, Deviation Bar, Broken-scale Bar.	Comparing sales revenue, production outputs, departmental expenditures across years or regions.
Two-Dimensional (2-D)	Area (Product of two linear dimensions: Length × Breadth, or (pi r^2)).	Rectangles, Sub-divided Rectangles, Squares, Circular Diagrams, Pie Charts.	Displaying multi-attribute aggregates (Price × Quantity = Total Outlay), corporate budget breakdowns.
Three-Dimensional (3-D)	Volume (Product of three dimensions: Length × Breadth × Height).	Cubes, Cylinders, Spheres.	Depicting extreme macroeconomic magnitudes (national wealth, global energy reserves) where ratios exceed 10,000:1.
Pictograms	Repetition or scaling of realistic representative visual icons.	Visual human silhouettes, automobile icons, coin stacks, grain sacks.	Public exhibitions, investor slide decks, social demographic summaries, literacy-neutral media.
Cartograms	Geographic space mapped against statistical density.	Choropleth statistical maps, Dot density maps, Cartographic flow diagrams.	Geographical sales distribution, state-wise tax collection, logistics network density, regional market share.

Unit 9: One-Dimensional Diagrams (Bar Diagrams)

9.1 Theoretical Principles of Bar Diagram Construction

In a one-dimensional diagram, magnitude is reflected solely by the length (for horizontal bars) or height (for vertical bars) of geometric rectangles called bars. The width of each bar has no mathematical significance and is kept strictly identical across all bars purely for aesthetic consistency and visual symmetry. Furthermore, the spacing between consecutive bars must remain uniform, typically set between one-half to the full width of a single bar.

Bars may be drawn vertically or horizontally. When categorical titles are lengthy (such as names of municipal corporations, specialized industrial machinery, or verbose qualitative descriptions), horizontal bar diagrams are preferred to allow neat text alignment along the vertical axis without awkward rotation. When representing chronological series (years, quarters, months), vertical bar diagrams are universally mandated to respect the natural psychological perception of time progressing horizontally from left to right.

9.2 Simple Bar Diagrams

A Simple Bar Diagram represents a single, independent categorical or chronological variable across distinct classes. Each bar originates from a common baseline (typically zero on the Y-axis for vertical charts).

Business Application Example 9.1: Annual Turnover Analysis
Consider the total revenue generated by a regional logistics enterprise over five consecutive financial years:

Financial Year	2019-20	2020-21	2021-22	2022-23	2023-24
Turnover (₹ in Crores)	45.0	38.5	62.0	85.5	110.0

Construction Protocol: Financial years are marked on the horizontal X-axis with uniform gaps. Turnover is calibrated on the vertical Y-axis starting at 0 with 20-Crore intervals (0, 20, 40, 60, 80, 100, 120). Five distinct vertical bars are erected whose heights correspond exactly to the respective turnover figures. The dip during 2020-21 (pandemic impact) and the rapid post-2021 acceleration are instantly noticeable.

9.3 Multiple Bar Diagrams (Compound Bar Diagrams)

A Multiple Bar Diagram places two or more adjacent bars side-by-side for each category or time point. This structure is deployed to facilitate direct, simultaneous comparison between two or more related economic phenomena (e.g., Imports vs. Exports, Production vs. Sales, Budgeted vs. Actual Expenditure).

Each bar in the cluster represents a specific sub-variable, shaded with distinctive patterns or contrasting colors. The cluster is separated from adjacent clusters by a wider gap to maintain clear visual grouping.

Business Application Example 9.2: International Trade Comparison
The following data represents the foreign trade performance (Imports and Exports) of a commercial commodities desk over four operational years:

Fiscal Year	Exports (₹ Crores)	Imports (₹ Crores)	Trade Balance (Exports - Imports)	Visual Status
2020-21	120	150	-30	Deficit (Import bar exceeds Export bar)
2021-22	160	175	-15	Deficit (Gap narrowing)
2022-23	210	190	+20	Surplus (Export bar surpasses Import bar)
2023-24	280	230	+50	Expanding Trade Surplus

Analytical Insight: Erecting twin bars for each fiscal year enables instantaneous comparison not only of total volume growth over time but also reveals the historic transition of the firm from a net trade deficit in 2020-21 to a robust surplus by 2023-24.

9.4 Sub-divided (Component) Bar Diagrams

When an aggregate total can be partitioned into distinct constituent components, a Sub-divided Bar Diagram is constructed. In this diagram, each bar represents the total magnitude of a given category, while the total height of the bar is divided into proportionate segments corresponding to its sub-components.

