R-squared is the percent of price variation in our dataset that is captured by the model. It is a percent from 0-100%. A high R-squared means that the model did a good job at explaining the variation between properties. A low R-squared means that the model couldn’t capture a lot of the reasons that there are price differences among homes in the area. The appraiser should rely on his area expertise to consider additional adjustments.
Updated over a week ago