A1 Vertaisarvioitu alkuperäisartikkeli tieteellisessä lehdessä
Predicting U.S. Recessions with Dynamic Binary Response Models
Tekijät: Kauppi Heikki, Saikkonen Pentti
Kustantaja: MIT Press
Julkaisuvuosi: 2008
Journal: Review of Economics and Statistics
Tietokannassa oleva lehden nimi: REVIEW OF ECONOMICS AND STATISTICS
Lehden akronyymi: REV ECON STAT
Vuosikerta: 90
Numero: 4
Aloitussivu: 777
Lopetussivu: 791
Sivujen määrä: 15
ISSN: 0034-6535
eISSN: 1530-9142
DOI: https://doi.org/10.1162/rest.90.4.777
Tiivistelmä
We develop dynamic binary probit models and apply them for predicting U.S. recessions using the interest rate spread as the driving predictor. The new models use lags of the binary response (a recession dummy) to forecast its future values and allow for the potential forecast power of lags of the underlying conditional probability. We show how multiperiod-ahead forecasts are computed iteratively using the same one-period-ahead model. Iterated forecasts that apply specific lags supported by statistical model selection procedures turn out to be more accurate than previously used direct forecasts based on horizon-specific model specifications.
We develop dynamic binary probit models and apply them for predicting U.S. recessions using the interest rate spread as the driving predictor. The new models use lags of the binary response (a recession dummy) to forecast its future values and allow for the potential forecast power of lags of the underlying conditional probability. We show how multiperiod-ahead forecasts are computed iteratively using the same one-period-ahead model. Iterated forecasts that apply specific lags supported by statistical model selection procedures turn out to be more accurate than previously used direct forecasts based on horizon-specific model specifications.
Turun yliopiston Tutkimustietojärjestelmän portaali