To ensure consistent reading, the components must be stacked in the exact same sequence across all bars (conventionally from the largest component at the base to the smallest at the top, or following a logical manufacturing flow). Cumulative values are computed to determine the boundary marks on each bar.

Numerical Illustration 9.3: Cost Structure Breakdown Across Manufacturing Plants
A manufacturing firm operates three regional production facilities (Plant Alpha, Plant Beta, Plant Gamma). The quarterly production cost components (in ₹ Lakhs) are detailed below:

Cost Element Plant Alpha (₹ L) Cumulative Alpha Plant Beta (₹ L) Cumulative Beta Plant Gamma (₹ L) Cumulative Gamma

Direct Raw Materials 120 120 160 160 200 200

Direct Labor 80 200 100 260 120 320

Factory Overheads 50 250 60 320 80 400

Administrative & Selling 30 280 40 360 50 450

Total Cost of Production 280 -- 360 -- 450 --

Step 1: The overall heights of the bars for Plant Alpha, Beta, and Gamma are scaled to 280, 360, and 450 units respectively.

Cost Element	Plant Alpha (₹ L)	Cumulative Alpha	Plant Beta (₹ L)	Cumulative Beta	Plant Gamma (₹ L)	Cumulative Gamma
Direct Raw Materials	120	120	160	160	200	200
Direct Labor	80	200	100	260	120	320
Factory Overheads	50	250	60	320	80	400
Administrative & Selling	30	280	40	360	50	450
Total Cost of Production	280	--	360	--	450	--

Step 2: On Bar Alpha, horizontal dividing lines are etched at cumulative heights: 120 (Materials), 200 (Labor), 250 (Overheads), and 280 (Admin).

Step 3: The same cumulative partitioning is applied to Plant Beta (160, 260, 320, 360) and Plant Gamma (200, 320, 400, 450).

Step 4: Distinct shading patterns (stripes, dots, crosshatching) are applied identically across corresponding component blocks.

9.5 Percentage Sub-divided Bar Diagrams

While sub-divided bars reflect differences in both total magnitude and component composition, they make it difficult to compare the relative proportions of components when total magnitudes vary widely. For instance, in Plant Gamma above, the raw material cost of ₹200 Lakhs is visually larger than Plant Alpha's ₹120 Lakhs, yet its relative percentage share might be smaller.

To isolate and compare relative percentage shares, all bars are drawn to a uniform total height representing 100%. The component values are converted into percentages of the respective total, and cumulative percentages dictate the segment heights.

Component Percentage Conversion Formula PERCENTAGE NORMALIZATION

P er ce n t a g e S ha r e = (C o m p o n e n t V a l u e / A g g r e g a t e T o t a l) * 100%

Operational Rule: The sum of individual percentages for each bar must equal exactly 100.0%. Cumulative percentages establish the boundary marks:

Cumulative % (1) = % Component 1
Cumulative % (2) = % Component 1 + % Component 2
Cumulative % (k) = Cumulative % (k-1) + % Component k = 100.0%

Numerical Illustration 9.4: Normalization of Plant Cost Structures to 100%

Cost Element Plant Alpha (%) Cumul. % Alpha Plant Beta (%) Cumul. % Beta Plant Gamma (%) Cumul. % Gamma

Direct Materials (120/280)100 = 42.86% 42.86% (160/360)100 = 44.44% 44.44% (200/450)100 = 44.44% 44.44%

Direct Labor (80/280)100 = 28.57% 71.43% (100/360)100 = 27.78% 72.22% (120/450)100 = 26.67% 71.11%

Factory Overheads (50/280)100 = 17.86% 89.29% (60/360)100 = 16.67% 88.89% (80/450)100 = 17.78% 88.89%

Administrative & Selling (30/280)100 = 10.71% 100.00% (40/360)100 = 11.11% 100.00% (50/450)100 = 11.11% 100.00%

Total Percentage 100.00% -- 100.00% -- 100.00% --

Managerial Takeaway: Although Plant Gamma's absolute cost of ₹450 Lakhs is 60.7% higher than Plant Alpha's ₹280 Lakhs, the percentage bar diagram reveals remarkable structural stability across all plants: Direct Materials constitute ~43-44%, Direct Labor ~27-28%, Overheads ~17-18%, and Administration ~11%. This demonstrates identical operational efficiencies despite scale differences.

