Sampling (Random, Systematic, Stratified)

Sampling Overview

Sampling is the process of selecting a smaller group or set of locations from a larger area to collect data during fieldwork. It is essential because it is usually impossible to collect data from every single location in a study area.

The purpose of sampling in geography fieldwork is to gather information that accurately represents the whole area or population being studied. This helps in making reliable conclusions about patterns, trends, or differences.

A key point is that the sample must be representative. This means the data collected should reflect the characteristics of the entire area or population, avoiding bias that could distort results.

Sampling is important because it allows researchers to save time and resources while still collecting trustworthy data that can be used to make valid conclusions about the study area.

Random Sampling

Random sampling gives every location in the study area an equal chance of being selected. This method helps to reduce bias because the choice of sample points is not influenced by the researcher.

To carry out random sampling, you can use tools such as random number generators, or overlay a grid on a map and select coordinates randomly. For example, if you have a grid with numbered squares, you might use a random number generator to pick which squares to sample.

Random sampling is especially useful when the study area is fairly uniform or when you want to avoid any systematic patterns influencing the data.

For instance, if you want to study litter distribution in a park, you could divide the park into grid squares and randomly select 10 squares to survey.

Example: Suppose a park is divided into 100 grid squares numbered 1 to 100. Using a random number generator, you select squares 7, 23, 45, 67, and 89 to collect data on litter presence. This ensures every square had an equal chance of selection, reducing bias.

For example, if a park has 50 grid squares, selecting 5 squares randomly ensures unbiased data collection.

Systematic Sampling

Systematic sampling involves selecting sample locations at regular intervals across the study area. For example, you might choose every 5th house on a street or every 10 metres along a riverbank.

This method is easy to implement and ensures that samples are spread evenly, which can be useful for detecting patterns or changes over distance.

However, there is a risk: if the interval chosen matches a natural pattern in the area, you might miss important variations. For example, if every 5th house is a corner house and you only sample those, your data may not represent the whole street well.

Example: In a study of footpath wear in a park, you might measure wear every 10 metres along a path. This systematic approach provides a clear, even spread of data points.

Example: A river is 100 metres long. You decide to measure water speed every 10 metres, so you take measurements at 0 m, 10 m, 20 m, and so on up to 100 m. This systematic sampling helps identify how water speed changes along the river.

Stratified Sampling

Stratified sampling involves dividing the study area or population into different strata or groups based on a particular characteristic, then sampling proportionally from each group.

This method ensures that all key groups are represented in the sample, making the data more reliable, especially when the population is diverse.

For example, if studying housing types in a town, you might divide the area into strata such as detached houses, semi-detached, and flats. You then sample a proportionate number of each type to reflect their presence in the town.

Example: In a coastal study, you might divide the coastline into rocky, sandy, and urban sections. You then select sample points from each section in proportion to their length to ensure all types of coastline are represented.

Example: A town has 60% detached houses, 30% semi-detached, and 10% flats. If you want to sample 100 houses, you would select 60 detached, 30 semi-detached, and 10 flats to reflect the actual distribution.