Very simply, if the dependent variable is time series, it is most likely its present value depends on its past values (i.e. autocorrelated); then it is logically to include lagged values of this dependent variable as explanatory variables and this is the main idea of time series models.

Hi,

You can follow this discussion in this link and I hope it is useful

https://stats.stackexchange.com/questions/52458/inclusion-of-lagged-dependent-variable-in-regression/218017

Best wishes

To solve the autocorrelation problem. One of assumption of least square method is no autocorrelation of residuals.

Very simply, if the dependent variable is time series, it is most likely its present value depends on its past values (i.e. autocorrelated); then it is logically to include lagged values of this dependent variable as explanatory variables and this is the main idea of time series models.

Is there a reason other than autocorrelation remedy?@ Ayman Amin and Alma Braimllari Spaho