Cost Element	Plant Alpha (%)	Cumul. % Alpha	Plant Beta (%)	Cumul. % Beta	Plant Gamma (%)	Cumul. % Gamma
Direct Materials	(120/280)100 = 42.86%*	42.86%	(160/360)100 = 44.44%*	44.44%	(200/450)100 = 44.44%*	44.44%
Direct Labor	(80/280)100 = 28.57%*	71.43%	(100/360)100 = 27.78%*	72.22%	(120/450)100 = 26.67%*	71.11%
Factory Overheads	(50/280)100 = 17.86%*	89.29%	(60/360)100 = 16.67%*	88.89%	(80/450)100 = 17.78%*	88.89%
Administrative & Selling	(30/280)100 = 10.71%*	100.00%	(40/360)100 = 11.11%*	100.00%	(50/450)100 = 11.11%*	100.00%
Total Percentage	100.00%	--	100.00%	--	100.00%	--

9.6 Bilateral / Deviation Bar Diagrams

When a business variable contains both positive and negative values, a Deviation (Bilateral) Bar Diagram is deployed. A baseline corresponding to zero is drawn horizontally across the middle of the frame. Positive deviations (profits, trade surpluses, net cash inflows, positive growth rates) extend upward from the baseline, while negative deviations (losses, trade deficits, cash burns, contraction rates) project downward.

Business Application Example 9.5: Net Annual Profit / Loss Across Corporate Divisions
A diversified consumer retail enterprise tracks the net financial performance of its six regional operating divisions for FY 2023-24:

Division	North Zone	South Zone	East Zone	West Zone	Central Zone	Overseas Retail
Net P&L (₹ Lakhs)	+85.0	+120.0	-45.0	+60.0	-25.0	+15.0
Bar Orientation	Upward (+85)	Upward (+120)	Downward (-45)	Upward (+60)	Downward (-25)	Upward (+15)

Visual Contrast: Shading positive bars in corporate green and negative bars in warning red immediately alerts senior leadership to the ongoing operational cash drains in East Zone and Central Zone, isolating turnaround priorities without requiring detailed spreadsheet examination.

9.7 Broken-Scale Bar Diagrams and Sliding Bar Diagrams

In corporate datasets containing extreme outliers, scaling the vertical axis to accommodate an anomalously high figure compresses all other bars into tiny, indistinguishable stubs. To resolve this:

Broken-Scale Bar Diagram: The axis and the anomalous bar are interrupted by a distinct zig-zag break line (kink). For example, if four branches report sales of ₹20L, ₹25L, ₹30L, and the flagship headquarters branch reports ₹500L, the axis scales up to ₹40L, breaks with a zig-zag, and resumes at ₹490L–₹510L.
Sliding Bar Diagram: Used to represent bivariate percentage splits (such as percentage of satisfied vs. dissatisfied customers, or male vs. female workforce ratios). The zero line is centered vertically; positive or favorable responses extend to the right, while unfavorable or contrasting responses extend to the left.

Unit 10: Two-Dimensional, Three-Dimensional, Pictograms & Cartograms

10.1 Foundations of Two-Dimensional (Area) Diagrams

In two-dimensional diagrams, the area of the geometric figure is directly proportional to the magnitude of the statistical data being represented. Both length and breadth are varied mathematically. Two-dimensional diagrams are primarily deployed in two circumstances:

When the differences in magnitudes between items are very large, rendering 1D bars either too tall or too microscopic to display on a single page.
When the statistical aggregate is the mathematical product of two independent underlying variables (such as $Total Revenue = Price \times Quantity$ , or $Agricultural Output = Acreage \times Yield per Acre$ ).

10.2 Rectangular Diagrams and Sub-divided Rectangles

In a rectangular diagram, the width of the rectangle represents one variable, and the height represents another related variable. The resulting area ( $Width \times Height$ ) represents their economic product.

A Sub-divided Rectangle is constructed by setting the width proportional to total expenditure or output, and then partitioning the height into percentage shares, or setting width to quantity and subdividing length according to unit cost elements.

Numerical Illustration 10.1: Bivariate Commercial Modeling via Rectangular Diagrams
Compare the economic performance of two regional electricity distribution companies:

Discom North: Total Power Sold = 50 Million kWh; Average Tariff = ₹6.00 per kWh. Total Revenue = ₹300 Million.

