Proximity-Adjusted WLC: spatially explicit weighted linear combination

Strengths

• •Explicitly models spatial heterogeneity of preferences
• •Single reference location parameter is interpretable and adjustable
• •Reduces to standard WLC when all alternatives are equidistant: no discontinuity

Limitations

• •Reference location must be specified a priori: result is sensitive to this choice
• •Rank reversal is structural (adding alternatives redistributes weights)
• •Operates on point locations only in base formulation; area or polygon alternatives require centroid approximation

Assumptions to verify

• •A meaningful reference location can be justified (e.g. city centre, service hub, decision maker's location)
• •Euclidean distance is an appropriate proximity measure (flat terrain, no barriers)
• •Criterion values are positive (linear-max normalisation requirement)
• •Decision maker accepts that spatial proximity modifies effective criterion importance

When not to use

• •Non-spatial problem: alternatives have no geographic location → use SAW
• •Reference location cannot be justified → spatial bias is arbitrary
• •All alternatives are equidistant from any plausible reference → standard WLC is equivalent and simpler

How to cite