Dynamic Models for Dynamic Theories: The Ins and Outs of Lagged Dependent Variables

Abstract

A lagged dependent variable in an OLS regression is often used as a means of capturing dynamic effects in political processes and as a method for ridding the model of autocorrelation. But recent work contends that the lagged dependent variable specification is too problematic for use in most situations. More specifically, if residual autocorrelation is present, the lagged dependent variable causes the coefficients for explanatory variables to be biased downward. We use a Monte Carlo analysis to assess empirically how much bias is present when a lagged dependent variable is used under a wide variety of circumstances. In our analysis, we compare the performance of the lagged dependent variable model to several other time series models. We show that while the lagged dependent variable is inappropriate in some circumstances, it remains an appropriate model for the dynamic theories often tested by applied analysts. From the analysis, we develop several practical suggestions on when and how to use lagged dependent variables on the right-hand side of a model.

Modeling 25 years of spatio-temporal surface water and inundation dynamics on large river basin scale using time series of Earth observation data

“…tional predictor variable into the model equation. Models in which a lagged-dependent variable is used as an additional predictor variable are referred to as dynamic linear regression models or lagged-dependent variable (LDV) models and are commonly used for the analysis and forecasting of time series data in economics (Keele and Kelly, 2006;Shumway and Stoffer, 2006). The lagged-dependent variable introduces a temporal component into the model, so that the SWE at a given time step is also a function of the SWE of the previous time step in the time series.…”

Grassland and Cropland Net Ecosystem Production of the U.S. Great Plains: Regression Tree Model Development and Comparative Analysis

“…The cross validation method withholds a specific group of flux data (data from a particular flux tower, year, or a random sample of weekly fluxes) from model development as an independent test and the mapping model is developed from the remaining flux dataset. The cross validation approach is widely accepted [52][53][54][55] and has been used in C flux mapping [5,10,11,13,18] and biomass mapping [47,56], as well as to assess expected model performance on unseen data, identify of influential flux towers and years, and to help optimize models to minimize over fitting (using random cross validation) [19,57,58]. Cross validation approaches provide robust accuracy assessments from many independent withheld "test" data, which helps to identify and minimize over fitting or over generalization [59], and allows all of the limited flux towers to be utilized in developing the final mapping models-maximizing mapping accuracy and robustness for crop and grassland NEP.…”

An Approach Toward Public Hospital Performance Assessment

“…LDV is applied purposely to provide robust estimates of the effects of independent variables and yield more accurate parameter estimates. [36] Adding LDV to a regression model has been demonstrated as a veritable way of helping purge error autocorrelation. [37] Furthermore, considering that the endogenous problem is crucial for the robustness of the estimated results, the system GMM is deployed to ensure that the instruments and moment conditions are rational.…”