Discom South: Total Power Sold = 100 Million kWh; Average Tariff = ₹4.50 per kWh. Total Revenue = ₹450 Million.

Step 1: Set the horizontal breadths proportional to Power Sold in the ratio 50 : 100, which simplifies to 1 : 2 (e.g., 4 cm and 8 cm).

Step 2: Set the vertical heights proportional to Average Tariff in the ratio 6.00 : 4.50, which simplifies to 4 : 3 (e.g., 6 cm and 4.5 cm).

Step 3: Area of Discom North Rectangle = 4 cm * 6 cm = 24 sq cm (representing ₹300 Million).

Step 4: Area of Discom South Rectangle = 8 cm * 4.5 cm = 36 sq cm (representing ₹450 Million).

Ratio of Areas = 24 : 36 = 2 : 3, which matches exactly the ratio of total revenues (300 : 450 = 2 : 3).

10.3 Square Diagrams

When comparing items that vary widely in absolute magnitude, simple linear bars become unwieldy. In a Square Diagram, values are converted into proportional squares. Since the area of a square is $Side^{2}$ , the length of each side is set proportional to the square root of the given statistical value:

Square Diagram Side Scaling Formula SQUARE ROOT TRANSFORMATION

S i d eo f S q u a r e (s) = c * S QR T (V a l u e)

Where c is an arbitrary scaling constant selected to fit the layout.

For a value of ₹10,000 Crores, (sqrt{10,000} = 100). If $c = 0.05 cm$ , side = 5.0 cm.
For a value of ₹2,500 Crores, (sqrt{2,500} = 50). Side = 2.5 cm.
Area ratio = (5.0^2 : 2.5^2 = 25 : 6.25 = 4 : 1), perfectly matching the original financial ratio of 10,000 : 2,500.

10.4 Circular Diagrams and Pie Charts (Angular Diagrams)

A Pie Chart (also designated as an Angular or Sector Diagram) is a two-dimensional circular statistical chart where the total area of the circle represents the total aggregate (100%), and individual angular sectors represent the proportional components of that aggregate.

Because the sum of all central angles surrounding the center of a circle is identically (360^circ), each component's proportional share is converted into a corresponding central angle:

Central Angle Conversion Formula for Pie Charts ANGULAR CALCULATION

S ec t or A n g l e (t h e t a) = [C o m p o n e n t V a l u e / T o t a l A g g r e g a t e V a l u e] * 360 d e g r ees

Verification Identity: The mathematical sum of all computed sector angles must equal exactly 360 degrees:

sum_{i=1}^k heta_i = heta_1 + heta_2 + dots + heta_k = 360^circ quad ext{and} quad r propto sqrt{ ext{Total Value}}

Rigorous Construction Protocol for Pie Charts:

Calculate the total aggregate value of all constituent items.
Compute the individual percentage share of each item: (% = (text{Item} / text{Total}) × 100).
Compute the exact sector angle in degrees: (theta = (text{Item} / text{Total}) × 360^circ).
Draw a circle of appropriate radius using a compass. Establish a baseline radius vertically upward at the 12 o'clock position.
Using a protractor, measure and mark the sector angle for the largest component starting from the 12 o'clock line in a clockwise direction.
Proceed sequentially with remaining components in descending order of magnitude, using the terminal radius of the previous sector as the baseline for the next.
Label each sector clearly with its category name and percentage share. Apply distinct colors or hatchings accompanied by a structured legend.

Numerical Illustration 10.2: Capital Outlay & Budget Allocation for a Tech Corporation
A multinational enterprise allocates its annual capital expenditure budget of text{text{Rs. } }500 Crores across five strategic divisions. Compute the exact sector angles required for constructing a textbook-grade pie chart:

Strategic Expenditure Head Budget Outlay (text{text{Rs. } } Crores) Percentage Share (%) Sector Angle Calculation Exact Sector Angle (°)

Research & AI Development 175.0 (175/500)100 = 35.0% 35.0% 360° = 0.35 * 360° 126.0°

Global Cloud Infrastructure 125.0 (125/500)100 = 25.0% 25.0% 360° = 0.25 * 360° 90.0°

Marketing & Brand Expansion 100.0 (100/500)100 = 20.0% 20.0% 360° = 0.20 * 360° 72.0°

Talent Acquisition & Training 60.0 (60/500)100 = 12.0% 12.0% 360° = 0.12 * 360° 43.2°

Cybersecurity & Compliance 40.0 (40/500)100 = 8.0% 8.0% 360° = 0.08 * 360° 28.8°

Total Aggregate Budget 500.0 100.0% Sum of Angles 360.0°

Verification Check: 126.0° + 90.0° + 72.0° + 43.2° + 28.8° = 360.0°. Sum of percentages = 100.0%. Precision is perfectly preserved.

