Collinearity is a situation in which the predictor, or exogenous, variables in a linear regression model are linearly related among themselves or with the intercept term, and this relation may lead to adverse effects on the estimated model parameters, particularly the regression coefficients and their associated standard errors. In practice, researchers often treat correlation between predictor variables as collinearity, but strictly speaking they are not the same; strong correlation implies collinearity, but the opposite is not necessarily true. When there is strong collinearity in a linear regression model, the model estimation procedure is not able to uniquely identify the regression coefficients for highly correlated variables or terms and therefore cannot separate the covariate effects. This lack of identifiability affects the interpretability of the regression model ...

  • Loading...
locked icon

Sign in to access this content

Get a 30 day FREE TRIAL

  • Watch videos from a variety of sources bringing classroom topics to life
  • Read modern, diverse business cases
  • Explore hundreds of books and reference titles