Statistics Basics: Data Types, Sources & Classification

TAKEAWAYS:

• Data classification is the foundation of statistical analysis, dividing raw information into meaningful categories (qualitative/quantitative, discrete/continuous).
• Primary vs. secondary data determines the reliability and cost of your analysis—primary data is original but expensive; secondary data is cheaper but may lack relevance.
• Tourism applications use data classification to analyze visitor demographics, seasonal trends, and revenue patterns (e.g., NTC classifying passenger traffic by season).
• Business decisions rely on classified data for inventory management (Daraz’s product categorization), marketing segmentation (Pathao’s rider demographics), and financial forecasting (bank loan approvals).
• Visual tools like frequency distributions and ogives transform raw data into actionable insights (e.g., NEPSE’s stock trend analysis).
• Exam focus: Expect questions on distinguishing data types, classifying real-world datasets (e.g., hotel occupancy rates), and interpreting visual representations (ogives, bar charts).

1. Introduction to Statistics: Why It Matters

Statistics is the science of collecting, organizing, analyzing, interpreting, and presenting data to make informed decisions. In Travel and Tourism Management, statistics helps:

• Predict tourist arrivals (e.g., NTC’s annual passenger data).
• Optimize pricing (e.g., Daraz’s dynamic discounts based on demand).
• Assess customer satisfaction (e.g., Pathao’s rider feedback analysis).

Key Definitions

• Population: The entire group being studied (e.g., all hotels in Kathmandu).
• Sample: A representative subset (e.g., 20 hotels surveyed for cleanliness ratings).
• Parameter: A fixed value describing the population (e.g., mean income of all Nepali tourists).
• Statistic: A variable describing the sample (e.g., mean income of surveyed tourists).

2. Types of Data: Qualitative vs. Quantitative

Data is classified based on measurement scale and nature:

A. Qualitative (Categorical) Data

Descriptive data divided into categories (no numerical value).

• Nominal: No order (e.g., hotel star ratings: 1★, 2★, 3★).
• Ordinal: Ordered categories (e.g., customer satisfaction: Poor, Average, Good, Excellent).

Real-World Example:

• eSewa classifies transactions by service type (electricity, water, telecom) — this is nominal data.
• Pathao categorizes riders by vehicle type (bike, car, auto) — ordinal if ordered by capacity.

B. Quantitative Data

Numerical data that can be measured.

• Discrete: Countable values (e.g., number of tourists arriving daily at Tribhuvan Airport).
• Continuous: Measurable values (e.g., weight of luggage in kg, temperature in °C).

Worked Example 1: Classifying Tourism Data Classify the following data collected by NTC:

1. Number of domestic flights per day.
2. Passenger complaints categorized as "delay," "lost baggage," or "rude staff."
3. Average waiting time at immigration (in minutes).
4. Hotel ratings (1 to 5 stars).

Solution:

3. Sources of Data: Primary vs. Secondary

Data can be collected from two primary sources:

A. Primary Data

Collected firsthand for a specific purpose. Advantages:

• Highly relevant to the study.
• Up-to-date and accurate. Disadvantages:
• Time-consuming and expensive.
• Requires skilled personnel.

Methods of Collection: Real-World Example:

• NTC conducts surveys to collect data on tourist satisfaction at airports (primary data).
• Daraz uses customer feedback forms to gather opinions on product quality.

B. Secondary Data

Collected from existing sources for other purposes. Advantages:

• Saves time and money.
• Wider scope of data. Disadvantages:
• May not fit the current study’s needs.
• Risk of outdated or biased data.

Sources: Worked Example 2: Identifying Data Sources A tourism student wants to analyze backpacker trends in Nepal. Identify whether the following sources are primary or secondary:

1. Interviews with 50 backpackers at Thamel.
2. Data from the Nepal Tourism Board’s 2023 report.
3. Observations of backpacker behavior at Pokhara Lake.
4. A study on "Backpacking in Southeast Asia" published in 2020.

Solution:

4. Data Classification: Organizing Raw Data

Raw data is unorganized and meaningless. Classification involves:

1. Grouping data into categories.
2. Arranging data in a meaningful order.
3. Summarizing data for easier analysis.

A. Frequency Distribution

A table showing how often each value occurs. Example: Number of tourists visiting Pokhara per day for a week.