Strategic Expenditure Head	Budget Outlay (text{text{Rs. } } Crores)	Percentage Share (%)	Sector Angle Calculation	Exact Sector Angle (°)
Research & AI Development	175.0	(175/500)100 = 35.0%*	35.0% * 360° = 0.35 * 360°	126.0°
Global Cloud Infrastructure	125.0	(125/500)100 = 25.0%*	25.0% * 360° = 0.25 * 360°	90.0°
Marketing & Brand Expansion	100.0	(100/500)100 = 20.0%*	20.0% * 360° = 0.20 * 360°	72.0°
Talent Acquisition & Training	60.0	(60/500)100 = 12.0%*	12.0% * 360° = 0.12 * 360°	43.2°
Cybersecurity & Compliance	40.0	(40/500)100 = 8.0%*	8.0% * 360° = 0.08 * 360°	28.8°
Total Aggregate Budget	500.0	100.0%	Sum of Angles	360.0°

10.5 Three-Dimensional Diagrams (Volume Diagrams)

When data variations span multiple orders of magnitude (for example, comparing an economy with GDP of text{text{Rs. } }10,000 Crores against one with text{text{Rs. } }100,000,000 Crores), even 2D areas fail. In three-dimensional diagrams, volume represents magnitude. The standard geometric bodies utilized are cubes, spheres, and cylinders.

In a Cube Diagram, since the volume of a cube is (text{Side}^3), the linear edge length of the cube is scaled proportional to the cube root of the numerical value:

S i d eo f C u b e = c * (V a l u e)^{(} 1/3)

While mathematically elegant, three-dimensional diagrams are notoriously difficult for human observers to calibrate visually and are prone to severe misinterpretation. Consequently, their modern commercial use is largely restricted to scientific illustrations.

10.6 Pictograms and Cartograms

Pictograms (Picture Diagrams)

A pictogram represents statistical quantities through repeated realistic visual icons or symbols. For instance, a vehicle icon may be designated to represent 50,000 units produced, or a human silhouette may denote 1,000,000 citizens.

Standard Rule: Magnitude must be shown by repeating identical unit icons of the same size, NOT by enlarging a single icon (which creates visual distortion due to quadratic area expansion).
Merits: Immediate public engagement, highly appealing for general exhibitions and corporate annual brochures.
Demerits: Imprecise; fractions of an icon are difficult to draw or interpret accurately.

Cartograms (Statistical Maps)

A cartogram displays quantitative information distributed across geographic administrative boundaries (countries, states, districts) using thematic cartography.

Choropleth Technique: Geographic regions are shaded with increasing intensity of color corresponding to density intervals (e.g., state-wise GST collections, per capita income).
Dot Cartograms: Placing dots of uniform value across the map to represent population or industrial plant density.
Logistics & Market Share: Deployed by supply chain leaders to map freight corridors, warehouse catchment zones, and regional dealer penetration.

Unit 11: Graphical Presentation of Frequency Distributions & Partition Values

11.1 The Mathematical Coordinate Plane and Graphing Mechanics

Graphs represent mathematical functions and continuous empirical frequency distributions plotted upon a Cartesian coordinate grid. Unlike diagrams, which are artistic representations of discrete categories, graphs possess continuous mathematical properties that permit interpolation, extrapolation, and the direct geometric derivation of positional averages.

In business statistics, data is plotted primarily in the First Quadrant, where both the independent variable along the horizontal X-axis (abscissa) and the dependent variable along the vertical Y-axis (ordinate) are non-negative.

The False Base Line (Kink / Break Line) Technique

By standard statistical convention, the vertical scale must start at zero. However, if all observations in a business dataset fluctuate within a narrow, elevated range (for instance, stock market index values fluctuating between 72,000 and 74,000 points, or factory daily production ranging between 9,800 and 10,200 units), starting the Y-axis at zero forces the curve to compress into a virtually flat, indistinguishable horizontal line at the very top of the graph.

To resolve this without misleading the reader, a False Base Line (represented by a distinct pair of saw-tooth zig-zag lines or an axis break symbol) is inserted between 0 and the lowest observation (e.g., 0 → [kink

→ 71,000 → 72,000 → 73,000). This magnifies subtle operational variations while explicitly alerting the viewer that the base scale has been truncated.

