Properties of predictors in overdifferenced nearly nonstationary autoregression

• Daniel Peña Sánchez de Rivera ^[1] ; Ismael Sánchez ^[2]
  1. [1] Universidad Carlos III de Madrid

     Universidad Carlos III de Madrid

     Madrid, España

     
  2. [2] Universitat d'Alacant

     Universitat d'Alacant

     Alicante, España

     
• Localización: Working papers = Documentos de trabajo: Serie AD, Nº. 8, 1999, págs. 1-25
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • This paper analyzes the effect of overdifferencing a stationary AR(p+1) process whoselargest root is near unity. It is found that if the process is nearly nonstationary, the estimators ofthe overdifferenced model ARIMA (p, 1, 0) are root-T consistent. It is also found that thismisspecified ARIMA (p, 1, 0) has lower predictive mean squared error, to terms of small order,that the properly specified AR(p+1) model due to its parsimony. The advantage of theoverdifferenced predictor depends on the remaining roots, the prediction horizon, and the meanof the process.