Everything is related to everything else, but near things are more related than distant things.

• Objects (or regions) near each other are more likely to be similar to one another
Objects (or regions) that are distant from each other are more likely to be different from each other
• This aspect of nature keeps coming up again and again in GIS!

In theory, a random sample is best. Its the "gold standard".

• Each location has equal chance of being selected (Unbiased)
Easy to do, randomly select 𝑥,𝑦 coordinates
• A foundational assumption of many statistical tests

Can be difficult to implement in practice.

• There is a chance, that all samples will miss important features
• May be barriers to accessing some features
• Remote or rugged terrain
• Private or restricted property
• Systematic under-responses

A random starting point is chosen and a fixed sampling interval is used.

• Randomly select first of 3 students
• Then select every 3rd after that
• Choose a random starting point
• Then draw equally spaced grid

A random starting point is chosen and a fixed sampling interval is used.

• General premise behind remote sensing (satellite data collection)
• Can be a good for areas that contain few features and abrupt boundaries
• e.g., Agricultural fields
• Not ideal for attributes that exhibit periodicity
• e.g., Roads

A random starting point is chosen and a fixed sampling interval is used.

• General premise behind remote sensing (satellite data collection)
• Can be a good for areas that contain few features and abrupt boundaries
• e.g., Agricultural fields
• Not ideal for attributes that exhibit periodicity
• e.g., Roads

Helps to address the issues with systematic sampling by sampling at random locations, but still applying some "systematic bias"

• Create a systematic sampling grid, then take random samples within cells
• Divide a population by certain attributes, then take random samples from sub-populations
• Gender, race, age, political party, etc.

Helps to address the issues with systematic sampling by sampling at random locations, but still applying some "systematic bias"

• Can avoid over/under sampling regularly repeating features
• Account for important factors

Intense sampling of features in clusters around a number of selected locations

• Locations can be selected for specific features:
• e.g., Shopping centers, known history of invasive species
• Or, locations can be selected at random across the grid
• More efficient use of time and resources
• May not be representative

Most commonly used along line features like roads, rivers

• Allows you to focus your efforts on features of interest
• Requires understanding of spatial structure for maximum effectiveness

The number of samples required is a function of how similar units of that population are.

• Spatial structure can vary wildly across a landscape
• A little knowledge of your study area will help you to establish ways to best stratify to maximize returns with minimal effort
• Need to balance effective coverage with the cost (in $ or time)
• Eg. short vs. long census form

Spatial interpolation only makes sense for a continuous field with numeric values.

• Rainfall, temperature, pressure
• Estimate between weather stations
• Elevation between measured locations
• With qualitative data, this can be problematic

Best applied to discrete samples of continuous quantitative variables.

• Elevation
• Temperature
• Precipitation

Calculates the "density" of discrete point observations/samples and converts to a raster surface

• Shows the probability of occurrence at any given location
• Weight cells by "value" of points
• Often applied to counts of qualitative data
• Disease outbreaks
• Crime data