Post Your Answer

Single linear regression method can be used if the outcome of variable Y has a linear relationship with the variable X or if the residuals are uncorrelated. Some of the important things to consider while conducting a single linear regression method are normally distributed residuals and issues with influential cases. Assumptions of multiple regression test include, regression residuals should be normally distributed, a linear relationship between the dependent and the independent variables.

Geeta, another assumption to be considered while performing a single linear regression test is that the data needs to display homoscedasticity.

Gopalakrishna, the assumption you mentioned does not hold good for a single linear regression test. It is the assumption of multiple linear regression method. Some of the other assumptions that should be considered while using multiple regression test are (1) the data should not show multicollinearity. This occurs when you have two or more independent variables that are correlated with each other. (2) There should not be any significant outliers, or influential points.