Worked Example 3: Creating a Frequency Table The following data shows the number of days tourists stayed in Nepal (sample of 20 tourists): 5, 7, 3, 8, 6, 4, 9, 5, 7, 6, 8, 4, 5, 6, 7, 9, 10, 5, 6, 8

Solution:

1. Determine classes: Use a range of 2-3 days (e.g., 3-5, 6-8, etc.).
2. Tally frequencies:

B. Ogives (Cumulative Frequency Graphs)

Ogives help find median, quartiles, and percentiles visually.

Types:

1. Less Than Ogive: Shows cumulative frequency below a class.
2. More Than Ogive: Shows cumulative frequency above a class.

Worked Example 4: Drawing Ogives Using the height data from past exam questions:

Solution: Finding the Median:

• Total frequency (N) = 50.
• Median position = $\frac{N}{2}=25$.
• On the less than ogive, locate 25 on the y-axis and drop to the x-axis → Median height ≈ 64.5 cm.

5. Applications in Tourism and Business

A. Real-World Example 1: NTC’s Passenger Traffic Analysis

Problem: NTC wants to classify passenger traffic by season to optimize flight schedules. Data Classification:

• Qualitative: Passenger type (domestic/international).
• Quantitative: Number of passengers per month (discrete).
• Primary Data: Monthly surveys at airports.
• Secondary Data: Historical flight records.

Visualization: Insight: Peak in June (monsoon season) → NTC can increase flights during this period.

B. Real-World Example 2: Daraz’s Inventory Management

Problem: Daraz needs to classify products to manage stock efficiently. Data Classification:

• Qualitative: Product category (electronics, fashion, groceries).
• Quantitative: Sales volume per product (discrete).
• Primary Data: Daily sales tracking.
• Secondary Data: Market trend reports.

Frequency Table:

Insight: Fashion has the highest variability → Daraz can focus on dynamic pricing for this category.

**C. Real-World Example 3: Bank Loan Approvals (Nepal)

Problem: A bank classifies loan applicants to assess risk. Data Classification:

• Qualitative: Employment type (salaried, self-employed, business).
• Quantitative: Income (continuous), loan amount (discrete).
• Primary Data: Applicant interviews.
• Secondary Data: Credit bureau reports.

Decision Tree:

flowchart TD
    A["Loan Applicant"] --> B["Income < Rs. 500,000?"]
    B -->|"Yes"| C["Self-Employed?"]
    C -->|"Yes"| D["Reject (High Risk)"]
    C -->|"No"| E["Approve (Low Risk)"]
    B -->|"No"| F["Business Owner?"]
    F -->|"Yes"| G["Approve with Collateral"]
    F -->|"No"| H["Approve"]

Insight: Salaried applicants with stable income get faster approvals.

6. Common Mistakes to Avoid

1. Misclassifying data: Treating ordinal data as interval (e.g., assuming hotel ratings are numerically equal).
2. Ignoring data sources: Using outdated secondary data (e.g., 2020 tourism trends for 2024 decisions).
3. Incorrect frequency tables: Forgetting to include all classes or miscounting frequencies.
4. Ogive errors: Plotting cumulative frequency against the wrong axis (always x = class boundary, y = cumulative frequency).

Exam Tip: How to Score Full Marks

1. Definitions: Always define terms clearly (e.g., "Primary data is collected directly by the researcher for a specific purpose").
2. Examples: Use real-world tourism/business examples (NTC, Daraz, banks) to illustrate concepts.
3. Visuals: For ogives/frequency tables, label axes clearly and show calculations (e.g., median position).
4. Comparisons: Use tables to distinguish between primary/secondary data or qualitative/quantitative types.
5. Practical Application: In case studies, link data classification to decision-making (e.g., "This classification helps NTC allocate resources efficiently").

Sample Exam Question: "Distinguish between primary and secondary data with examples from the tourism industry. How would a hotel manager use each type to improve operations?"

Model Answer: Primary data is collected firsthand (e.g., a hotel conducting guest satisfaction surveys to measure service quality). Secondary data is existing data (e.g., using Nepal Tourism Board reports to analyze competitor occupancy rates).

• Primary use: The manager can adjust staffing based on real-time feedback.
• Secondary use: The manager can compare performance against industry benchmarks.

Key Formulas to Remember

Summary Table: Data Classification

Final Checklist Before Exam

✅ Can you distinguish primary vs. secondary data with examples? ✅ Can you classify tourism/business data into qualitative/quantitative? ✅ Can you construct a frequency table and draw ogives? ✅ Can you explain how NTC/Daraz use data classification in real decisions? ✅ Do you know how to find the median from an ogive?