tailieunhanh - Handbook of Economic Forecasting part 95

Handbook of Economic Forecasting part 95. Research on forecasting methods has made important progress over recent years and these developments are brought together in the Handbook of Economic Forecasting. The handbook covers developments in how forecasts are constructed based on multivariate time-series models, dynamic factor models, nonlinear models and combination methods. The handbook also includes chapters on forecast evaluation, including evaluation of point forecasts and probability forecasts and contains chapters on survey forecasts and volatility forecasts. Areas of applications of forecasts covered in the handbook include economics, finance and marketing | 914 M. Marcellino Chauvet 1998 found a good performance also for the factor MS model in tracking the recession of 1990 using the proper version of Zt t in that context. This is basically the only forecasting application of the factor MS models described in Section so that further research is needed to close the gap. For example SW s procedure for the CLI construction could be implemented using Kim and Nelson s 1998 MS version of the factor model or a switching element could be introduced in the SW s VAR Equations 46 and 47 . The MS model can also be used to derive analytic forecasts of recession or expansion duration. Suppose that xt follows the simpler MS model in 9 - 11 and that it is known that in period t the economy is in a recession . st 1. Then Pr st 1 1 xt . x1 pn Pr st 2 1 st 1 1 xt . X1 Pr st 2 1 st 1 1 xt . x1 Pr st 1 1 xt .x p2n 57 and the probability that the recession ends in period t n is Pr st n 0 st n-1 1 . st 1 1 xt . x1 1 - pup-1. 58 Instead if 11 is substituted with 18 . the state probabilities are time-varying then Pr st n 0 St n-1 1 . st 1 1 xt . . . x1 n 1 1 - P11 i n p11 t 59 j 1 with exp 9yt j -1 I P11 t j E --------- ---------- I xt . x1 yt . y1 . 60 1 exp 0yt j-1 It follows that an estimator of the expected remaining duration of the recession t in period t is given by T E t st 1 i 1 - pn t i fl pn t j 61 i 1 j 1 which simplifies to T E t st 1 i 1 - P11 p1-1 62 for constant probabilities. An interesting issue is therefore whether the leading indicators are useful to predict t or not. Ch. 16 Leading Indicators 915 To conclude Bayesian methods for the estimation of Markov switching models were developed by Albert and Chib 1993a McCulloch and Tsay 1994 Filardo and Gordon 1994 and several other authors see . Filardo and Gordon 1999 for a comparison of Bayesian linear MS and factor models for coincident indicators and Canova 2004 Chapter 11 for an overview. Yet to the best of our knowledge there are no applications to forecasting .