Handling missing prices in a thinly traded stock market: Implications for the specification of event study methods

This paper employs a simulation approach to provide new evidence on how thin trading affects the specification of the event study methods in a thinly traded environment. We examine the properties of the returns computed with alternative procedures for handling missing prices as well as their impact on the specification of the event study methods. We use the simulation approach to assess the specification of different methods. The results indicate that the way missing prices are approximated clearly affects the estimated abnormal returns and the consequent test statistics. The increase of variance in the event period needs to be taken into account when estimating standard deviations.