Multicollinearity in Multiple Regression

Statistics Help for Dissertation Students & Researchers

Regression and Multicollinearity

     Multicollinearity in regression occurs when predictor variables (independent variables) in the regression model are more highly correlated with other predictor variables than with the dependent variable. Multicollinearity does not adversely affect the regression equation if the purpose of your research is only to predict the dependent variable from a set of predictor variables. In this case the predictions in your regression will still be accurate, and the overall R2 will give you an indication of how well the predictor variables in your model predict the dependent variable. Multicollinearity does not affect the goodness of fit and the goodness of prediction. Request Statistics Help Today
 

     In regression, multicollinearity can be a problem if the purpose of your study is to estimate the contributions of individual predictors. When multicollinearity is present, p values can be misleading and the regression coefficients’ confidence intervals will be very wide and may vary dramatically with the addition or exclusion of just one case/participant. If this is the case, removing any highly correlated terms from the model will greatly affect the estimated coefficients of the other highly correlated terms. Multicollinearity inflates the variances of the parameter estimates. This may lead to lack of statistical significance of individual independent variables even though the overall model may be significant. This is especially true for small and moderate sample sizes. Such problems will result in incorrect conclusions about relationships between independent and dependent variables. This is a mistake you don’t want to make in your study. Contact us today and we will evaluate your regression analysis for multicollinearity.
Request Research & Statistics Help Today!