Inference with Dependent Data in Accounting and Finance Applications

We review developments in conducting inference for model parameters in the presence of intertemporal and spatial dependence with an emphasis on panel data applications. We review the use of heteroscedasticity and autocorrelation consistent (HAC) standard error estimators, which include the standard clustered and multi-way clustered estimators, and discuss alternative sample-splitting inference procedures, which include the Fama-Macbeth procedure, within this context. We outline pros and cons of the different procedures. We then illustrate the properties of the discussed procedures within a simulation experiment designed to mimic the type of firm-level panel that might be encountered in finance and accounting applications. Our conclusion, based on the theoretical properties and simulation performance among readily available alternatives, is that sample-splitting procedures with suitably chosen splits are likely to offer the most reliable guide in terms of delivering robust inferential statements with approximately correct coverage properties in the types of large heterogeneous panels many researchers are likely to face