Linear Regression

  • Bryan Kestenbaum

Learning Objectives

  1. 1.

    A regression line is identified by the smallest sum of squared distances from the data.

  2. 2.

    A residual is the difference between the data predicted from a model and the actual data.

  3. 3.

    Potential pitfalls in fitting a linear regression model are influential data points and nonlinear associations.

  4. 4.

    In a multiple linear regression model each coefficient represents the independent association of the covariate with the outcome variable, holding all other variables constant.

  5. 5.

    The null hypothesis for a coefficient in a simple linear regression model is that the coefficient is equal to 0.

  6. 6.

    Confounding can be detected by a substantial change in the coefficient of interest after including the potential confounding variable in the multiple regression model.



Linear Regression Model Multiple Regression Model Grocery Store Lower Glomerular Filtration Rate Fitted Regression Line 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 3.
    Lindner A, Charra B, Sherrard DJ, Scribner BH. Accelerated atherosclerosis in prolonged maintenance hemodialysis. N Engl J Med. Mar 28 1974;290(13):697–701.CrossRefPubMedGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.University of WashingtonSeattleUSA

Personalised recommendations