Outlier vs high leverage

An outlier is an observation for which the dependent variable is unusual, while a high leverage observation is an observation for which the independent variables are unusual.

Outliers may not largely affect the regression results, while high-leverage observations do.

Outliers can be detected using studentized residuals, and high-leverage observations can be detected using the leverage statistic.

An observation can be an outlier and/or a high-leverage point.

References

Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani. An Introduction to Statistical Learning : with Applications in R. New York :Springer, 2013.