Skip to main content

Table 2 In-sample estimation results: AUC

From: On business cycle forecasting

Forecast horizon (months)a 1 3 6 9 12
Models AUC
 Model with channels (a), (b), and (c) simultaneouslyb
  AR-Logit-Factor-MIDAS 0.980 (0.000) 0.980 (0.000) 0.980 (0.000) 0.981 (0.000) 0.981 (0.000)
 Models with either channel (a) or (b)
  ST-Probit-MCF 0.970 (0.000) 0.971 (0.000) 0.970 (0.000) 0.969 (0.000) 0.964 (0.000)
  AR-Probit-YS 0.912 (0.000) 0.916 (0.000) 0.927 (0.000) 0.917 (0.000) 0.923 (0.000)
 Models without any channel (a), (b) and (c)
  ST-Probit-YS-EI 0.890 (0.000) 0.888 (0.000) 0.900 (0.000) 0.897 (0.000) 0.912 (0.000)
  ST-Probit-YS 0.863 (0.000) 0.864 (0.000) 0.868 (0.000) 0.871 (0.000) 0.893 (0.000)
  1. a For each forecast horizon N (where N = 1, 3, 6, 9, 12), we evaluate the ability of each model to forecast the probability of a recession within the next N months
  2. bChannel (a): using a flexible function form by including a lagged recession probability into a dynamic Logit or Probit model of recession forecasting; Channel (b): employing a dynamic factor model to extract common factors from many monthly or weekly economic and financial variables; Channel (c): applying MIDAS to incorporate the mixed-frequency common factors in the dynamic Logit framework