In fixed-design ordinary least squares with a full-column-rank design matrix , the fitted response is , where
The regression leverage of observation is the diagonal entry of this hat matrix. Since is an orthogonal projection, lies between zero and one, and . Thus is the average regression leverage. These values depend on the design matrix, before any responses are observed.
If the errors have zero expectation and covariance matrix , the regression residual vector is , and idempotence gives
For simple linear regression with an intercept and a nonconstant predictor,
An observation far from the predictor sample mean has large regression leverage: it can pull the fitted regression function toward itself and therefore have a small regression residual. Large regression leverage, a regression outlier, and an influential observation describe different properties; their combination, rather than regression leverage alone, determines how much deleting an observation changes the fit.

Ancestors (6)

  1. Statistical modelling
  2. Statistical model
  3. Probability and statistics
  4. Area of mathematics
  5. Mathematics
  6. Home

Synonyms (1)

Discussion (0) New discussion

There are no discussions about this article yet.

Articles by others on the same topic (0)

There are currently no matching articles.