Omitting spatial characteristics such as proximity to amenities from hedonic land value models may lead to spatial autocorrelation and biased and inefficient estimators. A spatial autoregressive error model can be used to model the spatial structure of errors arising from omitted spatial effects. This paper demonstrates an alternative approach to modeling land values based on individual and joint misspecification tests using data from Roanoke County in Virginia. Spatial autocorrelation is found in land value models of Roanoke County. Defining neighborhoods based on geographic and socioeconomics characteristics produces better estimates of neighborhood effects on land values than simple distance measures. Implementing a comprehensive set of individual and joint misspecification tests results in better correction for misspecification errors compared to existing practices.