11.2 The Histogram: Mechanics, Frequency Density, and Modal Determination

A Histogram is a continuous graphical representation of a grouped frequency distribution consisting of adjacent vertical rectangles erected over class intervals. Because class intervals in continuous distributions are contiguous (e.g., 10-20, 20-30, 30-40), there are no gaps or spaces between adjacent rectangles.

Equal Class Intervals: When all class intervals have uniform width ((h)), the width of each rectangle represents the class interval, and the height of the rectangle is directly proportional to the class frequency ((f)). The area of each rectangle is $Area = h \times f$ .
Unequal Class Intervals: If class widths vary across the distribution, plotting raw frequencies as heights distorts the chart, as wider intervals falsely exaggerate volume. In such cases, Frequency Density (Adjusted Frequency) must be calculated to determine the height of each bar.

Frequency Density (Adjusted Frequency) Formula UNEQUAL INTERVAL ADJUSTMENT

A d j u s t e d H e i g h t = [C l a ss F r e q u e n cy (f) / C l a ss W i d t h (w)] * S t an d a r d B a se W i d t h (w_{0})

Where:

f = Raw frequency of the respective class interval.
w = Actual width of the given class interval (Upper Boundary - Lower Boundary).
w_0 = Standard base width, chosen as the width of the smallest class interval in the distribution.

11.3 Graphic Determination of the Mode using a Histogram

The Mode is the value of the variable that occurs with the greatest frequency. Geometrically, the mode resides within the tallest rectangle of the histogram, termed the Modal Class. The exact modal value can be derived graphically through a precise geometric construction without requiring manual algebraic calculation:

Geometric Step-by-Step Construction Protocol:

Identify the tallest rectangle in the histogram representing the modal class ( $L_{1} to L_{2}$ ). Let its height be (f_1).
Locate the top-left corner (point (A)) and top-right corner (point (B)) of the modal rectangle.
Locate the top-right corner of the immediately preceding rectangle (point (C)) and the top-left corner of the immediately following rectangle (point (D)).
Draw a straight line connecting point (A) to point (D).
Draw a straight line connecting point (B) to point (C).
Mark the intersection point of these two diagonal lines as point (P).
Drop a perpendicular line from point (P) straight down to the horizontal X-axis. The point where this perpendicular intersects the X-axis gives the exact graphic value of the Mode.

Mathematical Formula for Mode in Continuous Grouped Series ALGEBRAIC PROOF

M o d e (Z) = L + [(f_{1} - f_{0}) / (2 * f_{1} - f_{0} - f_{2})] * h

Variables & Geometric Alignment:

L = Lower boundary of the modal class.
f_1 = Frequency of the modal class (height of tallest rectangle).
f_0 = Frequency of the pre-modal class (height of preceding rectangle).
f_2 = Frequency of the post-modal class (height of succeeding rectangle).
h = Class width of the modal class.

Note: The formula is directly derived from the similarity of triangles formed by the intersecting diagonals in the histogram!

Numerical Problem 11.1: Determining the Modal Weekly Wage Graphically & Algebraically
The weekly wage distribution of 150 production workers in an automotive components plant is recorded as follows:

Weekly Wage Class (₹) 4000 - 5000 5000 - 6000 6000 - 7000 7000 - 8000 8000 - 9000 9000 - 10000

Number of Workers (f) 15 28 52 35 14 6

Step 1: The maximum frequency is 52. The Modal Class is ₹6,000 - ₹7,000.

Weekly Wage Class (₹)	4000 - 5000	5000 - 6000	6000 - 7000	7000 - 8000	8000 - 9000	9000 - 10000
Number of Workers (f)	15	28	52	35	14	6

Step 2: Identify parameters: L = 6,000; f_1 = 52; f_0 = 28; f_2 = 35; h = 1,000.

Step 3: Numerator: f_1 - f_0 = 52 - 28 = 24.

Step 4: Denominator: 2*f_1 - f_0 - f_2 = 2(52) - 28 - 35 = 104 - 63 = 41.

Step 5: Mode = 6000 + (24 / 41) * 1000 = 6000 + (0.585366 * 1000) = 6000 + 585.37 = ₹6,585.37.

Conclusion: Dropping a perpendicular from the intersection of diagonals inside the tallest bar at (6000-7000) strikes the X-axis at exactly ₹6,585.37!

