Elementary Statistics for Public Administration An Applied Perspective

Using linear regression requires assumptions that must be met.The criteria for using regression is discussed including the need for the dependent variable to be interval and to have a linear relationship with the independent variable(s).Omitting relevant variables and problems are discussed, along with explaining the importance of the error term in a regression.Detecting multicollinearity in the R Commander is illustrated, along with implications of and solutions for multicollinearity.The effects of heteroscedasticity are discussed with an illustration of it.