What is the primary difference between quantitative and qualitative data?

Quantitative data consists of numerical measurements that allow for statistical analysis, whereas qualitative data is descriptive and focuses on meanings, opinions, and observations.

When should a researcher choose systematic sampling over random sampling?

Systematic sampling is preferred when the researcher wants to ensure even coverage across a whole study area or along a transect, as it is easier and quicker to implement than generating random coordinates.

How does primary data differ from secondary data in terms of reliability?

Primary data reliability is known because the researcher controls the collection method, whereas secondary data reliability is uncertain because the original collection conditions and biases are often unknown.

What is a common error when conducting an Environmental Quality Survey (EQS)?

A common error is relying on a single person's subjective judgment, which introduces bias; this should be corrected by having multiple people complete the survey and using the mode or average score.

What risk is associated with a small sample size in data collection?

A small sample size may not be representative of the whole population, leading to inaccurate conclusions and low validity of the research findings.

Why is it a mistake to ignore secondary data entirely in a geographical enquiry?

Ignoring secondary data prevents the researcher from understanding historical trends or comparing their specific site to a wider regional or national context.

Define 'Stratified Sampling'.

Stratified sampling is a method where the population is divided into sub-groups (strata) based on specific characteristics, and samples are taken from each group in proportion to their size in the total population.

What is a 'Bipolar Scale' in the context of data collection?

A bipolar scale is a rating system used in surveys (like EQS) that ranges between two opposite extremes, such as $-3$ (very poor) to $+3$ (excellent), with $0$ as a neutral point.

What is a 'Risk Assessment'?

A risk assessment is a process of identifying potential hazards during fieldwork, evaluating the level of risk they pose, and determining the necessary precautions to minimize those risks.

Why is random sampling considered the 'least biased' method?

It is the least biased because every possible sample point has an equal chance of being selected, removing the researcher's subconscious preferences from the selection process.

Data Collection | OCR GCSE Geography

Data Collection

Summary

Data collection is the systematic process of gathering information from various sources to answer research questions, test hypotheses, and evaluate outcomes. It involves choosing between primary and secondary sources, selecting quantitative or qualitative formats, and applying rigorous sampling techniques to ensure the resulting data is both reliable and representative of the study area.

1. Definition & Core Concepts

Primary Data refers to original information collected firsthand by the researcher specifically for the current study. This ensures the data is up-to-date and directly relevant to the research objectives, though it can be time-consuming and resource-intensive to gather.

Secondary Data is information that already exists, having been collected by others for different purposes, such as census records, weather reports, or academic journals. While it is cost-effective and provides historical context, the researcher has no control over its original quality or potential bias.

Quantitative Data consists of numerical values and measurements that can be statistically analyzed. Examples include river velocity readings, traffic counts, or closed-ended questionnaire responses that provide objective, measurable evidence.

Qualitative Data involves descriptive, non-numerical information that captures meanings, opinions, and observations. This includes field sketches, open-ended interview transcripts, and photographs, offering depth and context that numbers alone cannot provide.

2. Primary Collection Methods

Questionnaires and Interviews are used to gather human perspectives through open questions (allowing free-form answers) or closed questions (limiting responses to specific options). While questionnaires can reach large samples quickly, interviews provide more in-depth qualitative insights.

Environmental Quality Surveys (EQS) use subjective scoring systems, such as bipolar scales (e.g., $-3$ to $+3$ ), to assess the aesthetic or functional quality of a site. Because these rely on human judgment, they are prone to individual bias, which can be mitigated by averaging scores from multiple observers.

Field Observations involve the direct recording of physical phenomena through sketches, photography, and standardized measurements. These methods capture the 'real-world' state of a geographical feature at a specific point in time.

3. Sampling Strategies

Diagram showing Random (scattered), Systematic (grid-like), and Stratified (grouped by zone) sampling patterns.

4. Key Distinctions

5. Exam Strategy & Tips

6. Common Pitfalls & Misconceptions

Data Collection

Summary

1. Definition & Core Concepts

2. Primary Collection Methods

3. Sampling Strategies

Random Sampling ensures that every member of a population or every point in a study area has an equal probability of being selected. This is the most effective method for reducing researcher bias, although it may accidentally leave large areas of a site unexamined.

Systematic Sampling involves selecting subjects or locations at regular, pre-defined intervals, such as every $10$ meters along a transect. It is straightforward to implement and ensures even coverage across a study area, but it can introduce bias if the interval happens to coincide with a recurring pattern in the environment.

Stratified Sampling divides the study area or population into distinct sub-groups (strata) based on known characteristics, then samples proportionally from each. This method allows for accurate comparisons between different groups, provided that the proportions of the total population are known beforehand.

Diagram showing Random (scattered), Systematic (grid-like), and Stratified (grouped by zone) sampling patterns.

4. Key Distinctions

Understanding the trade-offs between different data types and sources is essential for designing a valid geographical enquiry.

Feature	Primary Data	Secondary Data
Relevance	High (tailored to enquiry)	Variable (collected for other purposes)
Reliability	Known (methodology is controlled)	Uncertain (quality control unknown)
Cost/Time	High (requires fieldwork)	Low (often free and instant)
Currency	Up-to-date	May be obsolete
Feature	Quantitative	Qualitative
---	---	---
Nature	Numerical/Statistical	Descriptive/Textual
Objectivity	High (less researcher bias)	Low (subject to interpretation)
Sample Size	Large (easier to process)	Small (time-intensive analysis)

5. Exam Strategy & Tips

Justify Sampling: In exam answers, always explain why a specific sampling method was chosen. For example, 'Systematic sampling was used to ensure the entire length of the beach was covered at equal intervals.'
Address Subjectivity: If a question asks about the limitations of an Environmental Quality Survey, mention that it is subjective and explain how to improve it (e.g., by using a group consensus or calculating the mode of multiple surveys).
Safety First: Always link data collection methods to a Risk Assessment. Identify a specific hazard (e.g., slippery rocks), the risk it poses (e.g., injury from falling), and the management strategy (e.g., wearing sturdy footwear).
Check for Bias: Be prepared to evaluate if a sample size is large enough to be representative. Small samples often lead to skewed results that do not reflect the true nature of the population or environment.

6. Common Pitfalls & Misconceptions

Confusing Reliability and Validity: Reliability refers to the consistency of the results (can the study be repeated?), while validity refers to the accuracy (does the data actually measure what it claims to?). A study can be reliable but invalid if the equipment is calibrated incorrectly.

Sampling Bias: Students often assume random sampling is 'perfect,' but if the sample size is too small, it can miss significant features entirely. Conversely, systematic sampling can be biased if the interval matches a natural rhythm, such as sampling only at the peaks of sand dunes.

Over-reliance on Secondary Data: While secondary data is convenient, it may contain biases from the original author or be outdated, leading to incorrect conclusions if not cross-referenced with primary observations.