This paper models UK stock market returns in a smooth transition regression (STR)
framework. A variety of financial and macroeconomic series are employed that are assumed
to influence UK stock returns, namely GDP, interest rates, inflation, money supply and US
stock prices. STR models are estimated where the linearity hypothesis is strongly rejected for
at least one transition variable. These non-linear models describe the in-sample movements
of the stock returns series better than the corresponding linear model. Moreover, the US stock
market appears to play an important role in determining the UK stock market returns regime.