Comments - Linear Models Don’t have to Fit Exactly for P-Values To Be Accurate, Right, and Useful - AnalyticBridge2019-04-20T14:49:38Zhttps://www.analyticbridge.datasciencecentral.com/profiles/comment/feed?attachedTo=2004291%3ABlogPost%3A374045&xn_auth=no"Independent variables and ou…tag:www.analyticbridge.datasciencecentral.com,2017-11-13:2004291:Comment:3740792017-11-13T17:10:09.020ZWayne G. Fischer, PhDhttps://www.analyticbridge.datasciencecentral.com/profile/WayneGFischerPhD
<p>"<span>Independent variables and outcome variables should have a linear relationship among them." Wrong. "Linear" in (multiple) linear regression refers to the relationship between the outcome (dependent) variable and the unknown (to be estimated) *parameters* in the model. The model must be *linear* in the unknown parameters. There are many models that are *nonlinear* in the independent variables that can be transformed such that they are linear in the unknown parameters.</span></p>
<p>"<span>Independent variables and outcome variables should have a linear relationship among them." Wrong. "Linear" in (multiple) linear regression refers to the relationship between the outcome (dependent) variable and the unknown (to be estimated) *parameters* in the model. The model must be *linear* in the unknown parameters. There are many models that are *nonlinear* in the independent variables that can be transformed such that they are linear in the unknown parameters.</span></p>