This paper uses logistic regression to construct a one-quarter ahead predic
tion model for classical business cycle regimes in the UK. The binary depen
dent variable is obtained by applying simple mechanical rules to date turni
ng points in quarterly real GDP data from 1963 to 1999. Using a range of re
al and financial leading indicators, several parsimonious one-quarter-ahead
models are developed for the GDP regimes, with model selection based on th
e SIC criterion. A veal M4 variable is consistently found to have predictiv
e content. One model that performs well combines this with nominal UK and G
erman short-term interest rates. The role of the latter emphasises the open
nature of the UK economy.