This paper presents an empirical microstructure model of bid and ask quotes that features discreteness, random costs of market making, and ARCH volatility effects. Applied to intraday quotes at 15‐minute intervals for Alcoa (a randomly chosen Dow stock), the results show that quote exposure costs contain stochastic components that are persistent and large relative to the deterministic intraday “U” components. Analysis of the filtered estimates of the system suggest that bid and ask costs contain common components, and that these costs reflect risk as proxied by ARCH variance forecasts.

This paper proposes a dynamic model of bid and ask quotes that incorporates a stochastic cost of market-making, discreteness (restriction of quotes to a fixed grid) and clustering (the tendency of quotes to lie on `natural' multiples of the tick size). The Gibbs sampler provides a convenient vehicle for estimation. The model is estimated for daily and intradaily US Dollar/Deutschemark Reuters quotes.

This paper presents an empirical microstructure model of bid and ask quotes that features discreteness, random costs of market making, and ARCH volatility effects. Applied to intraday quotes at 15‐minute intervals for Alcoa (a randomly chosen Dow stock), the results show that quote exposure costs contain stochastic components that are persistent and large relative to the deterministic intraday “U” components. Analysis of the filtered estimates of the system suggest that bid and ask costs contain common components, and that these costs reflect risk as proxied by ARCH variance forecasts.