11.4 Frequency Polygon and Frequency Curve

1. Frequency Polygon

A Frequency Polygon is a closed rectilinear geometric figure formed by connecting the midpoints of the tops of the histogram rectangles with straight line segments.

Independent Construction: Plot mid-values ((m)) on the X-axis against frequencies on the Y-axis, then join consecutive coordinate pairs ((m_i, f_i)) using a ruler.
Closure Rule: To ensure the area under the polygon equals the area under the histogram, the polygon must be anchored to the X-axis at both ends by extending lines to the midpoints of two hypothetical adjacent classes with frequency zero.

2. Frequency Curve

A Frequency Curve is a smoothed version of the frequency polygon, obtained by drawing a smooth, free-hand continuous curve through the vertices of the polygon to eliminate sharp random sample zig-zags.

Area Equivalence: The total area enclosed by a smoothed frequency curve and the X-axis represents the total aggregate frequency ((N)).
Standard Shapes: Symmetrical (Bell-shaped Gaussian/Normal distribution), Positively Skewed (long tail to the right), Negatively Skewed (long tail to the left), U-shaped (bimodal extremes), and J-shaped distributions.

11.5 Cumulative Frequency Curves (Ogives) & Graphic Partition Values

An Ogive (pronounced oh-jive) is a smooth mathematical curve representing a cumulative frequency distribution. The term originates from architecture, referring to the characteristic S-shaped ogival curve of Gothic arches. There are two distinct types of ogives:

"Less than" Ogive: Constructed by plotting cumulative frequencies against the upper class boundaries. As upper boundaries increase, cumulative frequency monotonically increases, producing a smooth rising S-curve starting at the lower boundary of the first class and terminating at total frequency (N).
"More than" Ogive: Constructed by plotting cumulative frequencies against the lower class boundaries. As lower boundaries increase, remaining cumulative frequency monotonically decreases, producing a declining S-curve starting at total frequency (N) and terminating at zero.

Graphic Determination of Partition Values (Median, Quartiles, Deciles, Percentiles):

The Fundamental Theorem of Ogive Intersection: When both the "Less-than" Ogive and the "More-than" Ogive of the same distribution are plotted on the same coordinate grid, they intersect at a unique point (P). Dropping a perpendicular from point (P) straight down to the horizontal X-axis locates the Median ((M)) of the distribution. The Y-coordinate of point (P) corresponds precisely to (N/2).

Graphic Derivation Protocol for Partition Values on a "Less-than" Ogive PARTITION FORMULAS

P os i t i o n o nY - a x i s : M e d ian = N /2∣ Q_{1} = N /4∣ Q_{3} = 3 * N /4∣ P_{k} = (k * N) /100

Procedure:

Locate the target cumulative frequency rank on the vertical Y-axis: (N/2) for Median, (N/4) for First Quartile ((Q_1)), (3N/4) for Third Quartile ((Q_3)), and (k cdot N/100) for the (k)-th Percentile ((P_k)).
Draw a horizontal line from this Y-coordinate until it intersects the "Less than" Ogive at point (K).
From point (K), drop a vertical perpendicular straight down to the horizontal X-axis.
The point of intersection on the X-axis provides the exact statistical partition value!

Numerical Problem 11.2: Full Construction of Cumulative Tables, Ogives, and Partition Value Derivation
An audit of 200 corporate accounts measures processing turnaround times (in hours). Construct the "Less than" and "More than" cumulative distributions and determine the Median, First Quartile ((Q_1)), and Third Quartile ((Q_3)):

Turnaround Time (Hrs) Frequency (f) Upper Limit Less than Cumulative (cf) Lower Limit More than Cumulative (cf)

10 - 20 16 Less than 20 16 More than 10 200

20 - 30 34 Less than 30 16 + 34 = 50 More than 20 200 - 16 = 184

30 - 40 60 Less than 40 50 + 60 = 110 More than 30 184 - 34 = 150

40 - 50 50 Less than 50 110 + 50 = 160 More than 40 150 - 60 = 90

50 - 60 26 Less than 60 160 + 26 = 186 More than 50 90 - 50 = 40

60 - 70 14 Less than 70 186 + 14 = 200 More than 60 40 - 26 = 14

1. Median Determination: Rank = N/2 = 200/2 = 100.

Turnaround Time (Hrs)	Frequency (f)	Upper Limit	Less than Cumulative (cf)	Lower Limit	More than Cumulative (cf)
10 - 20	16	Less than 20	16	More than 10	200
20 - 30	34	Less than 30	16 + 34 = 50	More than 20	200 - 16 = 184
30 - 40	60	Less than 40	50 + 60 = 110	More than 30	184 - 34 = 150
40 - 50	50	Less than 50	110 + 50 = 160	More than 40	150 - 60 = 90
50 - 60	26	Less than 60	160 + 26 = 186	More than 50	90 - 50 = 40
60 - 70	14	Less than 70	186 + 14 = 200	More than 60	40 - 26 = 14

