10.4 Design-based and model-based inference

Statistical inference means the action of estimating parameters about a population from sample data.

Two possibilities to proceed:

• model-based (assumes a superpopulation model)
• design-based (assumes randomness in the locations - unweighted sample mean is used to estimate the population mean, and no model parameters need to be fit)

The model-based is best for:

• predictions are required for small areas to be sampled
• available data were not collected randomly

Design-based is best for:

• observations were collected using a spatial random sampling process
• needs for data aggregation
• not sensitive estimates, i.e. for regulatory or legal purposes