Heteroskedastic refers to a condition in which the variance of the residual term, or error term, in a regression model varies widely. If this is true, it may vary in a systematic way, and there may be some factor that can explain this. If so, then the model may be poorly defined and should be modified so that this systematic variance is explained by one or more additional predictor variables.
Click to rate this post!
[Total: 0 Average: 0]