Locating Y = 100 on the "Less-than" ogive falls in class 30-40 (cf = 110, preceding cf = 50, f = 60).

Algebraic Formula: Median = L + [ (N/2 - cf) / f ] * h = 30 + [ (100 - 50) / 60 ] * 10 = 30 + (50/60)*10 = 30 + 8.33 = 38.33 Hours.

2. First Quartile (Q_1): Rank = N/4 = 200/4 = 50. Exactly at upper limit of 20-30! Q_1 = 30.00 Hours.

3. Third Quartile (Q_3): Rank = 3N/4 = 150. Falls in class 40-50 (cf = 160, preceding cf = 110, f = 50).

Q_3 = L + [ (3N/4 - cf) / f ] * h = 40 + [ (150 - 110) / 50 ] * 10 = 40 + (40/50)*10 = 40 + 8.0 = 48.00 Hours.

4. Interquartile Range (IQR): Q_3 - Q_1 = 48.00 - 30.00 = 18.00 Hours. Semi-IQR (Quartile Deviation) = 18.00 / 2 = 9.00 Hours.

11.6 Time Series Graphs (Historigrams) and Ratio Charts

A Historigram (distinct from a frequency histogram) is a line graph depicting the chronological movement of one or more economic variables plotted against time on the horizontal axis.

Single & Multiple Variable Graphs: Displaying annual revenues or comparing sales vs. marketing expenditures across a decade.
Two-Scale Line Graphs: When two plotted variables have completely different units of measurement (e.g., Automobile production in Units on the left Y-axis and Steel price in ₹/Tonne on the right Y-axis).
Ratio Charts (Semi-Logarithmic Graphs): In a standard natural scale graph, a rise from ₹10 to ₹20 (a ₹10 gain or 100% surge) produces the exact same vertical climb as a rise from ₹1,000 to ₹1,010 (a ₹10 gain or 1% rise). To display proportional rate of growth rather than absolute change, the vertical Y-axis is calibrated logarithmically. Equal vertical distances then represent equal percentage changes, enabling meaningful growth rate comparisons across startup ventures and established corporate giants.

11.7 Master Synthesis: Comprehensive Evaluation Matrix of Diagrams and Graphs

Visual Technique	Input Data Nature	Construction Medium	Key Geometric Parameter	Primary Corporate Purpose
Simple Bar Diagram	Single discrete/categorical attribute	Plain layout	Height/Length of rectangle	Annual sales, regional branch comparisons.
Multiple Bar Diagram	Two or more related series	Plain layout	Clustered bar heights	Direct comparison of Exports vs. Imports, Budgets vs. Actuals.
Component (Sub-divided) Bar	Aggregate broken into absolute parts	Plain layout	Stacked bar segment heights	Total production cost partitioned into materials, labor, overheads.
Percentage Bar Diagram	Relative structural proportions	Plain layout (100% height)	Percentage-normalized segment heights	Comparing cost or asset allocation structures across differing firm sizes.
Pie Chart (Angular Diagram)	Proportional shares of a single whole	Circle ((360^circ))	Central sector angles (( heta))	Corporate budget breakdown, national income sources, market share.
Histogram	Continuous frequency distribution	Grid / Coordinates	Contiguous bar area (Density × Width)	Wage distributions, quality control tolerances; graphic determination of Mode.
Frequency Polygon & Curve	Continuous series	Grid / Coordinates	Vertices joined by lines/curves	Comparing distribution shapes, symmetry, skewness, and Kurtosis.
Ogives (Cumulative Curves)	Cumulative frequency distributions	Grid / Coordinates	"Less-than" and "More-than" S-curves	Graphic determination of Median, Quartiles, Deciles, and Percentiles.
Historigram (Time Series Graph)	Chronological historical data	Grid / Coordinates	Continuous line segments over time	Forecasting, secular trend identification, business cycle monitoring.