On business cycle forecasting

Frontiers of Business Research in China

Table 6 Forecasting the conventional target variable: out-of-sample estimation results

Forecast horizon (months)^a	1	3	6	9	12
Models	Relative QPS
Model with channels (a), (b), and (c) simultaneously^b
AR-Logit-Factor-MIDAS	0.400 (0.000)	0.507 (0.000)	0.580 (0.000)	0.867 (0.002)	1.125 (0.165)
Models with either channel (a) or (b)
ST-Probit-MCF	0.454 (0.000)	0.695 (0.010)	0.959 (0.635)	1.105 (0.265)	1.269 (0.005)
AR-Probit-YS	0.795 (0.000)	0.701 (0.000)	0.696 (0.000)	0.876 (0.199)	1.072 (0.443)
Models without any channel (a), (b) and (c)
ST-Probit-YS-EI	0.886 (0.001)	0.895 (0.006)	0.897 (0.000)	0.980 (0.067)	1.013 (0.018)
ST-Probit-YS	1	1	1	1	1
Models	Relative LPS
Model with channels (a), (b), and (c) simultaneously
AR-Logit-Factor-MIDAS	0.527 (0.001)	0.598 (0.004)	0.618 (0.004)	0.896 (0.006)	1.171 (0.228)
Models with either channel (a) or (b)
ST-Probit-MCF	0.582 (0.013)	0.853 (0.386)	0.943 (0.646)	1.114 (0.365)	1.317 (0.010)
AR-Probit-YS	0.731 (0.000)	0.657 (0.000)	0.616 (0.000)	0.794 (0.045)	1.027 (0.794)
Models without any channel (a), (b) and (c)
ST-Probit-YS-EI	0.908 (0.030)	0.885 (0.009)	0.872 (0.005)	0.975 (0.057)	1.011 (0.012)
ST-Probit-YS	1	1	1	1	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 in the N^th month
^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